Interpretable machine learning for predicting splitting strength of asphalt concrete: insights from SHAP analysis
Summary
An arXiv paper presents an interpretable machine-learning framework for predicting the splitting strength of asphalt concrete using SHAP analysis, comparing six models with TabPFN performing best.
View Cached Full Text
Cached at: 08/04/26, 07:44 AM
# Interpretable machine learning for predicting splitting strength of asphalt concrete: insights from SHAP analysis Source: [https://arxiv.org/abs/2608.00956](https://arxiv.org/abs/2608.00956) [View PDF](https://arxiv.org/pdf/2608.00956) > Abstract:This paper presents an interpretable machine\-learning framework for predicting the splitting strength \(ST\) of asphalt concrete and supporting data\-driven mixture design\. A database consisting of 296 samples was established, and 14 input variables related to asphalt properties, aggregate gradation, and fiber characteristics were selected for modeling\. Six machine\-learning models, namely TabPFN, ANN, SVR, RF, XGBoost, and LightGBM, were developed and compared\. Hyperparameter optimization was performed for five models using NSGA\-II, while TabPFN was directly applied with its default configuration\. The results show that all six models achieved satisfactory predictive capability, whereas TabPFN delivered the best overall performance on the testing set, with the lowest RMSE of 0\.28, MAE of 0\.21, MAPE of 18\.01%, MAD of 0\.14, the highest R^2 of 0\.88, and the highest composite score of 0\.91\. SHAP analysis further revealed that nine dominant variables accounted for 92\.0% of the total average contribution, among which Ag9\.5, FT, Ag4\.75, AC, and Du were the most influential\. In addition, favorable parameter ranges for improving ST were quantified, such as Ag9\.5 < 66\.8%, Ag4\.75 < 45\.0%, AC < 5\.4 wt\.%, AV < 3\.6%, and Du \> 134\.7 cm\. Finally, a GUI platform integrating prediction and SHAP\-based explanation was developed to improve the accessibility and practical applicability of the proposed framework\. ## Submission history From: Dongzhao Jin \[[view email](https://arxiv.org/show-email/7fef3eea/2608.00956)\] **\[v1\]**Sun, 2 Aug 2026 03:05:54 UTC \(1,194 KB\)
Similar Articles
From Scoring to Explanations: Evaluating SHAP and LLM Rationales for Rubric-based Teaching Quality Assessment
This paper proposes a framework for sentence-level interpretability of rubric-based scoring, comparing SHAP and LLM-generated rationales. It finds that fine-tuned pretrained language models outperform LLMs in prediction accuracy, and SHAP provides more faithful and transferable explanations.
From field-scale to large-scale spectral libraries: Tabular foundation models in soil spectroscopy
This paper systematically compares tabular foundation models (TabPFN) with classical regression approaches across 85 soil spectroscopy tasks, finding that TabPFN combined with PLS-derived features achieves the best predictive performance from field-scale to global spectral libraries.
Evaluating Machine Learning Models for Post-Wildfire Debris-Flow Prediction
This paper systematically evaluates 15 machine learning models, including the TabPFN foundation model, for post-wildfire debris-flow prediction using USGS basin-scale data, finding TabPFN achieves the best performance (threat score 0.637) and that synthetic data augmentation improves most models.
Applied Explainability for Large Language Models: A Comparative Study
A comparative study evaluating three explainability techniques (Integrated Gradients, Attention Rollout, SHAP) on fine-tuned DistilBERT for sentiment classification, highlighting trade-offs between gradient-based, attention-based, and model-agnostic approaches for LLM interpretability.
On Surrogate Modeling of Static Response of AM Short-Fiber Thermoplastics Using Graph Neural Networks
This paper proposes a data-driven surrogate modeling framework using a hybrid Graph Neural Network-Long Short-Term Memory architecture to predict the static response of additively manufactured short-fiber thermoplastics, achieving high accuracy (R²≈0.98) and two orders of magnitude speedup over finite element simulations.