Predicting Soil Textural Classes Using Random Forest Models: Learning from Imbalanced Dataset

Abstract

Soil provides a key interface between the atmosphere and the lithosphere and plays an important role in food production, ecosystem services, and biodiversity. Recently, demands for applying machine learning (ML) methods to improve the knowledge and understanding of soil behavior have increased. While real-world datasets are inherently imbalanced, ML models overestimate the majority classes and underestimate the minority ones. The aim of this study was to investigate the effects of imbalance in training data on the performance of a random forest model (RF). The original dataset (imbalanced) included 6100 soil texture data from the surface layer of agricultural fields in northern Iran. A synthetic resampling approach using the synthetic minority oversampling technique (SMOTE) was employed to make a balanced dataset from the original data. Bioclimatic and remotely sensed data, distance, and terrain attributes were used as environmental covariates to model and map soil textural classes. Results showed that based on mean minimal depth (MMD), when imbalanced data was used, distance and annual mean precipitation were important, but when balanced data were employed, terrain attributes and remotely sensed data played a key role in predicting soil texture. Balanced data also improved the accuracies from 44% to 59% and 0.30 to 0.52 with regard to the overall accuracy and kappa values, respectively. Similar increasing trends were observed for the recall and F-scores. It is concluded that, in modeling soil texture classes using RF models through a digital soil mapping approach, data should be balanced before modeling.

Digital Mapping of Topsoil Texture Classes Using a Hybridized Classical Statistics–Artificial Neural Networks Approach and Relief Data

“…The results from the error matrix show that in all textural classes, there were some samples representing other ones. It should be noted that the imbalanced distribution of STCs may have affected the results [90]. Nevertheless, out of 4493 samples, 2360 were predicted correctly.…”

Integrating Multiscale Geospatial Analysis for Monitoring Crop Growth, Nutrient Distribution, and Hydrological Dynamics in Large-Scale Agricultural Systems

“…Prior work has mapped such geographic distinctions in soil texture at the state scale using digital soil data. Previous studies have delineated these distinctions in soil texture at the state's scale using digital soil data Arshad et al (1997); Mallah et al (2022) and have underscored the pivotal role of soil composition in agricultural land management Lindbo et al (2012). These maps provide an updated baseline understanding of soil textural patterns relevant to crop planning and other applications.…”

“…Most of these challenges hinge on integrating diverse multi-modal data. Digital soil mapping and analysis of soil surveys have been valuable for understanding soil nutrients, texture, fertility, and more Subburayalu et al (2014); Arshad et al (1997); Mallah et al (2022). In addition, hydrological data such as stream-flow measurements enables the characterization of water quality issues such as agricultural runoff and nutrient pollution Michalak et al (2013); Smith et al (2015).…”

AI and machine learning for soil analysis: an assessment of sustainable agricultural practices

“…Considerable efforts have been made in past toward the development of a global soil parameter database. These efforts involve everything from general laboratory analysis of soil from various localities to the installation of advanced sensors globally or geospatial technologies (Mallah et al 2022 ).…”