Artificial intelligence-based prediction of geotechnical impacts of polyethylene bottles and polypropylene on clayey soil

Abstract. This study aims to investigate the application of artificial intelligence (AI) methods in predicting resilient modulus soil mixtures with polyethylene (PE) bottles and polypropylene (PP). The AI used are neural network (ANN) classification regression random forest (CRRF), modeling was conducted using a database 160 datasets. also evaluated importance different input parameters on accuracy models. results show that CRRF model is more accurate than ANN effects materials PE PP modulus. Additionally, found number hidden layers neurons should be optimized for best performance increasing their does not always lead increased accuracy. Finally, identified most least important effect mixture both