Answers are grounded in this paper and cite their sources.
Remote sensing has become a major information source for smart and Precision Agriculture, enabling non-destructive monitoring of crop and environmental conditions across multiple spatial and temporal scales. Increasingly, its value depends on integration with analytical approaches capable of transforming observations into actionable agronomic information. This systematic review assessed the integration of remote sensing with artificial intelligence (AI), crop simulation models, data assimilation and digital decision-support systems, and their contribution to sustainable agricultural management. Following PRISMA 2020, Scopus-indexed peer-reviewed literature published between 2015 and 2026 was systematically reviewed, with 205 studies included in the final synthesis. AI-based approaches were identified in 71.2% (146/205) of the reviewed studies, crop simulation models were reported in 48.8% (100/205), and data assimilation approaches were identified in 46.3% (95/205). These frequencies describe the representation of the respective approaches in the reviewed literature and do not necessarily indicate their experimental implementation in every publication. The evidence shows a transition from descriptive remote sensing applications towards integrated systems supporting crop monitoring, yield prediction, irrigation and nutrient management, stress detection and resource optimisation. However, challenges remain regarding data interoperability, AI transferability and explainability, crop-model calibration, methodological heterogeneity, uncertainty and operational accessibility. Overall, remote sensing increasingly provides the observation layer of smart agricultural systems, while AI, crop modelling and data assimilation provide the analytical and predictive capabilities required for sustainable agricultural decision-making.
No takes yet. Share an insight, caveat, or question.
Coelho et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: