Determination of Soil Agricultural Aptitude for Sugar Cane Production in Vertisols with Machine Learning

Sugarcane is one of the main agro-industrial products consumed worldwide, and, therefore, use suitable soils a key factor to maximize its production. As result, need evaluate soil matrices, including many physical, chemical, and biological parameters, determine soil’s aptitude for growing food crops increases. Machine learning techniques were used perform an in-depth analysis physicochemical indicators vertisol-type in sugarcane The importance relationship between each was studied. Furthermore, objective present work, determination minimum number most important necessary agricultural suitability soils, with view reducing analyses terms required evaluation. results obtained relating estimation capability using different numbers parameters showed accuracy up 91% when implementing three parameters: Potassium (K), Calcium (Ca) Cation Exchange Capacity (CEC). reported results, indicated that it possible estimate eleven average 73% only data K, Ca CEC as input Learning models. Knowledge these enables values potential regard Hydrogen (pH), organic matter (OM), Phosphorus (P), Magnesium (Mg), Sulfur (S), Boron (B), Copper (Cu), Manganese (Mn), Zinc (Zn), Calcium/Magnesium ratio (Ca/Mg), also texture soil.