Combining Vegetation, Color, and Texture Indices with Hyperspectral Parameters Using Machine-Learning Methods to Estimate Nitrogen Concentration in Rice Stems and Leaves

•Different types of remote sensing parameters have good potential for monitoring nitrogen content in rice.•The machine-learning models significantly improve the monitoring precision of nitrogen content in rice organs.•The nitrogen-monitoring models based on the whole growth period can be applied to nitrogen monitoring in all growth periods.•Nitrogen content monitoring based on organ scale can better reflect the growth status of crops.