Answers are grounded in this paper and cite their sources.
<ns3:p>Abstract* Background The analysis and interpretation of agricultural soils presents significant limitations due to the lack of accessible technological tools that facilitate the understanding of laboratory results. This situation affects agronomic decision-making and, consequently, the productivity and sustainability of agricultural systems. In response to this problem, the present research proposes TERRAGEM, an AI-based mobile application that automates the interpretation of soil physicochemical parameters and generates personalized management recommendations. Methods The system was developed under the agile Rapid Application Development (RAD) methodology, structured in five phases: requirements gathering, prototype design, AI API integration, functional validation with 29 real soil analysis reports, and deployment in an emulated test environment. The MBaaS architecture uses Supabase as the backend, enabling efficient data management and authentication, while facilitating integration with external APIs for agricultural decision-making. Results TERRAGEM demonstrated correct operation in all evaluated use cases, generating automated interpretations of soil physicochemical parameters and personalized agronomic recommendations for the four crop types analyzed (grape, avocado, corn, and sweet potato). Conclusions TERRAGEM represents a significant contribution toward agricultural digitalization, facilitating the use of data for sustainable decision-making and contributing to the Sustainable Development Goals (SDG 2: Zero Hunger, and SDG 15: Life on Land).</ns3:p>
No takes yet. Share an insight, caveat, or question.
Delgado-Santiago et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: