This study evaluates the effectiveness of visible near-infrared (vis-NIR) spectroscopy in predicting soil properties and soil quality indices (SQIs) to assess soil fertility. The research focuses on seven key soil indicators—pH, organic matter (OM), potassium (K), calcium (Ca), magnesium (Mg), available phosphorus (P), and total nitrogen (TN)—which are crucial for nutrient availability, pH regulation, and soil structure. Traditional SQI analysis is laborious and costly, so the study explores vis-NIR spectroscopy as a rapid and non-destructive alternative. The Cubist model, a rule-based machine learning framework, was used to predict soil properties with good accuracy (R² = 0.35–0.93). Three approaches for calculating SQI were compared: measured SQI (SQI_m), predicted SQI (SQI_p), and direct prediction of SQI (SQI_dp). The results showed that SQI_dp exhibited the highest accuracy (R² = 0.90) in predicting soil quality compared to SQI_p (R² = 0.23). The study highlights the potential of vis-NIR spectroscopy in providing a rapid, cost-effective, and environmentally friendly method for soil quality assessment, contributing to sustainable agriculture and environmental conservation.This study evaluates the effectiveness of visible near-infrared (vis-NIR) spectroscopy in predicting soil properties and soil quality indices (SQIs) to assess soil fertility. The research focuses on seven key soil indicators—pH, organic matter (OM), potassium (K), calcium (Ca), magnesium (Mg), available phosphorus (P), and total nitrogen (TN)—which are crucial for nutrient availability, pH regulation, and soil structure. Traditional SQI analysis is laborious and costly, so the study explores vis-NIR spectroscopy as a rapid and non-destructive alternative. The Cubist model, a rule-based machine learning framework, was used to predict soil properties with good accuracy (R² = 0.35–0.93). Three approaches for calculating SQI were compared: measured SQI (SQI_m), predicted SQI (SQI_p), and direct prediction of SQI (SQI_dp). The results showed that SQI_dp exhibited the highest accuracy (R² = 0.90) in predicting soil quality compared to SQI_p (R² = 0.23). The study highlights the potential of vis-NIR spectroscopy in providing a rapid, cost-effective, and environmentally friendly method for soil quality assessment, contributing to sustainable agriculture and environmental conservation.