A GIS-Driven, Machine Learning-Enhanced Framework for Adaptive Land Bonitation
Bogdan Văduva, Anca Avram, Oliviu Matei, Laura Andreica, Teodor Rusu

Abstract. Traditional land bonitation, the agronomic evaluation of land quality and agricultural potential, often relies on static, historical data that fails to capture the dynamics of a changing climate. This paper presents a GIS-driven, machine learning-enhanced framework for adaptive land bonitation. By combining Geographic Information Systems (GIS) with machine learning algorithms, the framework continuously analyses complex spatial and environmental data to evaluate land potential dynamically. The result is a precision crop-matching tool that supports dynamic adaptation to evolving climate, rainfall and soil conditions, while contributing to sustainable land management. The approach provides stakeholders with highly accurate, future-proof land quality scores and prevents land degradation and over-farming.

Keywords: GIS; land bonitation; machine learning; adaptive evaluation; precision agriculture; sustainable land management

Bogdan Văduva, Anca Avram, Oliviu Matei, Laura Andreica, Teodor Rusu, "A GIS-Driven, Machine Learning-Enhanced Framework for Adaptive Land Bonitation", Agriculture (Basel), vol. 15, no. 16, MDPI, 2025, 2023. DOI: https://doi.org/10.3390/agriculture15161735.

Reference: Agriculture (Basel), vol. 15, no. 16, MDPI, 2025. DOI: 10.3390/agriculture15161735

Other publications