Bayesian Machine Learning in Geotechnical Site Characterization

This presents recent advancements in probabilistic geotechnical site characterization. It reviews probability theories and models for cross correlation and spatial correlation, and presents methods for Bayesian parameter estimation and prediction. Use of these methods is demonstrated with geotechnical site characterization examples.

Sommario

1. Bayesian Approach. 2. Review of Probability and Models. 3. Bayesian Parameter Estimation and Prediction. 4. Geotechnical Data and Bayesian Modeling. 5. Full-scale Real Case Study.

Info autore

Jianye Ching is Distinguished Professor at National Taiwan University and Convener of the Civil & Hydraulic Engineering Program of the Ministry of Science and Technology of Taiwan. He is Chair of ISSMGE's TC304 (risk), Chair of Geotechnical Safety Network (GEOSNet), and Managing Editor of the journal Georisk.

Riassunto

This presents recent advancements in probabilistic geotechnical site characterization. It reviews probability theories and models for cross correlation and spatial correlation, and presents methods for Bayesian parameter estimation and prediction. Use of these methods is demonstrated with geotechnical site characterization examples.

Dettagli sul prodotto

• Autori: Jianye Ching, Jianye (National Taiwan University Ching, Ching Jianye
• Editore: Taylor & Francis Ltd.
• Lingue: Inglese
• Formato: Copertina rigida
• Pubblicazione: 06.08.2024
• EAN: 9781032314419
• ISBN: 978-1-0-3231441-9
• Pagine: 176
• Serie: Challenges in Geotechnical and Rock Engineering
• Categorie: Scienze naturali, medicina, informatica, tecnica > Biologia > Ecologia; machine learning, NATURE / Natural Resources, MATHEMATICS / Probability & Statistics / General, TECHNOLOGY & ENGINEERING / Civil / General, TECHNOLOGY & ENGINEERING / Environmental / General, MATHEMATICS / Probability & Statistics / Bayesian Analysis, environmental science, engineering & technology, Science / Environmental Science, Waste Management, Probability & statistics, Civil engineering, surveying & building, COMPUTERS / Data Science / Machine Learning, Bayesian Inference