Machine learning (ML) is in constant transformation and various engineering disciplines are now heavily investing in it too. Currently, the majority of civil- and environmental-based works on ML are utilizing pure data-driven (i.e., black box) models built on correlations and associations. These models, however, do not truly identify the cause-effect relationship needed to answer questions such as: what caused a given structure to fail? Why does a particular construction material behave the way it does under specific conditions?

Causal Machine Learning in Civil and Environmental Engineering: Case Studies and Datasets aims to introduce causal ML approaches to civil and environmental engineering, covering theories, applications, as well as providing datasets, code, and examples of solutions to key problems in the sector. Students, academics, and engineering professionals both in the private and public sectors will find this book to be an invaluable reference source.

Introduces causal ML from a civil and environmental engineering perspective, comprehensively covering both theory and step-by-step application procedures.

Includes flowcharts and examples for the successful adoption of causal ML to solve various engineering problems.

Provides insight into not only the latest research developments, but also future implications of predictive science for engineering.

Is accompanied by a website where all relevant datasets, algorithms, and code are hosted.