Interpretable machine learning for predicting splitting strength of asphalt concrete: insights from SHAP analysis

• URL: http://arxiv.org/abs/2608.00956v1
• Date: Sun, 02 Aug 2026 03:05:54 GMT
• Title: Interpretable machine learning for predicting splitting strength of asphalt concrete: insights from SHAP analysis
• Abstract summary: This paper presents an interpretable machine-learning framework for predicting the splitting strength (ST) of asphalt concrete.<n>Six machine-learning models, namely TabPFN, ANN, SVR, RF, XGBoost, and LightGBM, were developed and compared.<n>Results show that 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 R2 of 0.88, and the highest composite score of 0.91.
• Score: 2.5274533414341493
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• GGUF-Metadata Prediction of Single-Sequence llama.cpp Throughput Across Three Systems [3.3498577203654816]
  We predict single-sequence model throughput from GGUF metadata using roofline-shaped predictors with quantization-specific scale factors fitted on reference models.<n>The cohort comprises 318 phase-depth measurements from 53 host-file configurations on two Apple M4 Max systems and an NVIDIA GTX 5080.
  arXiv  Detail & Related papers  (2026-09-14T00:31:14Z)
• Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization [54.749573452394664]
  We find that accuracy collapses as instance data grows, even when the formulation itself is simple.<n>We address this via a simple inference-time approach, BIND, which externalizes numeric data to structured files so the model binds data rather than from prompt prompt.<n>We validate our hypothesis by finetuning a model exclusively on binding and show that it outperforms end-to-end SFT and RL across three structurally distinct optimization categories.
  arXiv  Detail & Related papers  (2026-05-20T21:25:41Z)
• A Large-Scale Empirical Comparison of Meta-Learners and Causal Forests for Heterogeneous Treatment Effect Estimation in Marketing Uplift Modeling [3.321670207607951]
  Estimating Average Conditional Treatment Effects (CATE) at the individual level is central to precision marketing.<n>We present an empirical evaluation of four CATE estimators: S-Learner, T-Learner, X-Learner, and Causal Forest.<n>Our results provide practitioners with evidence-based guidance for method selection for large-scale uplift modeling pipelines.
  arXiv  Detail & Related papers  (2026-04-07T17:35:45Z)
• Exploring parameter-efficient fine-tuning (PEFT) of billion-parameter vision models with QLoRA and DoRA: insights into generalization for limited-data image classification under a 98:1 test-to-train regime [0.5765148824909591]
  This study systematically compared three approaches: training from scratch (ResNet-18, ViT-Small), frozen feature extraction, and parameter-efficient fine-tuning (PEFT) of the DINOv3 foundation model (6.7 billion parameters)<n>We evaluated QLoRA and DoRA across multiple configurations varying rank (8, 16, 64) and target modules (q_proj versus all-linear layers)<n>Results demonstrated that PEFT substantially outperformed alternatives, where the best QLoRA configuration (all-linear layers and rank=64) achieved 83.16% test accuracy with only 2.72% parameters (183.0M) in 5.8 hours
  arXiv  Detail & Related papers  (2026-03-18T14:46:07Z)
• Fine-tuning RoBERTa for CVE-to-CWE Classification: A 125M Parameter Model Competitive with LLMs [0.0]
  We construct a large-scale training dataset of 234,770 descriptions with AI-refined CWE labels.<n>On our held-out test set (27,780 samples, 205 CWE classes), the model achieves 87.4% top-1 accuracy.<n>On the external CTI-Bench benchmark (NeurIPS 2024), the model achieves 75.6% strict accuracy.
  arXiv  Detail & Related papers  (2026-03-16T07:15:57Z)
• Bayesian Transformer for Probabilistic Load Forecasting in Smart Grids [0.0]
  This study proposes a Bayesian Transformer framework that integrates three complementary uncertainty mechanisms into a PatchTST backbone.<n>A seven-level multi-quantile pinball-loss prediction head and post-training isotonic regression calibration produce sharp, near-nominally covered prediction intervals.<n>On the primary benchmark (PJM, H=24h), BT achieves a CRPS of 0.0289, improving 7.4% over Deep Ensembles and 29.9% over the deterministic LSTM.
  arXiv  Detail & Related papers  (2026-03-09T02:39:51Z)
• F10.7 Index Prediction: A Multiscale Decomposition Strategy with Wavelet Transform for Performance Optimization [0.9479454833578949]
  We propose a novel F10.7 index forecasting method using wavelet decomposition.<n>We incorporate the International Sunspot Number (ISN) and its wavelet-decomposed signals to assess their influence on prediction performance.
  arXiv  Detail & Related papers  (2026-02-24T09:18:57Z)
• Echo State Networks for Time Series Forecasting: Hyperparameter Sweep and Benchmarking [51.56484100374058]
  We evaluate whether a fully automatic, purely feedback-driven ESN can serve as a competitive alternative to widely used statistical forecasting methods.<n>Forecast accuracy is measured using MASE and sMAPE and benchmarked against simple benchmarks like drift and seasonal naive and statistical models.
  arXiv  Detail & Related papers  (2026-02-03T16:01:22Z)
• GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models [194.64264251080454]
  We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters.<n>Through multi-stage training on 23T tokens and comprehensive post-training with expert model iteration and reinforcement learning, GLM-4.5 achieves strong performance across agentic, reasoning, and coding tasks.<n>We release both GLM-4.5 (355B parameters) and a compact version, GLM-4.5-Air (106B parameters), to advance research in reasoning and agentic AI systems.
  arXiv  Detail & Related papers  (2025-08-08T17:21:06Z)
• Building Math Agents with Multi-Turn Iterative Preference Learning [56.71330214021884]
  This paper studies the complementary direct preference learning approach to further improve model performance.<n>Existing direct preference learning algorithms are originally designed for the single-turn chat task.<n>We introduce a multi-turn direct preference learning framework, tailored for this context.
  arXiv  Detail & Related papers  (2024-09-04T02:41:04Z)
• Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning [79.43940012723539]
  ADCLR is a self-supervised learning framework for learning accurate and dense vision representation. Our approach achieves new state-of-the-art performance for contrastive methods.
  arXiv  Detail & Related papers  (2023-06-23T07:38:09Z)
• Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems [63.713297451300086]
  We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9.3B. Their subsequent distillation into smaller models ranging from 17M-170M parameters, and their application to the Natural Language Understanding (NLU) component of a virtual assistant system.
  arXiv  Detail & Related papers  (2022-06-15T20:44:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.