CSIF（Contiguous Solar-induced Fluorescence， 日光诱导叶绿素荧光）数据下载与批量处理(shp裁剪nc，并输出为tif)

数据简介：

单位：mW m−2 nm−1 sr−1

文章出处：BG - A global spatially contiguous solar-induced fluorescence (CSIF) dataset using neural networks (copernicus.org)

下载链接：A global spatially contiguous solar-induced fluorescence (CSIF) dataset using neural networks (2000-2020)- 时空三极环境大数据平台 (tpdc.ac.cn)

数据处理：shp裁剪nc，并输出为tif

# -*- coding: utf-8 -*-
"""
遍历路径，shp批量裁剪nc
20240316, 19:42, YMJ
"""

import os
import geopandas
import numpy as np
import rasterio
from rasterio.enums import Resampling
import xarray as xr
from rasterio.transform import from_origin
from shapely.geometry import mapping, box
import geopandas as gpd

# 输入文件夹路径
input_folder = 'D:\\CSIF\\test'
# 输出文件夹路径
output_folder = 'D:\\CSIF\\daily_clip_resample\\'

shp_path = 'D:\\CMFD\\test\\area.shp'
gdf = gpd.read_file(shp_path)


# 获取输入文件夹中所有的 NetCDF 文件列表
nc_files = []
for root, subroot, files in os.walk(input_folder):
    for file in files:
        if file.endswith("nc"):
            file_path = os.path.join(root, file)
            nc_files.append(file_path)
print(nc_files)

# 循环处理每个 NetCDF 文件
for nc_file in nc_files:
    # 构造完整的输入文件路径
    input_nc_file = os.path.join(input_folder, nc_file)

    # 构造输出文件名（保留原始文件名，但修改扩展名为 '.tif'）
    output_filename = os.path.splitext(nc_file)[0] + '.tif'
    output_tif_file = os.path.join(output_folder, output_filename)

    # 打开待裁剪的 NetCDF 文件
    data_ds = xr.open_dataset(input_nc_file)
    data_ds.rio.write_crs("EPSG:4326", inplace=True)

  
    # 打开输出 TIFF 文件，并写入裁剪后的数据
    data_ds.rio.set_spatial_dims(x_dim="lon", y_dim="lat", inplace=True)
    clipped_ds = data_ds.rio.clip(gdf.geometry.apply(mapping), gdf.crs, drop=True)
    data = clipped_ds.clear_daily_SIF.values
    
    transform = from_origin(clipped_ds['lon'].values.min(),
                            clipped_ds['lat'].values.min(),
                            clipped_ds['lon'].values[1] - clipped_ds['lon'].values[0],
                            clipped_ds['lat'].values[0] - clipped_ds['lat'].values[1])
    
    with rasterio.open(output_tif_file, 'w', driver='GTiff', height=data.shape[0],
                        width=data.shape[1], count=1, dtype=str(data.dtype),
                        crs='EPSG:4326', transform=transform) as dst:
         dst.write(data, 1)