Improving Unmanned Aerial Vehicle Remote Sensing-Based Rice Nitrogen Nutrition Index Prediction with Machine Learning

Remote Sensing

Krzysztof Kusnierek¹  Tiantian Wang²  Hainie Zha²  Zhengqi Feng²  Weichao Sun²  Jing Zhang²  Yue Li²  Yuxin Miao² 

[1] Center for Precision Agriculture, Norwegian Institute of Bioeconomy Research (NIBIO), Nylinna 226, 2849 Kapp, Norway;International Center for Agro-Informatics and Sustainable Development (ICASD), College of Resources and Environmental Sciences, China Agricultural University, Beijing 100193, China;

关键词: fixed-wing uav remote sensing;    nitrogen status diagnosis;    random forest;    precision nitrogen management;    machine learning;   

DOI  :  10.3390/rs12020215

来源: DOAJ

【 摘 要 】

Optimizing nitrogen (N) management in rice is crucial for China’s food security and sustainable agricultural development. Nondestructive crop growth monitoring based on remote sensing technologies can accurately assess crop N status, which may be used to guide the in-season site-specific N recommendations. The fixed-wing unmanned aerial vehicle (UAV)-based remote sensing is a low-cost, easy-to-operate technology for collecting spectral reflectance imagery, an important data source for precision N management. The relationships between many vegetation indices (VIs) derived from spectral reflectance data and crop parameters are known to be nonlinear. As a result, nonlinear machine learning methods have the potential to improve the estimation accuracy. The objective of this study was to evaluate five different approaches for estimating rice (Oryza sativa L.) aboveground biomass (AGB), plant N uptake (PNU), and N nutrition index (NNI) at stem elongation (SE) and heading (HD) stages in Northeast China: (1) single VI (SVI); (2) stepwise multiple linear regression (SMLR); (3) random forest (RF); (4) support vector machine (SVM); and (5) artificial neural networks (ANN) regression. The results indicated that machine learning methods improved the NNI estimation compared to VI-SLR and SMLR methods. The RF algorithm performed the best for estimating NNI (R² = 0.94 (SE) and 0.96 (HD) for calibration and 0.61 (SE) and 0.79 (HD) for validation). The root mean square errors (RMSEs) were 0.09, and the relative errors were <10% in all the models. It is concluded that the RF machine learning regression can significantly improve the estimation of rice N status using UAV remote sensing. The application machine learning methods offers a new opportunity to better use remote sensing data for monitoring crop growth conditions and guiding precision crop management. More studies are needed to further improve these machine learning-based models by combining both remote sensing data and other related soil, weather, and management information for applications in precision N and crop management.

【 授权许可】

Unknown