Review of Recent Developments in AI-based Data Processing and Prediction for Braced Excavation Design

Abstract

Abstract This paper presents a review of the recent advances in the application of Artificial intelligence (AI) techniques for data processing and prediction in the design and construction of braced excavation systems. It introduces various AI algorithms employed in addressing complex data processing and deformation prediction challenges in braced excavation. A pivotal development has been in the area of soil parameter and in-situ monitoring data processing, which facilitates more reliable site characterization for efficient design. This paper delves into wall system and deformation predictions, showcasing AI’s ability to integrate multi-source data for real-time prediction. It also addresses spatiotemporal prediction, enhancing prediction accuracy by accounting for uncertainties. The significance of groundwater is highlighted by introducing predictive models that consider groundwater drawdown. Additionally, it discusses stability prediction based on the factor of safety of braced excavation, enabling proactive safety management for the retaining wall system and the surrounding environment. Furthermore, the paper discusses the challenges and opportunities associated with the use of generative AI and large language models, providing an overview of their significance, applications, and future directions in braced excavation.