Predictive comparison and assessment of ANFIS and ANN, as efficient tools in modeling degradation of total petroleum hydrocarbon (TPH)

Abstract

Composting is an effective organic waste management practice with a sustainable environmental impact on soil. In most cases, composting materials are agricultural residues constituting a huge environmental challenge. This study investigates the composting biostimulation of total petroleum hydrocarbon (TPH) contaminated soil using organic compost prepared from palm oil mill effluent (CPOME). The performance of CPOME in TPH degradation was evaluated using the first-order kinetic model and CO₂ evolution. The artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) modelling approaches were further employed to optimize the experimental response. The experimental designs for ANFIS and ANN modelling were done using the central composite design (CCD). Statistical parameters such as RMSE, MSE, and MAE were used to evaluate model performance and comparisons. The first-order kinetic model and CO₂ released showed that TPH degradation favours contaminated soil with 40 g/L initial TPH concentration. The first-order kinetic model observed a decrease in the constant degradation rate with increasing TPH concentration. The CO₂ evolution, which measures microbial respiration/activity, also showed a decline in released CO₂ with increasing TPH concentration. Lower values of RMSE, MSE, and MAE were obtained for the ANFIS model compared with the ANN. The R² values between the experimental and model-predicted responses showed that the ANFIS (0.9349) model predictions fitted adequately compared to the ANN (0.8862). Finally, comparison and model performances showed that the ANFIS model prediction capability was considerably better than the ANN. • The compost from palm oil mill effluent proved effective in TPH degradation • ANFIS predicted TPH degradation was better than the ANN predicted • Notable organic materials in the compost includes polysaccharides, nitrogen and lignin