Soil Fertility Forecasting with Neutrosophic-Based Uncertainty Management

Authors

Franklin Parrales-Bravo, Maestría en Gestión y Analítica de Datos, Universidad Bolivariana del Ecuador, Guayaquil, Ecuador; Grupo de Investigación en Inteligencia Artificial, Universidad de Guayaquil, Guayaquil, EcuadorFollow
Roberto Tolozano-Benites, Maestría en Gestión y Analítica de Datos, Universidad Bolivariana del Ecuador, Guayaquil, EcuadorFollow
Dayron Rumbaut-Rangel, Maestría en Gestión y Analítica de Datos, Universidad Bolivariana del Ecuador, Guayaquil, EcuadorFollow

Abstract

This study presents a machine learning framework that combines Random Forest classification with neutrosophic logic to predict soil fertility from 16 physicochemical properties. The model achieves robust classification accuracy (95%) while introducing a novel uncertainty quantification mechanism through neutrosophic truth (T ), indeterminacy (I) and falsity (F ) values derived from prediction probabilities, assigning high-confidence (T = 0.9) to probabilities ≥0.9, indeterminacy (I = 0.3) to borderline cases (0.5≤p

Recommended Citation

Parrales-Bravo, Franklin; Roberto Tolozano-Benites; and Dayron Rumbaut-Rangel. "Soil Fertility Forecasting with Neutrosophic-Based Uncertainty Management." Neutrosophic Sets and Systems 92, 1 (2025). https://digitalrepository.unm.edu/nss_journal/vol92/iss1/6