Edaphic homologous zones and digital tools as a basis for sustainable soil management in potato growing areas in Colombia

Abstract The physicochemical properties of soil are fundamental to sustainable land management and understanding its characteristics and spatial variability is essential for informed decision-making. This study aimed to evaluate the spatial variability of soil physicochemical properties in potato-producing regions of Colombia and to identify homologous edaphic zones using data science and geospatial analysis as a foundation for improved soil resource management. A total of 3,137 soil samples were analyzed following rigorous data cleaning and exploratory data analysis. K-means clustering was applied to delineate homologous edaphic zones, which were subsequently characterized based on key soil attributes. These clusters were spatially mapped, and preliminary analyses were conducted to assess the relationships between soil properties and crop productivity. The exploratory analysis revealed significant variability in phosphorus and iron concentrations. Three distinct edaphic clusters were identified, exhibiting notable differences in soil fertility profiles. While nutrient deficiencies were common, 59% of the area was classified as suitable for potato cultivation. Additionally, multiple relationships were identified between yield, soil characteristics, and climatic variables. Furthermore, the results underpin the creation of a fertilization recommendation system and aptitude value model aimed at promoting sustainable agricultural practices through evidence-based digital tools. The findings were integrated into a digital platform designed to support decision-making in Colombia’s potato production sector. This work provides a robust framework for the spatial analysis of soil properties and supports the development of site-specific management strategies.