AI-Enabled Integration of Onboard and Remote Sensing for Monitoring and Decision Support of Transportation Geotechnical Assets

Transportation infrastructure relies heavily on geotechnical assets such as slopes, embankments, retaining structures, foundations, and earthworks. The performance of these systems is influenced by environmental loading, progressive degradation, and increasingly frequent extreme events. Traditional inspection-based approaches often provide limited temporal and spatial resolution, making it difficult to detect early signs of deterioration or to understand the complex behavior of geotechnical systems at network scale. Recent advances in onboard (in-situ) and remote sensing technologies enable continuous and multi-scale observations of infrastructure performance. At the same time, developments in artificial intelligence (AI), machine learning (ML), and computational modelling provide new opportunities to transform large and heterogeneous monitoring datasets into actionable knowledge. These advances are creating new possibilities for data-driven analysis and predictive modelling of transportation geotechnical systems.The goal of this Research Topic is to advance computational and data-driven approaches for the assessment and prediction of transportation geotechnical infrastructure performance. In particular, the Topic focuses on methodologies that integrate monitoring data with AI/ML algorithms, statistical analysis, and physics-based models to improve understanding, diagnosis, and forecasting of infrastructure behavior. Despite rapid progress in sensing technologies, major challenges remain in the effective use of monitoring data, including data fusion, uncertainty quantification, model generalization, and the interpretability of AI-driven predictions. This Research Topic aims to highlight methodological advances that address these challenges and demonstrate how data-informed computational models can support condition assessment, anomaly detection, performance forecasting, and risk evaluation of geotechnical assets. Contributions that combine monitoring data with advanced modelling frameworks to support reliable and scalable infrastructure assessment are particularly encouraged.This Research Topic welcomes contributions focusing on computational modelling, data-driven analysis, and methodological developments relevant to the monitoring and assessment of transportation geotechnical assets. Topics of interest include, but are not limited to:• Data-driven modelling and machine learning for geotechnical infrastructure behavior and performance prediction• Integration and fusion of multi-source monitoring data to support computational modelling• Hybrid modelling approaches combining physics-based models and AI/ML techniques• Anomaly detection, damage identification, and performance forecasting using monitoring data• Uncertainty quantification, reliability assessment, and explainable AI in infrastructure monitoring• Methodological frameworks for transforming monitoring data into decision-relevant indicators• Computational approaches applied to slopes, embankments, retaining structures, foundations, and earthworksThe Research Topic welcomes original research articles, review papers, and methodological studies that contribute to advances in computational and data-driven approaches for geotechnical infrastructure assessment. Topic editors: Joaquim Tinoco, Jesús Balado Frías Source: https://www.frontiersin.org/research-topics/78322/ai-enabled-integration-of-onboard-and-remote-sensing-for-monitoring-and-decision-support-of-transportation-geotechnical-assets