Spectral purification improves monitoring accuracy of the comprehensive growth evaluation index for film-mulched winter wheat
Zhikai Cheng, Xiaobo Gu, Yadan Du, Zhihui Zhou, Wen-long LI, Xiaobo Zheng, Wenjing Cai, Tian CHANG
Abstract
In order to further improve the ability of unmanned aerial vehicle (UAV) remote-sensing for quickly and accurately monitoring the growth of winter wheat under film mulching, this research used treatments of ridge mulching, ridge–furrow full mulching, and flat cropping full mulching winter wheat. Based on the fuzzy comprehensive evaluation (FCE) method, four agronomic parameters (leaf area index, aboveground biomass, plant height, and leaf chlorophyll content) were used to calculate the comprehensive growth evaluation index (CGEI) of winter wheat, and 14 visible and near-infrared spectral indices were calculated using spectral purification technology to process the remote-sensing image data of winter wheat obtained by multispectral UAV. Four machine learning algorithms, partial least squares, support vector machines, random forests, and artificial neural network networks (ANN), were used to build the winter wheat growth monitoring model under film mulching, with accuracy evaluation and mapping of the spatial and temporal distribution of winter wheat growth status. The results showed that the CGEI of winter wheat under film mulching constructed based on the FCE method could objectively and comprehensively evaluate crop growth status, and the accuracy of remote-sensing inversion of the CGEI based on the ANN model was higher than for single agronomic parameters, with coefficient of determination of 0.75, root mean square error of 8.40, and mean absolute value error of 6.53. Spectral purification could eliminate the interference of background effects caused by mulching and soil, effectively improving the accuracy of remote-sensing inversion of winter wheat under film mulching, with the best inversion effect achieved on the ridge–furrow full mulching area after spectral purification. The results provided a theoretical reference for UAV remote-sensing to monitor the growth status of winter wheat with film mulching.