Point-to-Interval Prediction Method for Key Soil Property Contents Utilizing Multi-Source Spectral Data

Abstract

Key soil properties play pivotal roles in shaping crop growth and yield outcomes. Accurate point prediction and interval prediction of soil properties serve as crucial references for making informed decisions regarding fertilizer applications. Traditional soil testing methods often entail laborious and resource-intensive chemical analyses. To address this challenge, this study introduced a novel approach leveraging spectral data fusion techniques to forecast key soil properties. The initial datasets were derived from UV–visible–near-infrared (UV-Vis-NIR) spectral data and mid-infrared (MIR) spectral data, which underwent preprocessing stages involving smoothing denoising and fractional-order derivative[s] (FOD) transform techniques. After extracting the characteristic bands from both types of spectral data, three fusion strategies were developed, which were further enhanced using machine learning techniques. Among these strategies, the outer-product analysis fusion algorithm proved particularly effective in improving prediction accuracy. For point predictions, metrics such as the coefficient of determination (R2) and error metrics demonstrated significant enhancements compared to predictions based solely on single-source spectral data. Specifically, R2 values increased by 0.06 to 0.41, underscoring the efficacy of the fusion approach combined with partial least squares regression (PLSR). In addition, based on the coverage width criterion to establish reliable prediction intervals for key soil properties, including soil organic matter (SOM), total nitrogen (TN), hydrolyzed nitrogen (HN), and available potassium (AK). These intervals were developed within the framework of the kernel density estimation (KDE) interval prediction model, which facilitates the quantification of uncertainty in property estimates. For available phosphorus (AP), a preliminary assessment of its concentration was also provided. By integrating advanced spectral data fusion with machine learning, this study paves the way for more informed agricultural decision making and sustainable soil management strategies.