建筑工程技术

抽象的

An Examination of Physics-based Machine Learning in Civil Engineering

Michael Baxter

The potential are expanding across all industries thanks to the recent advancements in machine learning (ML) and deep learning (DL). Although ML is a useful tool that may be used in many different fields, it can be difficult to directly apply it to civil engineering issues. Lab-simulated ML for civil engineering applications frequently fails in real-world assessments. This is typically linked to a phenomenon known as data shift, which occurs when the data used to train and test the ML model differ from the data it meets in the real world. To address data shift issues, a physics-based ML model integrates data, partial differential equations (PDEs), and mathematical models. In order to accomplish supervised learning problems while adhering to any given laws, physics-based ML models are trained. Physics-based Fluid dynamics, quantum physics, computational resources, and data storage are among the many scientific fields where machine learning (ML) is taking centre stage. This essay examines the development of physics-based machine learning and its use in civil engineering.