Advanced Geo-statistics and AI/ML for Soil Quality Assessment, Prediction, and Management

Soil is one of the important natural resources, playing a vital role in maintaining food security, sustaining agriculture, and regulating the climate. However, increasing intensive farming, urbanization, industrialization along with shifting of climate conditions are leading to the degradation of soil fertility and quality, posing a significant threat to sustainable agriculture. This problem is now widespread from local to national and global scale. To address this issue, traditional methods often fall short due to their labor-intensive nature, high cost, and limited scope in addressing the spatial and temporal and multidimensional properties of soil system. The rapid advancement of data science, particularly Artificial intelligence (AI), machine learning (ML), and deep learning (DL) techniques coupled with the increasing availability of multi-source data from remote sensing, proximal sensors, and advance statistical modeling provides an unprecedented opportunity to real-time soil quality monitoring, accurate and robust soil quality assessment, pattern recognition, contamination prediction, and evidence-based real-time decision-making in soil remediation strategies. Such techniques enable rapid, cost-effective, and large-scale analysis across different temporal and spatial scale that can contribute significantly towards sustainable agriculture, improved productivity, land restoration, and environmental conservation.

In this context, this Research Topic welcomes cutting-edge multi-disciplinary research findings, innovative applications, field-scale studies, and critical reviews, with the aim of providing insights into ‘what’s new and what’s next’ at the intersection of soil science and AI/ML.

We welcome contributions that address, but are not limited to, the following themes:
• Advanced multivariate statistics (such as robust PCA, FA, and cluster analysis) for soil quality monitoring and contamination assessment;
• Statistical framework integrating physical, chemical and biological parameters for developing soil quality indices;
• Coupling AI/ML with GIS and statistical models for assessment and prediction of heavy metals, pesticides and emerging contaminants and PFAS in soil systems;
• Spatial autocorrelation and semivariogram modeling for soil quality analysis;
• Integration of geostatistics with remote sensing and hyperspectral imaging for soil quality evaluation;
• Statistical optimization and risk-benefit analysis for soil remediation studies;
• AI/ML algorithms for soil fertility, soil texture, organic matter mapping and classification;
• Machine learning applications for predicting the long-term impact of climate change on soil health and degradation;
• AI models for understanding microplastic–metals-soil interactions;
• Role of AL/ML techniques and big data analytics in smart agricultural systems;
• Use of AI/ML models in creation of multi-scale (local, regional, national or global) soil quality databases and support advance agriculture policies;
• Predicting soil erosion, salinization, and desertification using ML techniques;
• Modeling soil–water–pollutant interactions with advanced statics and hybrid AI models;
• AI-driven techniques for soil remediation strategies (bioremediation, phytoremediation, nanoremediation);
• Predictive models for evaluating the effectiveness of remediation techniques;
• AI/ML with GIS and hydrological models for precision farming, sustainable land and soil management.