Soil Moisture, Organic Carbon, and Nitrogen Content Prediction with Hyperspectral Data Using Regression Models

Abstract

Soil moisture, soil organic carbon, and nitrogen content prediction are considered significant fields of study as they are directly related to plant health and food production. Direct estimation of these soil properties with traditional methods, for example, the oven-drying technique and chemical analysis, is a time and resource-consuming approach and can predict only smaller areas. With the significant development of remote sensing and hyperspectral (HS) imaging technologies, soil moisture, carbon, and nitrogen can be estimated over vast areas. This paper presents a generalized approach to predicting three different essential soil contents using a comprehensive study of various machine learning (ML) models by considering the dimensional reduction in feature spaces. In this study, we have used three popular benchmark HS datasets captured in Germany and Sweden. The efficacy of different ML algorithms is evaluated to predict soil content, and significant improvement is obtained when a specific range of bands is selected. The performance of ML models is further improved by applying principal component analysis (PCA), a dimensional reduction method that works with an unsupervised learning method. The effect of soil temperature on soil moisture prediction is evaluated in this study, and the results show that when the soil temperature is considered with the HS band, the soil moisture prediction accuracy does not improve. However, the combined effect of band selection and feature transformation using PCA significantly enhances the prediction accuracy for soil moisture, carbon, and nitrogen content. This study represents a comprehensive analysis of a wide range of established ML regression models using data preprocessing, effective band selection, and data dimension reduction and attempt to understand which feature combinations provide the best accuracy. The outcomes of several ML models are verified with validation techniques and the best- and worst-case scenarios in terms of soil content are noted. The proposed approach outperforms existing estimation techniques.

Rapid and Automated Approach for Early Crop Mapping Using Sentinel-1 and Sentinel-2 on Google Earth Engine; A Case of a Highly Heterogeneous and Fragmented Agricultural Region

“…The Random Forest (RF) algorithm has been used in several studies related to crop classification, which has demonstrated good performance [21]. Additionally, the RF algorithm has produced reliable results in numerous investigations that predicted soil properties using regression models [22].…”

A Review on Unmanned Aerial Vehicle Remote Sensing: Platforms, Sensors, Data Processing Methods, and Applications

“…The data produced by hyper-spectral cameras are not only useful for investigating the reflected spectral intensity of green plants but also for analyzing the chemical properties of ground targets. Hyper-spectral data can provide information about the chemical composition and water content of soil [48], as well as the chemical composition of ground minerals [49,50]. This is because hyper-spectral cameras can capture data across many narrow and contiguous wavelength bands, allowing for detailed analysis of the unique spectral signatures of different materials.…”

“…In the study, the authors found that the effect of estimating soil water content using multi-spectral data was better than that using thermal imaging data, with a correlation coefficient R 2 = 96%. Datta et al [48] studied the relationship between hyper-spectral image data and soil moisture content. Based on all hyper-spectral band (AHSB) data, the authors used support vector regression (SVR) [148], which achieved a result correlation coefficient R 2 = 95.43%, RMSE = 0.8.…”

Predicting Soil Organic Matter, Available Nitrogen, Available Phosphorus and Available Potassium in a Black Soil Using a Nearby Hyperspectral Sensor System

“…Both principal components regression (PCR) and PLSR are linear chemometric tools used for the analysis of spectroscopic data for different applications. They are the most common modeling techniques for quantitative spectroscopy analyses in soils and have been extensively discussed in the literature [24][25][26]. They both represent techniques that are based on the decomposition of the spectral data into features that capture most of the variance that exists in the raw visible and near-infrared spectroscopic (VIS-NIRS) data and the creation of linear models using the scores of the most correlated features [27].…”