【论文题目】 Mapping plant nitrogen concentration and aboveground biomass of potato crops from Sentinel-2 data using ensemble learning models
利用集成学习模型从哨兵2号数据绘制马铃薯植株氮浓度和地上部生物量
【作者】 Hang Yin, Fei Li, Haibo Yang, Yunfei Di, Yuncai Hu, Kang Yu
尹航，李斐，杨海波，邸云飞，胡云才，于康
【摘要】
【Abstract】Excessive nitrogen (N) fertilization poses environmental risks at the regional and global levels. Satellite remote sensing provides a novel approach for large-scale N monitoring. In this study, we evaluated the performance of different types of spectral bands and indices (SIs) coupled with Ensemble Learning Models (ELM) in retrieving the plant N concentration (PNC) and plant aboveground biomass (AGB) in potato from Sentinel-2 images. The cloud-free Sentinel-2 imagery was acquired during the tuber formation to starch accumulation stages in 2020 to 2021. Fourteen optimal SIs were selected using the successive projections algorithm (SPA) and principal component analysis (PCA). The PNC and AGB estimation models were then built using ELM. Results showed that the SIs based on chlorophyll absorption bands were strongly related to potato PNC and AGB. Also, the N-correlated bands were mainly concentrated in the red edge (705 nm) and short-wave infrared (1610 and 2190 nm) regions. The ELM successfully predicted PNC and AGB (R2PNC = 0.74; R2AGB = 0.82). Compared with the other five base models (k-nearest neighbor (KNN), partial least squares regression (PLSR), support vector regression (SVR), random forest (RF), and Gaussian process regression (GPR)), the ELM provided higher PNC and AGB estimation accuracy and effectively reduced the overfitting to training data. This study demonstrated that the promising solution of using SPA-PCA coupled with an ensemble learning model improves the estimation accuracy in potato PNC and AGB based on Sentinel-2 imagery data.
【Keywords】ensemble learning model, feature selection, plant nitrogen concentration, spectral indices, potato, Sentinel-2 imagery
位置：