Remote Sensing & Geo-AI for Tracking and Quantifying Climate Smart Agriculture

Climate-smart agriculture (CSA) is a focal point in agricultural and climate policies, with key goals including mitigating greenhouse gas (GHG) emissions, improving soil health, boosting productivity, and enhancing farmer resiliency and livelihoods. Across croplands, advances in remote sensing and Artificial Intelligence are elevating the measurement and quantification of CSA and supporting next-generation Measurement, Reporting, and Verification (MRV) platforms. Remote sensing and Geo-AI, particularly through the use of multi-source observations, physical retrievals, GeoFM and AI architectures, and fusion with process-based crop models, are enabling field-scale analytics of management practices (activity data), quantification of outcomes (GHG, SOC, productivity), comparison against baselines, and assessment of treatment vs. control designs. These advances are important for growing impact and policymaking as CSA moves forward.This Research Topic aims to showcase innovative approaches and real-world applications of remote sensing and GeoAI for tracking and quantifying CSA practices and outcomes. The main objective is to stimulate discussion on methodologies and case studies that improve practice detection, outcome measurement, and broader MRV frameworks for sustainable agriculture.The scope of this topic will focus on advances in time-series analysis and GeoAI for detecting and quantifying CSA practices and outcomes. Submissions may include new methods, benchmark datasets, large-scale or site-specific case studies, and reviews.● Machine- and deep-learning analysis of multi-source and/or time series for tracking and comparing CSA● Development of remote sensing products for dMRV platforms purposed for cropland CSA and high-quality carbon credits● GeoFoundational Models for assessing cropland CSA● Mapping spatiotemporal dynamics of cover crops, tillage, and/or residue management practices across row crops● Tracking cropland fires and burn types (timing, extent, count, full, broadcast, partial, piles, intensity) in row crops, orchards, or smallholder farms● Mapping and modeling SOC, soil health indicators, and impacts of regenerative management practices● RS and Geo-AI for parameterizing crop models (DSSAT, DayCent, RothC, etc.)● Quantifying sustainable rice irrigation practices and impacts on GHG emissions● Geo-AI for enhancing precision agriculture● Development of AI models and data products for smallholder landscapes● Assessing impacts of CSA on soil, water, or air quality● Mapping seeding or planting practices using multi-source satellite remote sensing and machine-learning models. This includes studies that explore methodological innovations, transferability across regions, and agronomic and climate-driven motivations for such practice efforts focused toward climate-smart practices● Crop calendar detection and phenology modeling with a focus on identifying key agricultural events such as transplantation, sowing, and harvesting, especially in rainfed agricultural regions with two or more cropping cycles per annum that are climate-dependent, including deep learning- and AI-driven crop classification models across regions● Irrigation type mapping and water management practices in smallholder farming systems using remote sensing and GEO-AI models, including hydrological or land surface models; studies reporting methodological innovations and traditional versus climate-smart practicesDr. Nathan Torbick is the co-founder of Mitti Labs. The other Topic Editors declare no competing interests with regard to the Research Topic subject. Topic editors: Nathan Torbick, Ranjeet John Source: https://www.frontiersin.org/research-topics/79124/remote-sensing-geo-ai-for-tracking-and-quantifying-climate-smart-agriculture