decision-support
Decision-support systems are computational or human-guided tools that integrate data to help users make informed choices in complex, evolving situations. In plant science, these systems combine field data, environmental variables, and predictive models to guide decisions such as crop management, disease control, and resource allocation. By synthesizing diverse data sources, they help researchers and growers respond effectively to variable and unpredictable agricultural conditions.
open_in_new WikipediaOpenAlex · 2026-08-09
Researchers reviewed how machine learning algorithms are being applied across agriculture, from predicting crop yields to detecting plant diseases and managing soil and water. The review maps the current state of AI tools in farming and highlights where gaps remain for future research.
ML algorithms show strong performance across four core agricultural domains: crop yield prediction, disease identification, soil management, and water management.
Multiple ML model types are in use, with no single algorithm dominating across all applications, indicating the field is still maturing.
Significant research gaps remain, particularly in integrating multiple data types and translating models to real-world decision support systems at scale.