Mixture-based weight learning improves the random forest method for hyperspectral estimation of soil total nitrogen

Abstract

Visible and near-infrared reflectance spectroscopy is a promising technique to estimate soil total nitrogen, but because of many uncontrolled variations like soil water, developing a high-accuracy soil total nitrogen model is still challenging. This study proposed a new methodology called mixture-based weight learning to reduce the problems stated above. This method improves the estimation accuracy of soil total nitrogen by mixing soil total nitrogen with soil water, then using the random forest method to model soil total nitrogen. A series of different mixtures of soil water and soil total nitrogen were made, and based on the visible and near-infrared spectra measured under laboratory conditions, the optimal model (j = 0.03) was constructed and used as the final mixture-based weight learning–random forest model, which produced better results (R2 of validation = 0.757; root mean square error of validation = 0.235 g/kg; mean relative error of validation = 10.0%; ratio of performance to interquartile range of validation = 2.419) than a random forest model. Our mixture-based weight learning method combined with the random forest method has great potential for the accurate remote retrieval of soil total nitrogen and enhances the available ways to estimate soil properties.