A Framework for High-Resolution Mapping of Soil Organic Matter (SOM) by the Integration of Fourier Mid-Infrared Attenuation Total Reflectance Spectroscopy (FTIR-ATR), Sentinel-2 Images, and DEM Derivatives

Abstract

Soil organic matter (SOM), as the greatest carbon storage in the terrestrial environment, is inextricably related to the global carbon cycle and global climate change. Accurate estimation and mapping of SOM content are crucial for guiding agricultural output and management, as well as controlling the climate issue. Traditional chemical analysis is unable to satisfy the dynamic estimation of SOM due to its low timeliness. Remote and proximal sensing have significant advantages in terms of ease of use, estimation accuracy, and geographical resolution. In this study, we developed a framework based on machine learning to estimate SOM with high accuracy and resolution using Fourier mid-infrared attenuation total reflectance spectroscopy (FTIR-ATR), Sentinel-2 images, and DEM derivatives. This framework’s performance was evaluated on a regional scale using 245 soil samples from northeast China. Results indicated that the calibration size could be shrunk to 50% while achieving a fair prediction performance for SOM content. The Lasso, partial least squares (PLS), support vector regression (SVR), and convolutional neural networks (CNN) performed well in predicting SOM from FTIR-ATR spectra, and the performance was enhanced further by using Sentinel-2 images and DEM derivates. The PLS, SVR, and CNN models created SOM maps with higher spatial resolution and variation than the Kriging approach. The PLS and SVR models provided enough variety and were more realistic in the local SOM map, making them usable at the field scale, and the suggested framework took a fresh look at high-resolution SOM mapping.

Advancing Soil Health: Challenges and Opportunities in Integrating Digital Imaging, Spectroscopy, and Machine Learning for Bioindicator Analysis

“…The study assessed the predictive capabilities of various ML models and found that a hybrid method combining the Cubist model and the Bat algorithm yielded the best results with an R 2 value of 0.63. To improve the accuracy, Xu et al 99 combined a hand-held FTIR (Agilent 4300) with satellite NIR data for SOC analysis. They compared the prediction performance of different machine learning models: PLS, CNN, and SVM.…”

Estimates of Dust Emissions and Organic Carbon Losses Induced by Wind Erosion in Farmland Worldwide from 2017 to 2021

“…The loss of carbon further intensifies the greenhouse effect by increasing the temperature, resulting in lower soil moisture and so promoting further carbon losses [54]. Changes in SOC are an essential indicator for the loss of nutrients from black soils and for soil response to the greenhouse effect [55,56].…”

Mid-Infrared Variable Selection for Soil Organic Matter Fractions Based on Soil Model Systems and Permutation Importance Algorithm

“…Obtaining useful information about the mineralogical composition of the soil as well as the content and character of organic matter in laboratory conditions has a significant impact on expanding the possibilities of remote sensing methods. 45 ASTER has seven spectral bands in the shortwave IR region and five in the MIR region. For the calibration of these satellites, it is necessary to obtain as much information as possible in idealized laboratory conditions.…”