Explainable Artificial Intelligence Model for Evaluating Shear Strength Parameters of Municipal Solid Waste Across Diverse Compositional Profiles

2025-02-20

AI Summary

Predicting the shear strength of municipal solid waste (MSW) has long suffered from low accuracy and poor interpretability due to its extreme heterogeneity and time-dependent degradation behavior. To address this, we propose the first explainable AI (XAI) framework integrating a multilayer perceptron (MLP) with SHAP (Shapley Additive Explanations) attribution analysis. This framework quantifies, for the first time, the nonlinear effects of fiber content, particle size distribution, and organic/plastic fractions on cohesion and internal friction angle. Trained on extensive direct shear test data, the model achieves mean absolute percentage errors of 14.96% for cohesion and 7.42% for internal friction angle—substantially outperforming gradient-boosting methods. Crucially, it delivers auditable, component-wise contribution rankings and actionable, engineering-oriented recommendations, thereby unifying high predictive accuracy with strong model interpretability.

Technology Category

• Machine Learning: Transparent, Interpretable, Explainable ML
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Accurate prediction of shear strength parameters in Municipal Solid Waste (MSW) remains a critical challenge in geotechnical engineering due to the heterogeneous nature of waste materials and their temporal evolution through degradation processes. This paper presents a novel explainable artificial intelligence (XAI) framework for evaluating cohesion and friction angle across diverse MSW compositional profiles. The proposed model integrates a multi-layer perceptron architecture with SHAP (SHapley Additive exPlanations) analysis to provide transparent insights into how specific waste components influence strength characteristics. Training data encompassed large-scale direct shear tests across various waste compositions and degradation states. The model demonstrated superior predictive accuracy compared to traditional gradient boosting methods, achieving mean absolute percentage errors of 7.42% and 14.96% for friction angle and cohesion predictions, respectively. Through SHAP analysis, the study revealed that fibrous materials and particle size distribution were primary drivers of shear strength variation, with food waste and plastics showing significant but non-linear effects. The model's explainability component successfully quantified these relationships, enabling evidence-based recommendations for waste management practices. This research bridges the gap between advanced machine learning and geotechnical engineering practice, offering a reliable tool for rapid assessment of MSW mechanical properties while maintaining interpretability for engineering decision-making.

Problem

• Predict shear strength of Municipal Solid Waste
• Explainable AI for geotechnical engineering
• Influence of waste composition on strength

Innovation

• Explainable AI for shear strength
• Multi-layer perceptron with SHAP
• Predicts MSW mechanical properties accurately