feat: 项目初始化.

.gitignore

@@ -0,0 +1,11 @@
+.dodsrc
+
+__pycache__/
+
+data/
+
+*.pdf
+
+*.tif
+
+*.tiff

HLS_SuPER/HLS_PER.py

@@ -0,0 +1,317 @@
+# -*- coding: utf-8 -*-
+"""
+===============================================================================
+HLS Processing and Exporting Reformatted Data (HLS_PER)
+
+This module contains functions to conduct subsetting and quality filtering of 
+search results.
+-------------------------------------------------------------------------------
+Authors: Cole Krehbiel, Mahsa Jami, and Erik Bolch
+Last Updated: 2024-09-18
+===============================================================================
+"""
+
+import os
+import sys
+import logging
+
+import numpy as np
+from datetime import datetime as dt
+import xarray as xr
+import rioxarray as rxr
+import dask.distributed
+
+
+def create_output_name(url, band_dict):
+    """
+    Uses HLS default naming scheme to generate an output name with common band names.
+    This allows for easier stacking of bands from both collections.
+    """
+    # Get Necessary Strings
+    prod = url.split("/")[4].split(".")[0]
+    asset = url.split("/")[-1].split(".")[-2]
+    # Add: 获取影像DOY以备影像归档
+    time = url.split("/")[-1].split(".")[3]
+    file_doy = time[:8]
+    # Hard-coded one off for Fmask name incase it is not in the band_dict but is needed for masking
+    # 翻译：硬编码一个Fmask名称, 以防它不在band_dict中但需要用于掩膜处理
+    if asset == "Fmask":
+        output_name = f"{'.'.join(url.split('/')[-1].split('.')[:-2])}.FMASK.subset.tif"
+    else:
+        for key, value in band_dict[prod].items():
+            if value == asset:
+                output_name = (
+                    f"{'.'.join(url.split('/')[-1].split('.')[:-2])}.{key}.subset.tif"
+                )
+    return [output_name, file_doy]
+
+
+def open_hls(url, roi=None, scale=True, chunk_size=dict(band=1, x=512, y=512)):
+    """
+    Generic Function to open an HLS COG and clip to ROI. For consistent scaling, this must be done manually.
+    Some HLS Landsat scenes have the metadata in the wrong location.
+    """
+    # Open using rioxarray
+    da = rxr.open_rasterio(url, chunks=chunk_size, mask_and_scale=False).squeeze(
+        "band", drop=True
+    )
+
+    # Reproject ROI and Clip if ROI is provided
+    if roi is not None:
+        roi = roi.to_crs(da.spatial_ref.crs_wkt)
+        da = da.rio.clip(roi.geometry.values, roi.crs, all_touched=True)
+
+    # Apply Scale Factor if desired for non-quality layer
+    if scale and "Fmask" not in url:
+        # Mask Fill Values
+        da = xr.where(da == -9999, np.nan, da)
+        # Scale Data
+        da = da * 0.0001
+        # Remove Scale Factor After Scaling - Prevents Double Scaling
+        da.attrs["scale_factor"] = 1.0
+
+    # Add Scale Factor to Attributes Manually - This will overwrite/add if the data is missing.
+    if not scale and "Fmask" not in url:
+        da.attrs["scale_factor"] = 0.0001
+
+    return da
+
+
+def create_quality_mask(quality_data, bit_nums: list = [0, 1, 2, 3, 4, 5]):
+    """
+    Uses the Fmask layer and bit numbers to create a binary mask of good pixels.
+    By default, bits 0-5 are used.
+    """
+    mask_array = np.zeros((quality_data.shape[0], quality_data.shape[1]))
+    # Remove/Mask Fill Values and Convert to Integer
+    quality_data = np.nan_to_num(quality_data, 0).astype(np.int8)
+    for bit in bit_nums:
+        # Create a Single Binary Mask Layer
+        mask_temp = np.array(quality_data) & 1 << bit > 0
+        mask_array = np.logical_or(mask_array, mask_temp)
+    return mask_array
+
+
+def process_granule(
+    granule_urls,
+    roi,
+    quality_filter,
+    scale,
+    output_dir,
+    band_dict,
+    bit_nums=[0, 1, 2, 3, 4, 5],
+    chunk_size=dict(band=1, x=512, y=512),
+):
+    """
+    Processes a list of HLS asset urls for a single granule.
+    """
+
+    # Setup Logging
+    logging.basicConfig(
+        level=logging.INFO,
+        format="%(levelname)s:%(asctime)s ||| %(message)s",
+        handlers=[logging.StreamHandler(sys.stdout)],
+    )
+
+    # Check if all Outputs Exist for a Granule
+    if not all(
+        os.path.isfile(
+            f"{output_dir}/{create_output_name(url, band_dict)[1]}/{create_output_name(url, band_dict)[0]}"
+        )
+        for url in granule_urls
+    ):
+
+        # First Handle Quality Layer
+        if quality_filter:
+            # Generate Quality Layer URL
+            split_asset = granule_urls[0].split("/")[-1].split(".")
+            split_asset[-2] = "Fmask"
+            quality_url = (
+                f"{'/'.join(granule_urls[0].split('/')[:-1])}/{'.'.join(split_asset)}"
+            )
+
+            # Check if File exists in Output Directory
+            output_name = create_output_name(quality_url, band_dict)[0]
+            # Add: 以影像DOY为子目录归档同日影像
+            file_doy = create_output_name(quality_url, band_dict)[1]
+            output_dir = f"{output_dir}/{file_doy}"
+            if not os.path.isdir(output_dir):
+                os.makedirs(output_dir)
+            output_file = f"{output_dir}/{output_name}"
+
+            # Open Quality Layer
+            qa_da = open_hls(quality_url, roi, scale, chunk_size)
+
+            # Check if quality asset is already processed
+            if not os.path.isfile(output_file):
+                # Write Output
+                qa_da.rio.to_raster(raster_path=output_file, driver="COG")
+            else:
+                logging.info(
+                    f"Existing file {output_name} found in {output_dir}. Skipping."
+                )
+
+            # Remove Quality Layer from Granule Asset List if Present
+            granule_urls = [asset for asset in granule_urls if asset != quality_url]
+
+            # Create Quality Mask
+            qa_mask = create_quality_mask(qa_da, bit_nums=bit_nums)
+
+        # Process Remaining Assets
+
+        for url in granule_urls:
+            # Check if File exists in Output Directory
+            output_name = create_output_name(url, band_dict)
+            output_file = f"{output_dir}/{output_name}"
+
+            # Check if scene is already processed
+            if not os.path.isfile(output_file):
+                # Open Asset
+                da = open_hls(url, roi, scale, chunk_size)
+
+                # Apply Quality Mask if Desired
+                if quality_filter:
+                    da = da.where(~qa_mask)
+
+                # Write Output
+                da.rio.to_raster(raster_path=output_file, driver="COG")
+            else:
+                logging.info(
+                    f"Existing file {output_name} found in {output_dir}. Skipping."
+                )
+    else:
+        logging.info(
+            f"All assets related to {granule_urls[0].split('/')[-1]} are already processed, skipping."
+        )
+
+
+def build_hls_xarray_timeseries(
+    hls_cog_list, mask_and_scale=True, chunk_size=dict(band=1, x=512, y=512)
+):
+    """
+    Builds a single band timeseries using xarray for a list of HLS COGs. Dependent on file naming convention.
+    Works on SuPERScript named files. Files need common naming bands corresponding HLSS and HLSL bands,
+    e.g. HLSL30 Band 5 (NIR1) and HLSS30 Band 8A (NIR1)
+    """
+    # Define Band(s)
+    bands = [filename.split(".")[6] for filename in hls_cog_list]
+
+    # Make sure all files in list are the same band
+    if not all(band == bands[0] for band in bands):
+        raise ValueError("All listed files must be of the same band.")
+
+    band_name = bands[0]
+
+    # Create Time Variable
+    try:
+        time_list = [
+            dt.strptime(filename.split(".")[3], "%Y%jT%H%M%S")
+            for filename in hls_cog_list
+        ]
+    except ValueError:
+        print("A COG does not have a valid date string in the filename.")
+
+    time = xr.Variable("time", time_list)
+
+    timeseries_da = xr.concat(
+        [
+            rxr.open_rasterio(
+                filename, mask_and_scale=mask_and_scale, chunks=chunk_size
+            ).squeeze("band", drop=True)
+            for filename in hls_cog_list
+        ],
+        dim=time,
+    )
+    timeseries_da.name = band_name
+
+    return timeseries_da
+
+
+def create_timeseries_dataset(hls_file_dir, output_type, output_dir=None):
+    """
+    Creates an xarray dataset timeseries from a directory of HLS COGs.
+    Writes to a netcdf output. Currently only works for HLS SuPER outputs.
+    """
+
+    # Setup Logging
+    logging.basicConfig(
+        level=logging.INFO,
+        format="%(levelname)s:%(asctime)s ||| %(message)s",
+        handlers=[logging.StreamHandler(sys.stdout)],
+    )
+
+    # List Files in Directory
+    all_files = [file for file in os.listdir(hls_file_dir) if file.endswith(".tif")]
+
+    # Create Dictionary of Files by Band
+    file_dict = {}
+    for file in all_files:
+        tile = file.split(".")[2]
+        band = file.split(".")[6]
+        full_path = os.path.join(hls_file_dir, file)
+        if tile not in file_dict:
+            file_dict[tile] = {}
+        if band not in file_dict[tile]:
+            file_dict[tile][band] = []
+        file_dict[tile][band].append(full_path)
+
+    # logging.info(f"{file_dict}")
+
+    # Check that all bands within each tile have the same number of observations
+    for tile, bands in file_dict.items():
+        q_obs = {band: len(files) for band, files in bands.items()}
+        if not all(q == list(q_obs.values())[0] for q in q_obs.values()):
+            logging.info(
+                f"Not all bands in {tile} have the same number of observations."
+            )
+            logging.info(f"{q_obs}")
+
+    # Loop through each tile and build timeseries output
+
+    for tile, bands in file_dict.items():
+        dataset = xr.Dataset()
+
+        timeseries_dict = {
+            band: dask.delayed(build_hls_xarray_timeseries)(files)
+            for band, files in bands.items()
+        }
+        timeseries_dict = dask.compute(timeseries_dict)[0]
+        dataset = xr.Dataset(timeseries_dict)
+
+        # Set up CF-Compliant Coordinate Attributes
+        dataset.attrs["Conventions"] = "CF-1.6"
+        dataset.attrs["title"] = "HLS SuPER Timeseries Dataset"
+        dataset.attrs["institution"] = "LP DAAC"
+
+        dataset.x.attrs["axis"] = "X"
+        dataset.x.attrs["standard_name"] = "projection_x_coordinate"
+        dataset.x.attrs["long_name"] = "x-coordinate in projected coordinate system"
+        dataset.x.attrs["units"] = "m"
+
+        dataset.y.attrs["axis"] = "Y"
+        dataset.y.attrs["standard_name"] = "projection_y_coordinate"
+        dataset.y.attrs["long_name"] = "y-coordinate in projected coordinate system"
+        dataset.y.attrs["units"] = "m"
+
+        dataset.time.attrs["axis"] = "Z"
+        dataset.time.attrs["standard_name"] = "time"
+        dataset.time.attrs["long_name"] = "time"
+
+        # Get first and last date
+        first_date = (
+            dataset.time.data[0].astype("M8[ms]").astype(dt).strftime("%Y-%m-%d")
+        )
+        final_date = (
+            dataset.time.data[-1].astype("M8[ms]").astype(dt).strftime("%Y-%m-%d")
+        )
+
+        # Write Outputs
+        # if output_type == "NC4":
+        output_path = os.path.join(
+            output_dir, f"HLS.{tile}.{first_date}.{final_date}.subset.nc"
+        )
+        dataset.to_netcdf(output_path)
+        # elif output_type == "ZARR":
+        #     output_path = os.path.join(output_dir, "hls_timeseries_dataset.zarr")
+        #     dataset.to_zarr(output_path)
+        logging.info(f"Output saved to {output_path}")

HLS_SuPER/HLS_Su.py

@@ -0,0 +1,89 @@
+# -*- coding: utf-8 -*-
+"""
+===============================================================================
+This module contains functions related to searching and preprocessing HLS data.
+
+-------------------------------------------------------------------------------                        
+Authors: Mahsa Jami, Cole Krehbiel, and Erik Bolch
+Contact: lpdaac@usgs.gov                                                   
+Last Updated: 2024-09-18                                    
+===============================================================================
+"""
+
+# Import necessary packages
+import numpy as np
+import earthaccess
+
+
+# Main function to search and filter HLS data
+def hls_search(roi: list, band_dict: dict, dates=None, cloud_cover=None, log=False):
+    """
+    This function uses earthaccess to search for HLS data using an roi and temporal parameter, filter by cloud cover and delivers a list of results urls for the selected bands.
+    """
+    # Search for data
+    results = earthaccess.search_data(
+        short_name=list(band_dict.keys()),  # Band dict contains shortnames as keys
+        polygon=roi,
+        temporal=dates,
+    )
+
+    # Filter by cloud cover
+    if cloud_cover:
+        results = hls_cc_filter(results, cloud_cover)
+
+    # Get results urls
+    results_urls = [granule.data_links() for granule in results]
+
+    # Flatten url list
+    # results_urls = [item for sublist in results_urls for item in sublist]
+
+    # Filter url list based on selected bands
+    selected_results_urls = [
+        get_selected_bands_urls(granule_urls, band_dict)
+        for granule_urls in results_urls
+    ]
+    return selected_results_urls
+
+
+# Filter earthaccess results based on cloud cover threshold
+def hls_cc_filter(results, cc_threshold):
+    """
+    This function filters a list of earthaccess results based on a cloud cover threshold.
+    """
+    cc = []
+    for result in results:
+        # Retrieve Cloud Cover from json, convert to float and place in numpy array
+        cc.append(
+            float(
+                next(
+                    (
+                        aa
+                        for aa in result["umm"]["AdditionalAttributes"]
+                        if aa.get("Name") == "CLOUD_COVERAGE"
+                    ),
+                    None,
+                )["Values"][0]
+            )
+        )
+    cc = np.array(cc)
+    # Find indices based on cloud cover threshold
+    cc_indices = np.where(cc <= cc_threshold)
+    # Filter results based on indices
+    return [results[i] for i in cc_indices[0]]
+
+
+# Filter results urls based on selected bands
+def get_selected_bands_urls(url_list, band_dict):
+    """
+    This function filters a list of results urls based on HLS collection and selected bands.
+    """
+    selected_bands_urls = []
+    # Loop through urls
+    for url in url_list:
+        # Filter bands based on band dictionary
+        for collection, nested_dict in band_dict.items():
+            if collection in url:
+                for band in nested_dict.values():
+                    if band in url:
+                        selected_bands_urls.append(url)
+    return selected_bands_urls

HLS_SuPER/HLS_SuPER.py

@@ -0,0 +1,594 @@
+# -*- coding: utf-8 -*-
+"""
+===============================================================================
+HLS Subsetting, Processing, and Exporting Reformatted Data Prep Script                         
+Authors: Cole Krehbiel, Mahsa Jami, and Erik Bolch
+Contact: lpdaac@usgs.gov
+Last Updated: 2024-09-18  
+===============================================================================
+"""
+
+# Possible Future Improvements:
+# TODO Improve CF-1.6 NetCDF Compliance
+# TODO Improve behavior around deletion of cogs when a netcdf is requested
+# TODO Add ZARR as output option
+
+import argparse
+import sys
+import os
+import shutil
+import logging
+import time
+import json
+
+import earthaccess
+from shapely.geometry import polygon, box
+import geopandas as gpd
+from datetime import datetime as dt
+import dask.distributed
+
+from HLS_Su import hls_search
+from HLS_PER import process_granule, create_timeseries_dataset
+
+
+def parse_arguments():
+    """
+    Function to parse command line input arguments.
+    """
+    parser = argparse.ArgumentParser(
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+        description="Performs Spatial/Temporal/Band Subsetting, Processing, and Customized Exporting for HLS V2.0 files",
+    )
+
+    # roi: Region of interest as shapefile, geojson, or comma separated LL Lon, LL Lat, UR Lon, UR Lat
+    parser.add_argument(
+        "-roi",
+        type=str,
+        required=True,
+        help="(Required) Region of Interest (ROI) for spatial subset. \
+                        Valid inputs are: (1) a geojson or shapefile (absolute path to file required if not in same directory as this script), or \
+                        (2) bounding box coordinates: 'LowerLeft_lon,LowerLeft_lat,UpperRight_lon,UpperRight_lat'\
+                        NOTE: Negative coordinates MUST be written in single quotation marks '-120,43,-118,48'\
+                        NOTE 2: If providing an absolute path with spaces in directory names, please use double quotation marks "
+        " ",
+    )
+
+    # dir: Directory to save the files to
+    parser.add_argument(
+        "-dir",
+        required=False,
+        help="Directory to export output HLS files to.",
+        default=os.getcwd(),
+    )
+
+    # start: Start Date
+    parser.add_argument(
+        "-start",
+        required=False,
+        help="Start date for time period of interest: valid format is yyyy-mm-dd (e.g. 2020-10-20).",
+        default="2014-04-03",
+    )
+
+    # end: End Date
+    parser.add_argument(
+        "-end",
+        required=False,
+        help="Start date for time period of interest: valid format is yyyy-mm-dd (e.g. 2022-10-24).",
+        default=dt.today().strftime("%Y-%m-%d"),
+    )
+
+    # prod: product(s) desired to be downloaded
+    parser.add_argument(
+        "-prod",
+        choices=["HLSS30", "HLSL30", "both"],
+        required=False,
+        help="Desired product(s) to be subset and processed.",
+        default="both",
+    )
+
+    # layers: layers desired to be processed within the products selected
+    parser.add_argument(
+        "-bands",
+        required=False,
+        help="Desired layers to be processed. Valid inputs are ALL, COASTAL-AEROSOL, BLUE, GREEN, RED, RED-EDGE1, RED-EDGE2, RED-EDGE3, NIR1, SWIR1, SWIR2, CIRRUS, TIR1, TIR2, WATER-VAPOR, FMASK, VZA, VAA, SZA, SAA. To request multiple layers, provide them in comma separated format with no spaces. Unsure of the names for your bands?--check out the README which contains a table of all bands and band names.",
+        default="ALL",
+    )
+
+    # cc: maximum cloud cover (%) allowed to be returned (by scene)
+    parser.add_argument(
+        "-cc",
+        required=False,
+        help="Maximum (scene-level) cloud cover (percent) allowed for returned observations (e.g. 35). Valid range: 0 to 100 (integers only)",
+        default="100",
+    )
+
+    # qf: quality filter flag: filter out poor quality data yes/no
+    parser.add_argument(
+        "-qf",
+        choices=["True", "False"],
+        required=False,
+        help="Flag to quality filter before exporting output files (see README for quality filtering performed).",
+        default="True",
+    )
+
+    # sf: scale factor flag: Scale data or leave unscaled yes/no
+    parser.add_argument(
+        "-scale",
+        choices=["True", "False"],
+        required=False,
+        help="Flag to apply scale factor to layers before exporting output files. This is generally unecessary as most applications will scale automatically.",
+        default="False",
+    )
+
+    # of: output file format
+    parser.add_argument(
+        "-of",
+        choices=["COG", "NC4", "ZARR"],
+        required=False,
+        help="Define the desired output file format",
+        default="COG",
+    )
+
+    # chunksize: chunk size for processing with dask
+    parser.add_argument(
+        "-cs",
+        type=str,
+        help="Chunksize for processing scenes with dask in format 'band,x,y'. This is used to provide chunk_size argument to rioxarray.open_rasterio to improve processing speed.\
+            For example: '1,512,512' (native hls chunk size) provides better performance for ROIs that fall within a single scene, while '1,3600,3600' (full HLS scene) provides better performance for \
+            larger ROIs that span multiple scenes. The default is '1,512,512', but this can lead to a very large task list for large ROIs.",
+        default="1,512,512",
+    )
+
+    # logfile: Optional logfile path
+    parser.add_argument(
+        "-logfile",
+        required=False,
+        help="Optional path to output logfile. If not provided, logging will only be to the console.",
+    )
+
+    return parser.parse_args()
+
+
+def format_roi(roi):
+    """
+    Determines if submitted ROI is a file or bbox coordinates.
+
+    If a file, opens a GeoJSON or shapefile and creates a list of polygon vertices in the correct order. If the file has multiple polygons it will use a unary union convex hull of the external bounds.
+
+    If bbox coordinates, creates a geodataframe with a single Polygon geometry.
+
+    Returns a geopandas dataframe for clipping and a list of vertices for searching.
+    """
+    if os.path.isfile(roi):  # and roi.endswith(("geojson", "shp")):
+        print(roi)
+        try:
+            # Open ROI if file
+            roi = gpd.read_file(roi)
+            if len(roi) > 1:
+                # Merge all Polygon geometries and create external boundary
+                logging.info(
+                    "Multiple polygons detected. Creating single geometry of external coordinates."
+                )
+                single_geometry = roi.unary_union.convex_hull
+                roi = gpd.GeoDataFrame(geometry=[single_geometry], crs=roi.crs)
+                logging.info(roi)
+            # Check if ROI is in Geographic CRS, if not, convert to it
+            if roi.crs.is_geographic:
+                # List Vertices in correct order for search
+                vertices_list = list(roi.geometry[0].exterior.coords)
+
+            else:
+                roi_geographic = roi.to_crs("EPSG:4326")
+                logging.info(
+                    "Note: ROI submitted is being converted to Geographic CRS (EPSG:4326)"
+                )
+                vertices_list = list(roi_geographic.geometry[0].exterior.coords)
+        except (FileNotFoundError, ValueError):
+            sys.exit(
+                f"The GeoJSON/shapefile is either not valid or could not be found.\nPlease double check the name and provide the absolute path to the file or make sure that it is located in {os.getcwd()}"
+            )
+    else:
+        # If bbox coordinates are submitted
+        bbox = tuple(map(float, roi.strip("'\"").split(",")))
+        print(bbox)
+
+        # Convert bbox to a geodataframe for clipping
+        roi = gpd.GeoDataFrame(geometry=[box(*bbox)], crs="EPSG:4326")
+
+        vertices_list = list(roi.geometry[0].exterior.coords)
+
+    return (roi, vertices_list)
+
+
+def format_dates(start, end):
+    # Strip Quotes
+    start = start.strip("'").strip('"')
+    end = end.strip("'").strip('"')
+    # Convert to datetime
+    try:
+        start = dt.strptime(start, "%Y-%m-%d")
+        end = dt.strptime(end, "%Y-%m-%d")
+    except ValueError:
+        sys.exit(
+            "A date format is not valid. The valid format is ISO 8601: YYYY-MM-DD (e.g. 2020-10-20)"
+        )
+    if start > end:
+        sys.exit(
+            f"The Start Date requested: {start} is after the End Date Requested: {end}."
+        )
+    else:
+        dates = (start.strftime("%Y-%m-%d"), end.strftime("%Y-%m-%d"))
+    return dates
+
+
+def format_cloud_cover(cc):
+    try:
+        cc = int(cc.strip("'").strip('"'))
+    except ValueError:
+        sys.exit(
+            f"{cc} is not a valid input for filtering by cloud cover (e.g. 35). Valid range: 0 to 100 (integers only)"
+        )
+
+    # Validate that cc is in the valid range (0-100)
+    if cc < 0 or cc > 100:
+        sys.exit(
+            f"{cc} is not a valid input option for filtering by cloud cover (e.g. 35). Valid range: 0 to 100 (integers only)"
+        )
+    return cc
+
+
+def str_to_bool(value):
+    """
+    Converts a string to a boolean.
+    Accepts 'True', 'true', '1' as True.
+    Accepts 'False', 'false', '0' as False.
+    """
+    if isinstance(value, str):
+        if value.lower() in ("true", "1"):
+            return True
+        elif value.lower() in ("false", "0"):
+            return False
+    raise ValueError(f"Cannot convert {value} to boolean.")
+
+
+def create_band_dict(prod, bands):
+    """
+    Creates a dictionary of bands and common band names for each collection requested.
+    """
+    shortname = {"HLSS30": "HLSS30.v2.0", "HLSL30": "HLSL30.v2.0"}
+
+    # Create a dictionary with product name and shortname
+    if prod == "both":
+        prods = shortname
+    else:
+        prods = {prod: shortname[prod]}
+
+    # Strip spacing, quotes, make all upper case and create a list
+    bands = bands.strip(" ").strip("'").strip('"').upper()
+    band_list = bands.split(",")
+
+    # Create a LUT dict including the HLS product bands mapped to names
+    lut = {
+        "HLSS30": {
+            "COASTAL-AEROSOL": "B01",
+            "BLUE": "B02",
+            "GREEN": "B03",
+            "RED": "B04",
+            "RED-EDGE1": "B05",
+            "RED-EDGE2": "B06",
+            "RED-EDGE3": "B07",
+            "NIR-Broad": "B08",
+            "NIR1": "B8A",
+            "WATER-VAPOR": "B09",
+            "CIRRUS": "B10",
+            "SWIR1": "B11",
+            "SWIR2": "B12",
+            "FMASK": "Fmask",
+            "VZA": "VZA",
+            "VAA": "VAA",
+            "SZA": "SZA",
+            "SAA": "SAA",
+        },
+        "HLSL30": {
+            "COASTAL-AEROSOL": "B01",
+            "BLUE": "B02",
+            "GREEN": "B03",
+            "RED": "B04",
+            "NIR1": "B05",
+            "SWIR1": "B06",
+            "SWIR2": "B07",
+            "CIRRUS": "B09",
+            "TIR1": "B10",
+            "TIR2": "B11",
+            "FMASK": "Fmask",
+            "VZA": "VZA",
+            "VAA": "VAA",
+            "SZA": "SZA",
+            "SAA": "SAA",
+        },
+    }
+
+    # List of all available/acceptable band names
+    all_bands = [
+        "ALL",
+        "COASTAL-AEROSOL",
+        "BLUE",
+        "GREEN",
+        "RED",
+        "RED-EDGE1",
+        "RED-EDGE2",
+        "RED-EDGE3",
+        "NIR1",
+        "SWIR1",
+        "SWIR2",
+        "CIRRUS",
+        "TIR1",
+        "TIR2",
+        "WATER-VAPOR",
+        "FMASK",
+        "VZA",
+        "VAA",
+        "SZA",
+        "SAA",
+    ]
+
+    # Validate that bands are named correctly
+    for b in band_list:
+        if b not in all_bands:
+            sys.exit(
+                f"Band: {b} is not a valid input option. Valid inputs are {all_bands}. To request multiple layers, provide them in comma separated format with no spaces. Unsure of the names for your bands?--check out the README which contains a table of all bands and band names."
+            )
+
+    # Set up a dictionary of band names and numbers by product
+    band_dict = {}
+    for p in prods:
+        band_dict[p] = {}
+        for b in band_list:
+            if b == "ALL":
+                band_dict[p] = lut[p]
+            else:
+                try:
+                    band_dict[p][b] = lut[p][b]
+                except ValueError:
+                    print(f"Product {p} does not contain band {b}")
+    return band_dict
+
+
+def format_chunksize(chunksize):
+    """
+    Converts comma-separated chunksize string to dictionary.
+    """
+    keys = ["band", "x", "y"]
+    values = list(map(int, chunksize.strip("'\"").split(",")))
+
+    if len(values) != len(keys):
+        raise ValueError(
+            "Chunksize must provide band, x and y (3) values separated by commas."
+        )
+
+    return dict(zip(keys, values))
+
+
+def confirm_action(prompt):
+    """
+    Prompts the user to confirm an action.
+    """
+    while True:
+        response = input(prompt).lower()
+        if response in ["y", "yes"]:
+            return True
+        elif response in ["n", "no"]:
+            return False
+        else:
+            print("Invalid input. Please enter 'y' or 'n'.")
+
+
+def setup_dask_environment():
+    """
+    Passes RIO environment variables to dask workers for authentication.
+    """
+    import os
+    import rasterio
+
+    cookie_file_path = os.path.expanduser("~/cookies.txt")
+
+    global env
+    gdal_config = {
+        "GDAL_HTTP_UNSAFESSL": "YES",
+        "GDAL_HTTP_COOKIEFILE": cookie_file_path,
+        "GDAL_HTTP_COOKIEJAR": cookie_file_path,
+        "GDAL_DISABLE_READDIR_ON_OPEN": "YES",
+        "CPL_VSIL_CURL_ALLOWED_EXTENSIONS": "TIF",
+        "GDAL_HTTP_MAX_RETRY": "10",
+        "GDAL_HTTP_RETRY_DELAY": "0.5",
+        "GDAL_HTTP_TIMEOUT": "300",
+    }
+
+    env = rasterio.Env(**gdal_config)
+    env.__enter__()
+
+
+def main():
+    """
+    Main function to run the HLS SuPER script.
+    """
+
+    # Parse arguments
+    args = parse_arguments()
+
+    # Configure logging
+    log_handlers = [logging.StreamHandler(sys.stdout)]
+    if args.logfile:
+        log_handlers.append(logging.FileHandler(args.logfile))
+
+    logging.basicConfig(
+        level=logging.INFO,
+        format="%(levelname)s:%(asctime)s ||| %(message)s",
+        handlers=log_handlers,
+    )
+
+    # Handle Login Credentials with earthaccess
+    earthaccess.login(persist=True)
+
+    # Start Log
+    logging.info("HLS SuPER script started")
+
+    # Format ROI
+    roi, vl = format_roi(args.roi)
+    logging.info("Region of Interest formatted successfully")
+
+    # Set Output Directory
+    if args.dir is not None:
+        output_dir = os.path.normpath(args.dir.strip("'").strip('"')) + os.sep
+    else:
+        # Defaults to the current directory
+        output_dir = os.getcwd() + os.sep
+
+    logging.info(f"Output directory set to: {output_dir}")
+
+    # Format/Validate Dates
+    dates = format_dates(args.start, args.end)
+    logging.info(f"Date Parameters: {dates}")
+
+    # Create Product/Band Dictionary
+    band_dict = create_band_dict(args.prod, args.bands)
+    logging.info(f"Products/Bands Selected: {band_dict}")
+
+    # Format Cloud Cover
+    cc = format_cloud_cover(args.cc)
+    logging.info(f"Cloud Cover Filter <= {cc}")
+
+    # Quality Filtering
+    qf = str_to_bool(args.qf)
+    logging.info(f"Quality Filtering: {qf}")
+
+    # Scale Factor
+    scale = str_to_bool(args.scale)
+    logging.info(f"Apply Scale Factor: {scale}")
+
+    # Chunk Size
+    chunk_size = format_chunksize(args.cs)
+    logging.info(f"Chunk Size: {chunk_size}")
+
+    # Output File Type
+    if args.of not in ["COG", "NC4"]:
+        sys.exit(
+            f"Output format {args.of} is not a valid output format. Please choose from 'COG', 'NC4'."
+        )
+
+    logging.info(f"Output format: {args.of}")
+
+    # Search for Data and Save Results
+    results_urls_file = os.path.join(output_dir, "hls_super_results_urls.json")
+    use_existing_file = False
+
+    if os.path.isfile(results_urls_file):
+        logging.info(f"Results url list already exists in {output_dir}.")
+        # Confirm if user wants to use existing file.
+        if confirm_action(
+            f"Do you want to use the existing results file ({results_urls_file})? (y/n)"
+        ):
+            use_existing_file = True
+
+        else:
+            if not confirm_action(
+                "Do you want to overwrite the existing results file? (y/n)"
+            ):
+                sys.exit(
+                    f"Processing aborted. Please move, rename, or remove existing file: {results_urls_file}."
+                )
+
+    if use_existing_file:
+        logging.info("Using existing results file.")
+        with open(results_urls_file, "r") as file:
+            results_urls = json.load(file)
+
+    else:
+        logging.info("Searching for data...")
+        results_urls = hls_search(
+            roi=vl, band_dict=band_dict, dates=dates, cloud_cover=cc
+        )
+        logging.info(f"Writing search results to {results_urls_file}")
+        with open(results_urls_file, "w") as file:
+            json.dump(results_urls, file)
+
+    total_assets = sum(len(sublist) for sublist in results_urls)
+
+    if cc:
+        logging.info(
+            f"{len(results_urls)} granules remain after cloud filtering. {total_assets} assets will be processed."
+        )
+    else:
+        logging.info(f"{total_assets} assets will be processed.")
+
+    # Confirm Processing
+    if not confirm_action("Do you want to proceed with processing? (y/n)"):
+        sys.exit("Processing aborted.")
+
+    # Initialize Dask Cluster
+    client = dask.distributed.Client()
+
+    # Setup Dask Environment (GDAL Configs)
+    client.run(setup_dask_environment)
+
+    logging.info(
+        f"Dask environment setup successfully. View dashboard: {client.dashboard_link}."
+    )
+
+    # Scatter Results Results url
+    client.scatter(results_urls)
+
+    # If NC4, create a temporary directory to store COGs
+    if args.of == "NC4":
+        cog_dir = os.path.join(output_dir, "temp")
+        if not os.path.exists(cog_dir):
+            os.makedirs(cog_dir, exist_ok=True)
+        else:
+            if not confirm_action(
+                "Temporary directory to store COGs already exists. Use these files to create NC4 outputs? (y/n)"
+            ):
+                sys.exit(
+                    f"Processing aborted. Please remove existing directory: {cog_dir}."
+                )
+
+    else:
+        cog_dir = output_dir
+
+    # Process Granules
+    start_time = time.time()
+    logging.info("Processing...")
+    tasks = [
+        dask.delayed(process_granule)(
+            granule_url,
+            roi=roi,
+            quality_filter=qf,
+            scale=scale,
+            output_dir=cog_dir,
+            band_dict=band_dict,
+            bit_nums=[0, 1, 2, 3, 4, 5],
+            chunk_size=chunk_size,
+        )
+        for granule_url in results_urls
+    ]
+    dask.compute(*tasks)
+
+    # Create Timeseries Dataset if NC4
+    if args.of == "NC4":
+        logging.info("Creating timeseries dataset...")
+        create_timeseries_dataset(cog_dir, output_type=args.of, output_dir=output_dir)
+
+    # Close Dask Client
+    client.close()
+
+    # Remove Temporary COGs if NC4
+    if args.of == "NC4":
+        logging.info("Timeseries Dataset Created. Removing Temporary Files...")
+        shutil.rmtree(cog_dir)
+
+    # End Timer
+    total_time = time.time() - start_time
+    logging.info(f"Processing complete. Total time: {round(total_time,2)}s, ")
+
+
+if __name__ == "__main__":
+    main()

HLS_SuPER/README.md

@@ -0,0 +1,254 @@
+# HLS Subsetting, Processing, and Exporting Reformatted Data Prep Script  
+
+---
+
+## Objective  
+
+NASA's Land Processes Distributed Active Archive Center (LP DAAC) archives and distributes Harmonized Landsat Sentinel-2 (HLS) version 2.0 products in the LP DAAC Cumulus cloud archive as Cloud Optimized GeoTIFFs (COG). the HLS_SuPER.py data prep script is a command line-executable Python script that allows users to submit inputs for their desired spatial (GeoJSON, Shapefile, bounding box) region of interest (ROI), time period of interest, and the specific desired product(s) and bands/layers within the HLS products. The script also includes options for cloud screening observations by a user-defined threshold, quality filtering, applying the scale factor to the data, and users can pick between two output file format options:
+
+  1. COG which returns an output for each source file
+  2. NetCDF4 which creates a single output with variables corresponding to bands and stacking all temporal observations for each band.
+  
+To construct these outputs, the input arguments provided by the user in command line are submitted to NASA's Common Metadata Repository API endpoint via the `earthaccess` Python library to find data. The script then returns a .json containing a nested list of all resulting granules with assets nested within for each HLS observation that intersect the user's input parameters. After outputing this file, it is leveraged to access the cloud-native HLS data for each asset, which are clipped to the ROI provided and exported in the desired output file format. Optionally, data can be quality filtered (see section on quality filtering below) and/or scaled. **This script does not support resampling or reprojection.**
+
+### Available Products  
+
+1. Daily 30 meter (m) global HLS Sentinel-2 Multi-spectral Instrument Surface Reflectance - [HLSS30.002](https://doi.org/10.5067/HLS/HLSS30.002)  
+
+2. Daily 30 meter (m) global HLS Landsat 8 Operational Land Imager Surface Reflectance - [HLSL30.002](https://doi.org/10.5067/HLS/HLSL30.002)  
+
+> **Note:** On November 2021, this data prep script is updated to processes Version 2.0 daily 30 meter (m) global HLS Sentinel-2 Multi-spectral Instrument Surface Reflectance (HLSS30) data and Version 2.0 daily 30 m global HLS Landsat 8 OLI Surface Reflectance (HLSL30) data.  
+
+---
+
+## Prerequisites  
+
+1. **Earthdata Login account**  
+    - Create an Earthdata Login account (if you don't already have one) at <https://urs.earthdata.nasa.gov/users/new>
+    - Remember your username and password; you will need them to download or access data during the workshop and beyond.
+2. **A Local Copy of this Repository**
+    - Copy/clone/[download](https://github.com/nasa/HLS-Data-Resources/archive/refs/heads/main.zip) the [HLS-Data-Resources Repository](https://github.com/nasa/HLS-Data-Resources.git). You will need all three of the python scripts downloaded to the same directory on your OS (HLS_Su.py, HLS_PER.py, HLS_SuPER.
+3. **Compatible Python Environment**
+    - See the [Python Environment Setup](#python-environment-setup) section below.
+    - If you have previously set up the [**lpdaac_vitals** environment](https://github.com/nasa/VITALS/blob/main/setup/setup_instructions.md) for a workshop or content from the [VITALS repository](https://github.com/nasa/VITALS/tree/main), you can use that environment for this script as well. 
+
+
+### Python Environment Setup  
+
+For local Python environment setup we recommend using [mamba](https://mamba.readthedocs.io/en/latest/) to manage Python packages. To install *mamba*, download [miniforge](https://github.com/conda-forge/miniforge) for your operating system.  If using Windows, be sure to check the box to "Add mamba to my PATH environment variable" to enable use of mamba directly from your command line interface. **Note that this may cause an issue if you have an existing mamba install through Anaconda.**  
+
+1. Using your preferred command line interface (command prompt, terminal, cmder, etc.) navigate to your local copy of the repository, then type the following to create a compatible Python environment.
+
+    For Windows:
+
+    ```cmd
+    mamba create -n lpdaac_vitals -c conda-forge --yes python=3.10 fiona=1.8.22 gdal hvplot geoviews rioxarray rasterio jupyter geopandas earthaccess jupyter_bokeh h5py h5netcdf spectral scikit-image jupyterlab seaborn dask ray-default
+    ```
+
+    For MacOSX:
+
+    ```cmd
+    mamba create -n lpdaac_vitals -c conda-forge --yes python=3.10 gdal=3.7.2 hvplot geoviews rioxarray rasterio geopandas fiona=1.9.4 jupyter earthaccess jupyter_bokeh h5py h5netcdf spectral scikit-image seaborn jupyterlab dask ray-default ray-dashboard
+    ```
+
+2. Next, activate the Python Environment that you just created.
+
+    ```cmd
+    mamba activate lpdaac_vitals 
+    ```
+**Still having trouble getting a compatible Python environment set up? Contact [LP DAAC User Services](https://lpdaac.usgs.gov/lpdaac-contact-us/).**  
+
+## Script Execution  
+
+1. Once you have completed the prerequisites, open your command line interface navigate to the directory containing the script.
+ 
+2. Ensure your python environment created above is activated.
+
+    ```cmd
+    mamba activate lpdaac_vitals 
+    ```
+
+3.  The script requires an `roi`, which can be either a shapefile, geojson, or list of bbox coordinates (lower left longitude, lower left latitude, upper right longitude, upper right latitude). Other arguments are optional. See below for some examples of how to execute the script.
+
+```cmd
+> python HLS_SuPER.py -roi <insert geojson, shapefile, or bounding box coordinates here> -dir <insert directory to save the output files to>
+```  
+
+> **Note:** After running the script, it will show inputs then conduct a search for results. A prompt for a **y/n** will appear to proceed with processing. This is to ensure that the user is away of the quantity of results/files that will be processed.
+
+### Examples  
+
+#### Region of interest (```-roi```) specified using a geojson file  
+
+```None  
+> python HLS_SuPER.py -roi LA_County.geojson  
+```  
+
+#### Region of interest (```-roi```) specified using a bounding box and save outputs to specified directory  
+
+```None  
+> python HLS_SuPER.py -dir C:\Users\HLS\ -roi '-122.8,42.1,-120.5,43.1'  
+```  
+
+> **Note:** The bounding box is a comma-separated string of LL-Lon, LL-Lat, UR-Lon, UR-Lat.  **Also**, if the first value in your bounding box is negative, you **MUST** use *single* quotations around the bounding box string. If you are using MacOS, you may need to use double quotes followed by single quotes ("'-122.8,42.1,-120.5,43.1'")  
+
+## Additional Script Execution Documentation  
+
+To see the full set of command line arguments and how to use them, type the following in the command prompt:  
+
+```None
+> python HLS_SuPER.py -h  
+
+usage: HLS_SuPER.py [-h] -roi ROI [-dir DIR] [-start START] [-end END]
+                    [-prod {HLSS30,HLSL30,both}] [-bands BANDS] [-cc CC]
+                    [-qf {True,False}] [-scale {True,False}]
+                    [-of {COG,NC4}]  
+...
+```
+
+### Script Arguments  
+
+#### -roi ROI  
+
+```None
+(Required) Region of Interest (ROI) for spatial subset. Valid inputs are: (1) a geojson or shapefile (absolute path to file required if not in same directory as this script), or (2) bounding box coordinates: 'LowerLeft_lon,LowerLeft_lat,UpperRight_lon,UpperRight_lat' NOTE: Negative coordinates MUST be
+written in single quotation marks '-120,43,-118,48'.  
+
+Example  
+> python HLS_SuPER.py -roi '-120,43,-118,48'  
+```  
+
+#### -dir DIR  
+
+```None  
+Directory to save output HLS files to. (default: <directory that the script is executed from>)  
+
+Example  
+> python HLS_SuPER.py -roi '-120,43,-118,48' -dir C:\Users\HLS\  
+```  
+
+#### -start START  
+
+```None  
+Start date for time period of interest: valid format is yyyy-mm-dd (e.g. 2020-10-20). (default: 2014-04-03)  
+
+Example  
+> python HLS_SuPER.py -roi '-120,43,-118,48' -dir C:\Users\HLS\ -start 2020-06-02  
+```  
+
+#### -end END  
+
+```None  
+Start date for time period of interest: valid format is yyyy-mm-dd (e.g. 2020-10-20). (default: current date)  
+
+Example  
+> python HLS_SuPER.py -roi '-120,43,-118,48' -dir C:\Users\HLS\ -start 2020-06-02 -end 2020-10-24  
+```  
+
+#### -prod {HLSS30,HLSL30,both}  
+
+```None  
+Desired product(s) to be subset and processed. (default: both)  
+
+Example  
+> python HLS_SuPER.py -roi '-120,43,-118,48' -dir C:\Users\HLS\ -start 2020-06-02 -end 2020-10-24 -prod both  
+```  
+
+#### -bands BANDS  
+
+```None  
+Desired layers to be processed. Valid inputs are ALL, COASTAL-AEROSOL, BLUE, GREEN, RED, RED-EDGE1, RED-EDGE2, RED-EDGE3, NIR1, SWIR1, SWIR2, CIRRUS, TIR1, TIR2, WATER-VAPOR, FMASK. To request multiple layers, provide them in comma separated format with no spaces. Unsure of the names for your bands?--check out the README which contains a table of all bands and band names. (default: ALL)  
+
+Example  
+> python HLS_SuPER.py -roi '-120,43,-118,48' -dir C:\Users\HLS\ -start 2020-06-02 -end 2020-10-24 -prod both -bands RED,GREEN,BLUE,NIR1  
+```  
+
+#### -cc CC  
+
+```None  
+Maximum cloud cover (percent) allowed for returned observations (e.g. 35). Valid range: 0 to 100 (integers only) (default: 100)  
+
+Example  
+> python HLS_SuPER.py -roi '-120,43,-118,48' -dir C:\Users\HLS\ -start 2020-06-02 -end 2020-10-24 -prod both -bands RED,GREEN,BLUE,NIR1 -cc 50`  
+```  
+
+#### -qf {True,False}  
+
+```None  
+Flag to quality filter before exporting output files (see section below for quality filtering performed). (default: True)  
+
+Example  
+> python HLS_SuPER.py -roi '-120,43,-118,48' -dir C:\Users\HLS\ -start 2020-06-02 -end 2020-10-24 -prod both -bands RED,GREEN,BLUE,NIR1 -cc 50 -qf True  
+```  
+
+#### -scale {True,False}  
+
+```None  
+Flag to apply scale factor to layers before exporting output files. (default: True)  
+
+Example  
+> python HLS_SuPER.py -roi '-120,43,-118,48' -dir C:\Users\HLS\ -start 2020-06-02 -end 2020-10-24 -prod both -bands RED,GREEN,BLUE,NIR1 -cc 50 -qf True -scale False  
+```
+
+#### -of {COG,NC4}  
+
+```None  
+Define the desired output file format (default: COG)  
+
+Example  
+> python HLS_SuPER.py -roi '-120,43,-118,48' -dir C:\Users\HLS\ -start 2020-06-02 -end 2020-10-24 -prod both -bands RED,GREEN,BLUE,NIR1 -cc 50 -qf True -scale False -of NC4  
+```  
+
+### Quality Filtering  
+
+If quality filtering is set to True (default), the following quality filtering will be used:  
+
+- Cloud == 0 (No Cloud)  
+- Cloud shadow == 0 (No Cloud shadow)  
+- Adjacent to cloud/shadow == 0 (No Adjacent to cloud/shadow)
+- Snow/ice == 0 (No Snow/ice)
+- Water == 0 (No Water)
+- aerosol level == Climatology aerosol (No Low, Moderate, and High aerosol level)
+
+
+meaning that any pixel that does not meet the criteria outlined above will be removed and set to `_FillValue` in the output files.  
+
+The quality table for the HLS `Fmask` can be found in section 6.4 of the [HLS V2.0 User Guide](https://lpdaac.usgs.gov/documents/1118/HLS_User_Guide_V2.pdf).  
+
+If you do not want the data to be quality filtered, set argument `qf` to `False`.  
+
+### Output File Formats  
+
+Cloud-Optimized GeoTIFF (COG) is the default output file format. If NetCDF-4 (NC4) is selected by the user as the output file format, the script will export a single NC4 file for each HLS tile returned by the query, in the source HLS projection. 
+
+#### Output File Names  
+
+The standard format  for HLS S30 V2.0 and HLS L30 V2.0 filenames is as follows:  
+**ex:** HLS.S30.T17SLU.2020117T160901.v2.0.B8A.tif  
+> **HLS.S30/HLS.L30**: Product Short Name  
+  **T17SLU**: MGRS Tile ID (T+5-digits)  
+  **2020117T160901**: Julian Date and Time of Acquisition (YYYYDDDTHHMMSS)  
+  **v2.0**: Product Version  
+  **B8A/B05**: Spectral Band  
+  **.tif**: Data Format (Cloud Optimized GeoTIFF)  
+
+For additional information on HLS naming conventions, be sure to check out the [HLS Overview Page](https://lpdaac.usgs.gov/data/get-started-data/collection-overview/missions/harmonized-landsat-sentinel-2-hls-overview/#hls-naming-conventions).  
+
+If you selected COG as the output file format, the output file name will have product specific band names renamed the common names in available bands and include **.subset.tif** at the end of the filename:  
+> HLS.S30.T17SLU.2020117T160901.v2.0.NIR1.subset.tif  
+
+If you selected nc4 as the output file format, the following naming convention will be used:  
+**ex:** HLS.T17SLU.2020-10-24.2020-11-10.subset.nc4  
+> HLS.[MGRS Tile ID].[date of first observation in output file].[date of last observation in output file].subset.nc4  
+
+---
+
+## Contact Info  
+
+Email: <LPDAAC@usgs.gov>  
+Voice: +1-866-573-3222  
+Organization: Land Processes Distributed Active Archive Center (LP DAAC)¹  
+Website: <https://lpdaac.usgs.gov/>  
+Date last modified: 2024-09-18  
+
+¹Work performed under USGS contract 140G0121D0001 for NASA contract NNG14HH33I.  

README.md

@@ -0,0 +1,122 @@
+# NASA EARTHDATA 数据爬取与预处理 —— 以 HLS 数据集为例
+
+## 1 安装 miniforge
+
+### 1.1 miniforge
+
+- miniforge是结合conda与mamba的最小化包，比Anaconda和Miniconda更快更轻量，并且配置命令与原conda基本一致，支持直接使用mamba命令。
+- 简而言之，环境配置效率上，miniforge > Mambaforge (202407已废弃) > Miniconda + Mamba > Miniconda > Anaconda
+
+- 官方仓库地址：https://github.com/conda-forge/miniforge
+- 官方下载地址：https://conda-forge.org/download/
+
+
+### 1.2 配置环境变量
+
+- 为了在控制台中直接使用conda命令, 需要将安装的相关目录配置到Path环境变量中。
+
+```
+D:\program\miniforge3
+D:\program\miniforge3\Scripts
+D:\program\miniforge3\Library\bin
+```
+
+### 1.3 配置权限
+
+- 详细配置与miniconda相同，图文教程地址：https://gis-xh.github.io/my-note/python/01conda/Win11-Miniconda-install/
+- Windows环境下，需要设置虚拟环境文件夹的访问权限为所有用户可访问，否则会出现无法读取虚拟环境文件的问题
+- 具体地：
+  - 设置`D:\program\miniforge3\env`目录为所有用户可访问，具体操作为：右键点击文件夹 -> 属性 -> 安全 -> 编辑 -> 添加 -> 添加所有用户 -> 全选 -> 应用 -> 确定
+
+### 1.4 配置镜像源
+
+- 生成下载源文件的配置文件 (若已经安装过Anaconda/Miniconda，则无需执行此步骤)
+
+```sh
+conda config --set show_channel_urls yes
+```
+
+- 在`C:\Users\实际用户名\`目录找到`.condarc`文件，使用记事本打开，输入如下内容并保存
+
+```
+envs_dirs:
+  - D:\program\miniforge3\envs
+  - 其他路径地址(可选，创建虚拟环境时将会按照顺序查找)
+channels:
+  - defaults
+show_channel_urls: true
+channel_alias: https://mirrors.tuna.tsinghua.edu.cn/anaconda
+default_channels:
+  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
+  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free
+  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/r
+  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/pro
+  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/msys2
+custom_channels:
+  conda-forge: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
+  msys2: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
+  bioconda: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
+  menpo: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
+  pytorch: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
+  simpleitk: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
+```
+
+### 1.5 初始化 conda
+
+- 打开控制台，初始化 PowerShell 与 CMD
+
+```sh
+conda init powershell
+```
+
+```sh
+conda init cmd.exe
+```
+
+## 2 运行环境配置
+
+### 2.1 使用mamba创建并激活虚拟环境
+
+- 克隆虚拟环境 (Windows环境下推荐)
+
+```sh
+mamba env create -f setup/lpdaac_windows.yml
+```
+
+- 激活虚拟环境
+
+```sh
+mamba activate lpdaac_windows
+```
+
+## 3 HLS 数据爬取
+
+### 3.1 账户准备
+
+- 参考自NASA官网示例Demo：https://github.com/nasa/LPDAAC-Data-Resources/blob/main/setup/setup_instructions_python.md
+- 首次运行爬取命令时，需要输入用户名和密码，用户名和密码可以在 [Earthdata](https://urs.earthdata.nasa.gov/) 注册获取。
+- 需要注意的是，密码中最好不要出 `@/#/$/%` 等符号，爬取时可能会出错。
+
+### 3.2 爬取云端数据并在内存中进行预处理
+
+- `-roi`：感兴趣区，需要按照 **左下右上** 的逆时针顺序设置点坐标
+- `-dir`：输出目录，必须是已存在的目录
+- `-start`：开始时间，格式为 `YYYY-MM-DD`
+- `-end`：结束时间，格式为 `YYYY-MM-DD`
+- `-prod`：产品名称，例如 `HLSL30`，`HLSS30`，`both`
+- `-bands`：波段名称，如 `COASTAL-AEROSOL,BLUE,GREEN,RED,NIR1,SWIR1,SWIR2,CIRRUS,TIR1,TIR2,Fmask`
+- `-cc`：筛选影像云量阈值，如 `70`
+- `-qf`：是否使用质量波段过滤云/云阴影像元，默认 `True`
+- `-scale`：是否对影像使用缩放因子，默认 `True`
+
+- 爬取所有光谱波段
+
+```sh
+python .\\HLS_SuPER\\HLS_SuPER.py -roi '113.10114,30.62845,114.24349,31.59081' -dir .\\data\\HLS\\L30 -start 2024-01-01 -end 2024-01-31 -prod HLSL30 -bands COASTAL-AEROSOL,BLUE,GREEN,RED,NIR1,SWIR1,SWIR2,CIRRUS,TIR1,TIR2,Fmask -cc 70 -qf True -scale True
+```
+
+- 仅爬取必要的核心波段
+
+```sh
+python .\\HLS_SuPER\\HLS_SuPER.py -roi '113.10114,30.62845,114.24349,31.59081' -dir .\\data\\HLS\\L30\\subset -start 2024-01-01 -end 2024-01-31 -prod HLSL30 -bands BLUE,GREEN,RED,NIR1,SWIR1,SWIR2 -cc 70 -qf True -scale True
+```

setup/lpdaac_windows.yml

@@ -0,0 +1,420 @@
+name: lpdaac_windows
+channels:
+  - defaults
+  - conda-forge
+dependencies:
+  - affine=2.4.0=pyhd8ed1ab_0
+  - aiobotocore=2.7.0=pyhd8ed1ab_1
+  - aiofiles=22.1.0=pyhd8ed1ab_0
+  - aiohttp=3.8.6=py310h8d17308_1
+  - aiohttp-cors=0.7.0=py_0
+  - aioitertools=0.11.0=pyhd8ed1ab_0
+  - aiosignal=1.3.1=pyhd8ed1ab_0
+  - aiosqlite=0.19.0=pyhd8ed1ab_0
+  - ansicon=1.89.0=py310h5588dad_7
+  - anyio=4.0.0=pyhd8ed1ab_0
+  - argon2-cffi=23.1.0=pyhd8ed1ab_0
+  - argon2-cffi-bindings=21.2.0=py310h8d17308_4
+  - arrow=1.3.0=pyhd8ed1ab_0
+  - asciitree=0.3.3=py_2
+  - asttokens=2.4.1=pyhd8ed1ab_0
+  - async-timeout=4.0.3=pyhd8ed1ab_0
+  - attrs=23.1.0=pyh71513ae_1
+  - aws-c-auth=0.7.3=h0127223_1
+  - aws-c-cal=0.6.1=hfb91821_1
+  - aws-c-common=0.9.0=hcfcfb64_0
+  - aws-c-compression=0.2.17=h04c9df6_2
+  - aws-c-event-stream=0.3.1=h495bb32_4
+  - aws-c-http=0.7.11=hf013885_4
+  - aws-c-io=0.13.32=he824701_1
+  - aws-c-mqtt=0.9.3=h64f41f2_1
+  - aws-c-s3=0.3.14=hb8b96c7_1
+  - aws-c-sdkutils=0.1.12=h04c9df6_1
+  - aws-checksums=0.1.17=h04c9df6_1
+  - aws-crt-cpp=0.21.0=hf1ed06d_5
+  - aws-sdk-cpp=1.10.57=heb7cc7f_19
+  - babel=2.13.1=pyhd8ed1ab_0
+  - backports=1.0=pyhd8ed1ab_3
+  - backports.functools_lru_cache=1.6.5=pyhd8ed1ab_0
+  - beautifulsoup4=4.12.2=pyha770c72_0
+  - bleach=6.1.0=pyhd8ed1ab_0
+  - blessed=1.19.1=pyh95a074a_2
+  - blosc=1.21.5=hdccc3a2_0
+  - bokeh=3.3.0=pyhd8ed1ab_0
+  - boto3=1.28.64=pyhd8ed1ab_0
+  - botocore=1.31.64=pyhd8ed1ab_0
+  - bounded-pool-executor=0.0.3=pyhd8ed1ab_0
+  - branca=0.7.0=pyhd8ed1ab_1
+  - brotli=1.0.9=hcfcfb64_9
+  - brotli-bin=1.0.9=hcfcfb64_9
+  - brotli-python=1.0.9=py310h00ffb61_9
+  - bzip2=1.0.8=hcfcfb64_5
+  - c-ares=1.21.0=hcfcfb64_0
+  - ca-certificates=2023.7.22=h56e8100_0
+  - cached-property=1.5.2=hd8ed1ab_1
+  - cached_property=1.5.2=pyha770c72_1
+  - cachetools=5.3.2=pyhd8ed1ab_0
+  - cairo=1.18.0=h1fef639_0
+  - cartopy=0.22.0=py310hecd3228_1
+  - certifi=2023.7.22=pyhd8ed1ab_0
+  - cffi=1.16.0=py310h8d17308_0
+  - cfitsio=4.3.0=h9b0cee5_0
+  - cftime=1.6.3=py310h3e78b6c_0
+  - charset-normalizer=3.3.2=pyhd8ed1ab_0
+  - click=8.1.7=win_pyh7428d3b_0
+  - click-plugins=1.1.1=py_0
+  - cligj=0.7.2=pyhd8ed1ab_1
+  - cloudpickle=3.0.0=pyhd8ed1ab_0
+  - colorama=0.4.6=pyhd8ed1ab_0
+  - colorcet=3.0.1=pyhd8ed1ab_0
+  - colorful=0.5.4=pyhd8ed1ab_0
+  - comm=0.1.4=pyhd8ed1ab_0
+  - configobj=5.0.8=pyhd8ed1ab_0
+  - contourpy=1.2.0=py310h232114e_0
+  - cryptography=41.0.5=py310h6e82f81_0
+  - cycler=0.12.1=pyhd8ed1ab_0
+  - cytoolz=0.12.2=py310h8d17308_1
+  - dask=2023.10.1=pyhd8ed1ab_0
+  - dask-core=2023.10.1=pyhd8ed1ab_0
+  - datashader=0.16.0=pyhd8ed1ab_0
+  - debugpy=1.8.0=py310h00ffb61_1
+  - decorator=5.1.1=pyhd8ed1ab_0
+  - defusedxml=0.7.1=pyhd8ed1ab_0
+  - distlib=0.3.7=pyhd8ed1ab_0
+  - distributed=2023.10.1=pyhd8ed1ab_0
+  - earthaccess=0.7.1=pyhd8ed1ab_0
+  - entrypoints=0.4=pyhd8ed1ab_0
+  - exceptiongroup=1.1.3=pyhd8ed1ab_0
+  - executing=2.0.1=pyhd8ed1ab_0
+  - expat=2.5.0=h63175ca_1
+  - fasteners=0.17.3=pyhd8ed1ab_0
+  - filelock=3.13.1=pyhd8ed1ab_0
+  - fiona=1.9.5=py310h65cc672_0
+  - folium=0.15.0=pyhd8ed1ab_0
+  - font-ttf-dejavu-sans-mono=2.37=hab24e00_0
+  - font-ttf-inconsolata=3.000=h77eed37_0
+  - font-ttf-source-code-pro=2.038=h77eed37_0
+  - font-ttf-ubuntu=0.83=hab24e00_0
+  - fontconfig=2.14.2=hbde0cde_0
+  - fonts-conda-ecosystem=1=0
+  - fonts-conda-forge=1=0
+  - fonttools=4.44.0=py310h8d17308_0
+  - fqdn=1.5.1=pyhd8ed1ab_0
+  - freetype=2.12.1=hdaf720e_2
+  - freexl=2.0.0=h8276f4a_0
+  - frozenlist=1.4.0=py310h8d17308_1
+  - fsspec=2023.10.0=pyhca7485f_0
+  - gdal=3.7.3=py310haa9213b_2
+  - geopandas=0.14.0=pyhd8ed1ab_1
+  - geopandas-base=0.14.0=pyha770c72_1
+  - geos=3.12.0=h1537add_0
+  - geotiff=1.7.1=hcf4a93f_14
+  - geoviews=1.11.0=pyhd8ed1ab_0
+  - geoviews-core=1.11.0=pyha770c72_0
+  - gettext=0.21.1=h5728263_0
+  - gitdb=4.0.11=pyhd8ed1ab_0
+  - gitpython=3.1.40=pyhd8ed1ab_0
+  - google-api-core=2.13.0=pyhd8ed1ab_0
+  - google-auth=2.23.4=pyhca7485f_0
+  - googleapis-common-protos=1.61.0=pyhd8ed1ab_0
+  - gpustat=1.1.1=pyhd8ed1ab_0
+  - grpcio=1.54.3=py310h8020be6_0
+  - h5netcdf=1.3.0=pyhd8ed1ab_0
+  - h5py=3.10.0=nompi_py310h20f5850_100
+  - hdf4=4.2.15=h5557f11_7
+  - hdf5=1.14.2=nompi_h73e8ff5_100
+  - holoviews=1.18.1=pyhd8ed1ab_0
+  - hvplot=0.9.0=pyhd8ed1ab_0
+  - icu=73.2=h63175ca_0
+  - idna=3.4=pyhd8ed1ab_0
+  - imagecodecs-lite=2019.12.3=py310h3e78b6c_7
+  - imageio=2.31.5=pyh8c1a49c_0
+  - importlib-metadata=6.8.0=pyha770c72_0
+  - importlib_metadata=6.8.0=hd8ed1ab_0
+  - importlib_resources=6.1.1=pyhd8ed1ab_0
+  - intel-openmp=2023.2.0=h57928b3_50497
+  - ipykernel=6.26.0=pyha63f2e9_0
+  - ipython=8.17.2=pyh5737063_0
+  - ipython_genutils=0.2.0=py_1
+  - ipywidgets=8.1.1=pyhd8ed1ab_0
+  - isoduration=20.11.0=pyhd8ed1ab_0
+  - jedi=0.19.1=pyhd8ed1ab_0
+  - jinja2=3.1.2=pyhd8ed1ab_1
+  - jinxed=1.2.0=pyh95a074a_0
+  - jmespath=1.0.1=pyhd8ed1ab_0
+  - joblib=1.3.2=pyhd8ed1ab_0
+  - json5=0.9.14=pyhd8ed1ab_0
+  - jsonpointer=2.4=py310h5588dad_3
+  - jsonschema=4.19.2=pyhd8ed1ab_0
+  - jsonschema-specifications=2023.7.1=pyhd8ed1ab_0
+  - jsonschema-with-format-nongpl=4.19.2=pyhd8ed1ab_0
+  - jupyter=1.0.0=pyhd8ed1ab_10
+  - jupyter-resource-usage=1.0.1=pyhd8ed1ab_0
+  - jupyter-server-mathjax=0.2.6=pyh5bfe37b_1
+  - jupyter_bokeh=3.0.7=pyhd8ed1ab_0
+  - jupyter_client=7.4.9=pyhd8ed1ab_0
+  - jupyter_console=6.6.3=pyhd8ed1ab_0
+  - jupyter_core=5.5.0=py310h5588dad_0
+  - jupyter_events=0.9.0=pyhd8ed1ab_0
+  - jupyter_server=2.10.0=pyhd8ed1ab_0
+  - jupyter_server_fileid=0.9.0=pyhd8ed1ab_0
+  - jupyter_server_terminals=0.4.4=pyhd8ed1ab_1
+  - jupyter_server_ydoc=0.8.0=pyhd8ed1ab_0
+  - jupyter_ydoc=0.2.4=pyhd8ed1ab_0
+  - jupyterlab=3.6.6=pyhd8ed1ab_0
+  - jupyterlab-geojson=3.4.0=pyhd8ed1ab_0
+  - jupyterlab-git=0.44.0=pyhd8ed1ab_0
+  - jupyterlab_pygments=0.2.2=pyhd8ed1ab_0
+  - jupyterlab_server=2.25.1=pyhd8ed1ab_0
+  - jupyterlab_widgets=3.0.9=pyhd8ed1ab_0
+  - kealib=1.5.2=ha10e780_1
+  - kiwisolver=1.4.5=py310h232114e_1
+  - krb5=1.21.2=heb0366b_0
+  - lazy_loader=0.3=pyhd8ed1ab_0
+  - lcms2=2.15=h67d730c_3
+  - lerc=4.0.0=h63175ca_0
+  - libabseil=20230125.3=cxx17_h63175ca_0
+  - libaec=1.1.2=h63175ca_1
+  - libarchive=3.7.2=h6f8411a_0
+  - libarrow=12.0.1=he3e0f11_8_cpu
+  - libblas=3.9.0=19_win64_mkl
+  - libboost-headers=1.82.0=h57928b3_6
+  - libbrotlicommon=1.0.9=hcfcfb64_9
+  - libbrotlidec=1.0.9=hcfcfb64_9
+  - libbrotlienc=1.0.9=hcfcfb64_9
+  - libcblas=3.9.0=19_win64_mkl
+  - libcrc32c=1.1.2=h0e60522_0
+  - libcurl=8.4.0=hd5e4a3a_0
+  - libdeflate=1.19=hcfcfb64_0
+  - libevent=2.1.12=h3671451_1
+  - libexpat=2.5.0=h63175ca_1
+  - libffi=3.4.2=h8ffe710_5
+  - libgdal=3.7.3=h3217549_2
+  - libglib=2.78.1=he8f3873_0
+  - libgoogle-cloud=2.12.0=h00b2bdc_1
+  - libgrpc=1.54.3=ha177ca7_0
+  - libhwloc=2.9.3=default_haede6df_1009
+  - libiconv=1.17=h8ffe710_0
+  - libjpeg-turbo=3.0.0=hcfcfb64_1
+  - libkml=1.3.0=haf3e7a6_1018
+  - liblapack=3.9.0=19_win64_mkl
+  - libnetcdf=4.9.2=nompi_h8284064_112
+  - libpng=1.6.39=h19919ed_0
+  - libpq=16.1=h43585b0_0
+  - libprotobuf=3.21.12=h12be248_2
+  - librttopo=1.1.0=h92c5fdb_14
+  - libsodium=1.0.18=h8d14728_1
+  - libspatialindex=1.9.3=h39d44d4_4
+  - libspatialite=5.1.0=hbf340bc_1
+  - libsqlite=3.44.0=hcfcfb64_0
+  - libssh2=1.11.0=h7dfc565_0
+  - libthrift=0.18.1=h06f6336_2
+  - libtiff=4.6.0=h6e2ebb7_2
+  - libutf8proc=2.8.0=h82a8f57_0
+  - libwebp-base=1.3.2=hcfcfb64_0
+  - libxcb=1.15=hcd874cb_0
+  - libxml2=2.11.5=hc3477c8_1
+  - libzip=1.10.1=h1d365fa_3
+  - libzlib=1.2.13=hcfcfb64_5
+  - linkify-it-py=2.0.0=pyhd8ed1ab_0
+  - llvmlite=0.41.1=py310hb84602e_0
+  - locket=1.0.0=pyhd8ed1ab_0
+  - lz4=4.3.2=py310hbbb2075_1
+  - lz4-c=1.9.4=hcfcfb64_0
+  - lzo=2.10=he774522_1000
+  - m2w64-gcc-libgfortran=5.3.0=6
+  - m2w64-gcc-libs=5.3.0=7
+  - m2w64-gcc-libs-core=5.3.0=7
+  - m2w64-gmp=6.1.0=2
+  - m2w64-libwinpthread-git=5.0.0.4634.697f757=2
+  - mapclassify=2.6.1=pyhd8ed1ab_0
+  - markdown=3.5.1=pyhd8ed1ab_0
+  - markdown-it-py=3.0.0=pyhd8ed1ab_0
+  - markupsafe=2.1.3=py310h8d17308_1
+  - matplotlib-base=3.8.1=py310hc9baf74_0
+  - matplotlib-inline=0.1.6=pyhd8ed1ab_0
+  - mdit-py-plugins=0.4.0=pyhd8ed1ab_0
+  - mdurl=0.1.0=pyhd8ed1ab_0
+  - minizip=4.0.2=h5bed578_0
+  - mistune=3.0.2=pyhd8ed1ab_0
+  - mkl=2023.2.0=h6a75c08_50496
+  - msgpack-python=1.0.6=py310h232114e_0
+  - msys2-conda-epoch=20160418=1
+  - multidict=6.0.4=py310h8d17308_1
+  - multimethod=1.9.1=pyhd8ed1ab_0
+  - multipledispatch=0.6.0=py_0
+  - munch=4.0.0=pyhd8ed1ab_0
+  - munkres=1.1.4=pyh9f0ad1d_0
+  - nbclassic=1.0.0=pyhb4ecaf3_1
+  - nbclient=0.8.0=pyhd8ed1ab_0
+  - nbconvert=7.11.0=pyhd8ed1ab_0
+  - nbconvert-core=7.11.0=pyhd8ed1ab_0
+  - nbconvert-pandoc=7.11.0=pyhd8ed1ab_0
+  - nbdime=3.2.1=pyhd8ed1ab_0
+  - nbformat=5.9.2=pyhd8ed1ab_0
+  - nest-asyncio=1.5.8=pyhd8ed1ab_0
+  - netcdf4=1.6.5=nompi_py310h6477780_100
+  - networkx=3.2.1=pyhd8ed1ab_0
+  - notebook=6.5.6=pyha770c72_0
+  - notebook-shim=0.2.3=pyhd8ed1ab_0
+  - numba=0.58.1=py310h9ccaf4f_0
+  - numcodecs=0.12.1=py310h00ffb61_0
+  - numpy=1.26.0=py310hf667824_0
+  - nvidia-ml-py=12.535.133=pyhd8ed1ab_0
+  - opencensus=0.11.3=pyhd8ed1ab_0
+  - opencensus-context=0.1.3=py310h5588dad_2
+  - openjpeg=2.5.0=h3d672ee_3
+  - openssl=3.1.4=hcfcfb64_0
+  - orc=1.9.0=hada7b9e_1
+  - overrides=7.4.0=pyhd8ed1ab_0
+  - packaging=23.2=pyhd8ed1ab_0
+  - pandas=2.1.2=py310hecd3228_0
+  - pandoc=3.1.3=h57928b3_0
+  - pandocfilters=1.5.0=pyhd8ed1ab_0
+  - panel=1.3.1=pyhd8ed1ab_0
+  - param=2.0.1=pyhca7485f_0
+  - parso=0.8.3=pyhd8ed1ab_0
+  - partd=1.4.1=pyhd8ed1ab_0
+  - pcre2=10.40=h17e33f8_0
+  - pexpect=4.8.0=pyh1a96a4e_2
+  - pickleshare=0.7.5=py_1003
+  - pillow=10.1.0=py310h1e6a543_0
+  - pip=23.3.1=pyhd8ed1ab_0
+  - pixman=0.42.2=h63175ca_0
+  - pkgutil-resolve-name=1.3.10=pyhd8ed1ab_1
+  - platformdirs=3.11.0=pyhd8ed1ab_0
+  - poppler=23.10.0=hc2f3c52_0
+  - poppler-data=0.4.12=hd8ed1ab_0
+  - postgresql=16.1=hc80876b_0
+  - pqdm=0.2.0=pyhd8ed1ab_0
+  - proj=9.3.0=he13c7e8_2
+  - prometheus_client=0.18.0=pyhd8ed1ab_0
+  - prompt-toolkit=3.0.39=pyha770c72_0
+  - prompt_toolkit=3.0.39=hd8ed1ab_0
+  - protobuf=4.21.12=py310h00ffb61_0
+  - psutil=5.9.5=py310h8d17308_1
+  - pthread-stubs=0.4=hcd874cb_1001
+  - pthreads-win32=2.9.1=hfa6e2cd_3
+  - ptyprocess=0.7.0=pyhd3deb0d_0
+  - pure_eval=0.2.2=pyhd8ed1ab_0
+  - py-spy=0.3.14=h975169c_0
+  - pyarrow=12.0.1=py310hd1a9178_8_cpu
+  - pyasn1=0.5.0=pyhd8ed1ab_0
+  - pyasn1-modules=0.3.0=pyhd8ed1ab_0
+  - pycparser=2.21=pyhd8ed1ab_0
+  - pyct=0.4.6=py_0
+  - pyct-core=0.4.6=py_0
+  - pydantic=1.10.13=py310h8d17308_1
+  - pygments=2.16.1=pyhd8ed1ab_0
+  - pykdtree=1.3.9=py310h3e78b6c_1
+  - pyopenssl=23.3.0=pyhd8ed1ab_0
+  - pyparsing=3.1.1=pyhd8ed1ab_0
+  - pyproj=3.6.1=py310hebb2149_4
+  - pyresample=1.27.1=py310hecd3228_2
+  - pyshp=2.3.1=pyhd8ed1ab_0
+  - pysocks=1.7.1=pyh0701188_6
+  - pystac=1.9.0=pyhd8ed1ab_0
+  - pystac-client=0.7.5=pyhd8ed1ab_0
+  - python=3.10.13=h4de0772_0_cpython
+  - python-cmr=0.9.0=pyhd8ed1ab_0
+  - python-dateutil=2.8.2=pyhd8ed1ab_0
+  - python-fastjsonschema=2.18.1=pyhd8ed1ab_0
+  - python-json-logger=2.0.7=pyhd8ed1ab_0
+  - python-tzdata=2023.3=pyhd8ed1ab_0
+  - python_abi=3.10=4_cp310
+  - pytz=2023.3.post1=pyhd8ed1ab_0
+  - pyu2f=0.1.5=pyhd8ed1ab_0
+  - pyviz_comms=2.3.2=pyhd8ed1ab_0
+  - pywavelets=1.4.1=py310h3e78b6c_1
+  - pywin32=306=py310h00ffb61_2
+  - pywinpty=2.0.12=py310h00ffb61_0
+  - pyyaml=6.0.1=py310h8d17308_1
+  - pyzmq=24.0.1=py310hcd737a0_1
+  - qtconsole-base=5.5.0=pyha770c72_0
+  - qtpy=2.4.1=pyhd8ed1ab_0
+  - rasterio=1.3.9=py310h4d3659c_0
+  - ray-core=2.7.1=py310h139b6d1_0
+  - ray-default=2.7.1=py310h5588dad_0
+  - re2=2023.03.02=hd4eee63_0
+  - referencing=0.30.2=pyhd8ed1ab_0
+  - requests=2.31.0=pyhd8ed1ab_0
+  - rfc3339-validator=0.1.4=pyhd8ed1ab_0
+  - rfc3986-validator=0.1.1=pyh9f0ad1d_0
+  - rioxarray=0.15.0=pyhd8ed1ab_0
+  - rpds-py=0.12.0=py310h87d50f1_0
+  - rsa=4.9=pyhd8ed1ab_0
+  - rtree=1.1.0=py310h1cbd46b_0
+  - s3fs=2023.10.0=pyhd8ed1ab_0
+  - s3transfer=0.7.0=pyhd8ed1ab_0
+  - scikit-image=0.20.0=py310h1c4a608_1
+  - scikit-learn=1.3.2=py310hfd2573f_1
+  - scipy=1.11.3=py310hf667824_1
+  - send2trash=1.8.2=pyh08f2357_0
+  - setproctitle=1.3.3=py310h8d17308_0
+  - setuptools=68.2.2=pyhd8ed1ab_0
+  - shapely=2.0.2=py310h839b4a8_0
+  - six=1.16.0=pyh6c4a22f_0
+  - smart_open=6.4.0=pyhd8ed1ab_0
+  - smmap=5.0.0=pyhd8ed1ab_0
+  - snappy=1.1.10=hfb803bf_0
+  - sniffio=1.3.0=pyhd8ed1ab_0
+  - snuggs=1.4.7=py_0
+  - sortedcontainers=2.4.0=pyhd8ed1ab_0
+  - soupsieve=2.5=pyhd8ed1ab_1
+  - spectral=0.23.1=pyh1a96a4e_0
+  - sqlite=3.44.0=hcfcfb64_0
+  - stack_data=0.6.2=pyhd8ed1ab_0
+  - tbb=2021.10.0=h91493d7_2
+  - tblib=2.0.0=pyhd8ed1ab_0
+  - terminado=0.17.0=pyh08f2357_0
+  - threadpoolctl=3.2.0=pyha21a80b_0
+  - tifffile=2020.6.3=py_0
+  - tiledb=2.16.3=h1ffc264_3
+  - tinycss2=1.2.1=pyhd8ed1ab_0
+  - tinynetrc=1.3.1=pyhd8ed1ab_0
+  - tk=8.6.13=h5226925_1
+  - tomli=2.0.1=pyhd8ed1ab_0
+  - toolz=0.12.0=pyhd8ed1ab_0
+  - tornado=6.3.3=py310h8d17308_1
+  - tqdm=4.66.1=pyhd8ed1ab_0
+  - traitlets=5.13.0=pyhd8ed1ab_0
+  - types-python-dateutil=2.8.19.14=pyhd8ed1ab_0
+  - typing-extensions=4.8.0=hd8ed1ab_0
+  - typing_extensions=4.8.0=pyha770c72_0
+  - typing_utils=0.1.0=pyhd8ed1ab_0
+  - tzdata=2023c=h71feb2d_0
+  - uc-micro-py=1.0.1=pyhd8ed1ab_0
+  - ucrt=10.0.22621.0=h57928b3_0
+  - unicodedata2=15.1.0=py310h8d17308_0
+  - uri-template=1.3.0=pyhd8ed1ab_0
+  - uriparser=0.9.7=h1537add_1
+  - urllib3=1.26.18=pyhd8ed1ab_0
+  - vc=14.3=h64f974e_17
+  - vc14_runtime=14.36.32532=hdcecf7f_17
+  - virtualenv=20.21.0=pyhd8ed1ab_0
+  - vs2015_runtime=14.36.32532=h05e6639_17
+  - wcwidth=0.2.9=pyhd8ed1ab_0
+  - webcolors=1.13=pyhd8ed1ab_0
+  - webencodings=0.5.1=pyhd8ed1ab_2
+  - websocket-client=1.6.4=pyhd8ed1ab_0
+  - wheel=0.41.3=pyhd8ed1ab_0
+  - widgetsnbextension=4.0.9=pyhd8ed1ab_0
+  - win_inet_pton=1.1.0=pyhd8ed1ab_6
+  - winpty=0.4.3=4
+  - wrapt=1.16.0=py310h8d17308_0
+  - xarray=2023.10.1=pyhd8ed1ab_0
+  - xerces-c=3.2.4=h63175ca_3
+  - xorg-libxau=1.0.11=hcd874cb_0
+  - xorg-libxdmcp=1.1.3=hcd874cb_0
+  - xyzservices=2023.10.1=pyhd8ed1ab_0
+  - xz=5.2.6=h8d14728_0
+  - y-py=0.5.5=py310h87d50f1_2
+  - yaml=0.2.5=h8ffe710_2
+  - yarl=1.9.2=py310h8d17308_1
+  - ypy-websocket=0.8.2=pyhd8ed1ab_0
+  - zarr=2.16.1=pyhd8ed1ab_0
+  - zeromq=4.3.4=h0e60522_1
+  - zict=3.0.0=pyhd8ed1ab_0
+  - zipp=3.17.0=pyhd8ed1ab_0
+  - zlib=1.2.13=hcfcfb64_5
+  - zstd=1.5.5=h12be248_0