"Multi-Source Agricultural Dataset for Crop Classification Using Soil Nutrients and Multispectral Vegetation Indices"
收藏DataCite Commons2026-01-30 更新2026-05-03 收录
下载链接：
https://ieee-dataport.org/documents/iot-framework-and-quantum-machine-learning-based-precision-agriculture-using-sentinel-2
下载链接
链接失效反馈官方服务：
资源简介：
"This dataset presents a multi-source agricultural feature collection designed for crop classification and precision farming research. It integrates soil nutrient parameters (Nitrogen, Phosphorus, Potassium, and pH), environmental temperature, multispectral satellite-style reflectance bands (B2, B3, B4, B8), and derived vegetation indices including NDVI, SAVI, GNDVI, EVI, and TVI. Additionally, a crop stress level indicator is included to reflect plant health conditions.The dataset supports machine learning and remote sensing applications for intelligent crop type prediction, crop health monitoring, and sustainable agriculture modeling. It is structured for multi-class crop classification tasks involving major crops such as rice, maize, coconut, and sugarcane. The features represent realistic agricultural, soil, and spectral conditions, making the dataset suitable for developing, benchmarking, and validating AI and hybrid classical\u2013quantum learning models in precision agriculture."
提供机构：
IEEE DataPort
创建时间：
2026-01-30
