Cătălin NEGULESCU1, Theodor BORANGIU2, Silviu RĂILEANU3, Victor-Valentin ANGHEL1
Abstract. In the context of agricultural digitalization, integrating data from multiple sources and leveraging modern technologies have become essential for supporting operational decision-making. This paper proposes a Farm Management Information System (FMIS) designed using a microservice-based architecture and supported by cloud computing and Internet of Things (IoT) technologies. This solution enables the collection and integration of heterogeneous data, including operational records, weather observations, and measurements from soil and plant sensors, through dedicated services and API interfaces. The architecture ensures modularity, interoperability, and incremental extensibility of functionalities. The main components for data ingestion, storage, and analysis are presented, together with decision-support mechanisms based on rules and predictive models. The prediction module employs machine learning algorithms based on decision trees, namely Random Forest and XGBoost, which are well suited for structured agricultural datasets. The approach is illustrated in the context of maize cultivation.
Keywords: FMIS, microservices, IoT data integration, machine learning, yield prediction.
DOI 10.56082/annalsarsciinfo.2026.1.42
1 Ph.D. student, POLITEHNICA Bucharest, catalin.negulescu@stud.electro.upb.ro, victor.anghel@stud.acs.upb.ro
2 University Professor, Ph.D., POLITEHNICA Bucharest, Academy of Romanian Scientists, theodor.borangiu@upb.ro
3 Associate Professor, Ph.D., POLITEHNICA Bucharest, silviu.raileanu@upb.ro
PUBLISHED in Annals of the Academy of Romanian Scientists Series on Science and Technology of Information, Volume 19, No1