A Novel Approach for Predicting Heavy Metal Contamination Based on Adaptive Neuro-Fuzzy Inference System and GIS in an Arid Ecosystem

The issue of agricultural soil pollution is especially important as it directly affects the quality food and lives humans animals. Soil linked to human activities practices. main objective this study assess predict contamination by heavy metals utilizing an innovative method based on adaptive neuro-fuzzy inference system (ANFIS), effective artificial intelligence technology, GIS in a semiarid dry environment. A total 150 samples were randomly collected neighboring area Bahr El-Baqar drain. Ordinary kriging (OK) was employed generate spatial pattern maps for following metals: chromium (Cr), iron (Fe), cadmium (Cd), nickel (Ni). known one most applications (AI), utilized selected (Cr, Fe, Cd, Ni). In used, 136 used training 14 testing. ANFIS predicting results compared with experimental results; comparison proved its effectiveness, root mean square error (RMSE) 0.048594 training, 0.0687 testing, which acceptable result. showed that both exponential spherical models quite suitable Cr, Ni. correlation values (R2) close test; however, stable model performed well Cd. high concentration prevalent, encompassing approximately 51.6% area. Furthermore, average degree 82.86 ± 15.59 mg kg−1 20,963.84 4447.83 1.46 0.42 48.71 11.88 clearly demonstrates superior option level pollution. Ultimately, these findings can serve foundation decision-makers develop measures mitigating metal contamination.