Use of modern digital techniques for mapping and assessment of salt-affected soils

Abstract

Soil salinity is a growing global challenge, threatening agricultural productivity and food security. Conventional methods for diagnosing salt-affected soils such as visual inspection, field sampling, and laboratory testing have long provided essential insights but remain time-consuming, costly, and limited in spatial coverage. Recent advances in geospatial technologies, particularly remote
sensing, geographic information systems (GIS), and machine learning (ML), are transforming how soil salinity is detected, mapped, and managed. Optical remote sensing now enables largescale monitoring by capturing spectral signals linked to salinity stress, while predictive algorithms such as random forests, support vector machines, and neural networks enhance mapping accuracy across diverse landscapes. Digital Soil Mapping (DSM) builds on these innovations by integrating multi-source environmental data with advanced models to generate high-resolution, continuous maps of soil salinity, offering actionable intelligence for precision agriculture. In India, pioneering applications of DSM have shown promising results, from improving fertilizer efficiency and water use in Maharashtra to large-scale initiatives like the Soil Intelligence System in Andhra Pradesh, Bihar, and Odisha. The ICAR-Central Soil Salinity Research Institute (CSSRI) has also advanced national-level salinity mapping efforts, combining legacy soil data with remote sensing and ML approaches. Emerging tools such as UAVs further add local-scale precision, enabling dynamic monitoring of soil health. Together, these developments illustrate how DSM is reshaping salinity diagnostics, bridging science and practice, and paving the way for more sustainable land management strategies in the face of climate change and increasing soil degradation.