bhargavi909/CropNet

CropNet数据集是一个开放、大规模、多模态的数据集，专门用于美国县级气候变化感知的作物产量预测。数据集包含三种模态的数据：Sentinel-2影像、WRF-HRRR计算数据集和USDA作物数据集，覆盖了2017至2022年6年间2200多个美国县的数据。Sentinel-2影像提供高分辨率卫星图像，用于监测作物生长；WRF-HRRR计算数据集包含每日和每月的气象参数，用于捕捉短期和长期气候变化对作物产量的影响；USDA作物数据集提供县级作物信息，如产量和生产数据。数据集旨在帮助研究者开发深度学习模型，以考虑短期生长季节天气变化和长期气候变化对作物产量的影响，从而精确预测县级作物产量。此外，CropNet Python包提供了方便的API，用于下载数据和开发深度学习模型。

The CropNet dataset is an open, large-scale, and multi-modal dataset specifically targeting climate change-aware crop yield predictions for the contiguous United States at the county level. It comprises three modalities of data: Sentinel-2 Imagery, WRF-HRRR Computed Dataset, and USDA Crop Dataset, spanning 6 years (2017-2022) across over 2200 U.S. counties. Sentinel-2 Imagery provides high-resolution satellite images for monitoring crop growth; the WRF-HRRR Computed Dataset contains daily and monthly meteorological parameters to capture the effects of short-term weather variations and long-term climate change on crop yields; the USDA Crop Dataset offers county-level crop information such as yield and production data. The dataset is designed to facilitate the development of deep learning models for timely and precise crop yield predictions by accounting for both short-term and long-term climate effects. Additionally, the CropNet Python package provides convenient APIs for downloading data and developing deep learning models.