Estimating River Widths in Complex Terrain Environments Using Scene Classification and Regression: Monthly River Surface Area Analysis on the Tibetan Plateau

Description: The deep learning method, RWSD (River Width estimation from Sentinel-2 images based on Deep learning), utilizes a combination of classification and regression models to estimate river widths, particularly for smaller rivers (e.g., width < 100m). The approach first classifies Sentinel-2 TOA images into lakes vs. non-lakes and active river channels vs. non-active channels or non-river areas, which include ice, snow, and land areas. Subsequently, the regression model estimates the wetted river width at the cross-section closest to the image center. Files and Descriptions: 1. TP_Lake.csv: This CSV file contains identified lakes in the Tibetan Plateau. 2. TP_River_Monthly_Statistics.csv: Monthly statistics for river data on the Tibetan Plateau, including estimations like active channel percentage and width for different river orders. 3. S2RiverWidth.py: The Python script that contains the main code for river width estimation model. This script includes the functions for preprocessing Sentinel-2 images and predicting river widths. 4. best_model_vCloud10.pth: The pre-trained deep learning model weights used for river width estimation. This model is a ResNeXt model fine-tuned on our dataset. It accepts Sentinel-2 TOA image with cloud percentage <10% (SCL). 5. SampleS2Img.tif: A sample Sentinel-2 TOA image in .tif format, used for testing the river width estimation model. Model Input Requirements:The model requires a Sentinel-2 TOA image in .tif format as input. The image should be scaled by a factor of 10,000 (with reflectance values range from 0 to 1). The `get_model_input` function automatically crops the image to 224x224 pixels around the center to fit the model's input requirements.### 数据集说明 本数据集所采用的深度学习方法为RWSD（River Width estimation from Sentinel-2 images based on Deep learning，基于深度学习的哨兵2号影像河道宽度估算方法），该方法通过结合分类与回归模型实现河道宽度估算，尤其适配宽度小于100米的小型河道。该方案首先对哨兵2号大气顶层反射率（TOA，Top-of-Atmosphere）影像进行分类，将其划分为湖泊与非湖泊、活跃河道与非活跃河道/非河道区域（涵盖冰、雪与陆地）；随后通过回归模型估算距离影像中心最近断面的湿河道宽度。 #### 文件及说明 1. TP_Lake.csv：该CSV文件存储了青藏高原地区已识别的湖泊数据集。 2. TP_River_Monthly_Statistics.csv：包含青藏高原河道数据的月度统计信息，涵盖不同河道级别的活跃河道占比、宽度等估算结果。 3. S2RiverWidth.py：实现河道宽度估算模型核心逻辑的Python脚本，内置哨兵2号影像预处理与河道宽度预测相关函数。 4. best_model_vCloud10.pth：用于河道宽度估算的预训练深度学习模型权重文件。该模型为基于本数据集微调后的ResNeXt模型，支持输入云占比小于10%（SCL）的哨兵2号大气顶层反射率影像。 5. SampleS2Img.tif：用于测试河道宽度估算模型的哨兵2号大气顶层反射率影像样例，格式为.tif。 #### 模型输入要求 模型需以.tif格式的哨兵2号大气顶层反射率影像作为输入，影像需经10000倍缩放（反射率取值范围为0至1）。`get_model_input`函数可自动将影像中心区域裁剪为224×224像素，以适配模型的输入尺寸要求。