TRIDENT-Risk: An AI-driven temporal ensemble framework for proactive high-severity accident risk forecasting in Intelligent Transportation Systems
- 1Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, Punjab, India
- 2School of Computer Science, Faculty of Science and Engineering, University of Nottingham, Ningbo China, Ningbo, Zhejiang, China
Abstract
High-severity traffic accidents impose substantial human and economic burdens, necessitating proactive and data-driven risk forecasting mechanisms within intelligent transportation systems. This study proposed TRIDENT-Risk, a temporal risk-driven imbalance-optimized ensemble framework for high-severity accident prediction using the eXtreme Gradient Boosting (XGBoost) model. The approach integrates spatial–temporal aggregation, multi-scale lag and rolling risk features, imbalance-aware gradient boosting, and threshold optimization to enhance minority-class detection. Experimental evaluation using publicly accessible US-Accidents dataset including about 7.7 million accident records from February 2016 to March 2023 demonstrated that the proposed TRIDENT-Risk achieved a ROC-AUC of 0.8917, PR-AUC of 0.7266, precision of 0.60, recall of 0.81, F1-score of 0.69 and accuracy of 0.82. Compared with the strongest baseline (MLP), the proposed framework improved high-risk recall from 0.70 to 0.81 (15.7% relative improvement), increased ROC-AUC from 0.8776 to 0.8917 and improved PR-AUC from 0.7016 to 0.7266, demonstrating superior minority-class detection and reliable proactive accident forecasting. Temporal grid-based aggregation was used to frame high-severity accidents as a binary prediction problem and an 80:20 chronological train-test split was used to eliminate temporal leaking. The proposed framework offers a scalable and interpretable solution for proactive traffic safety management and supports intelligent decision-making in next-generation transportation systems.
Related
- Development and evaluation of an intelligent centralized transportation dispatching information system in a large tertiary hospital: a single-center retrospective observational study
- Proactive early invisible spoilage-risk prediction through uncertainty-quantified temporal microbial growth intelligence
- An Explainable Disease-Aware Intelligent Histopathological Representation Learning Framework for Generalizable Breast Cancer Classification
- An agentic framework for intelligent clinical laboratory medicine.
- Athlete-AI: a multi-modal artificial intelligence framework for personalized athlete monitoring and injury risk forecasting
BibTeX
@article{vashisht2026tridentrisk,
title = {{TRIDENT-Risk: An AI-driven temporal ensemble framework for proactive high-severity accident risk forecasting in Intelligent Transportation Systems}},
author = {Sanchit Vashisht and Shalli Rani and Fazlullah Khan},
journal = {PLOS One},
year = {2026},
month = oct,
doi = {10.1371/journal.pone.0357089},
url = {https://doi.org/10.1371/journal.pone.0357089},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - TRIDENT-Risk: An AI-driven temporal ensemble framework for proactive high-severity accident risk forecasting in Intelligent Transportation Systems
AU - Sanchit Vashisht
AU - Shalli Rani
AU - Fazlullah Khan
PY - 2026
DA - 2026/10/07
JO - PLOS One
DO - 10.1371/journal.pone.0357089
UR - https://doi.org/10.1371/journal.pone.0357089
AB - High-severity traffic accidents impose substantial human and economic burdens, necessitating proactive and data-driven risk forecasting mechanisms within intelligent transportation systems. This study proposed TRIDENT-Risk, a temporal risk-driven imbalance-optimized ensemble framework for high-severity accident prediction using the eXtreme Gradient Boosting (XGBoost) model. The approach integrates spatial–temporal aggregation, multi-scale lag and rolling risk features, imbalance-aware gradient boosting, and threshold optimization to enhance minority-class detection. Experimental evaluation using publicly accessible US-Accidents dataset including about 7.7 million accident records from February 2016 to March 2023 demonstrated that the proposed TRIDENT-Risk achieved a ROC-AUC of 0.8917, PR-AUC of 0.7266, precision of 0.60, recall of 0.81, F1-score of 0.69 and accuracy of 0.82. Compared with the strongest baseline (MLP), the proposed framework improved high-risk recall from 0.70 to 0.81 (15.7% relative improvement), increased ROC-AUC from 0.8776 to 0.8917 and improved PR-AUC from 0.7016 to 0.7266, demonstrating superior minority-class detection and reliable proactive accident forecasting. Temporal grid-based aggregation was used to frame high-severity accidents as a binary prediction problem and an 80:20 chronological train-test split was used to eliminate temporal leaking. The proposed framework offers a scalable and interpretable solution for proactive traffic safety management and supports intelligent decision-making in next-generation transportation systems.
SN - 1932-6203
ER -