Content deleted Content added
m Open access bot: url-access=subscription updated in citation with #oabot. |
|||
Line 333:
Machine Learning is becoming a useful tool to investigate and predict evacuation decision making in large scale and small scale disasters. Different solutions have been tested to predict if and when householders decide to evacuate during wildfires and hurricanes.<ref>{{Cite journal |last1=Sun |first1=Yuran |last2=Huang |first2=Shih-Kai |last3=Zhao |first3=Xilei |date=1 February 2024 |title=Predicting Hurricane Evacuation Decisions with Interpretable Machine Learning Methods |journal=International Journal of Disaster Risk Science |language=en |volume=15 |issue=1 |pages=134–148 |doi=10.1007/s13753-024-00541-1 |issn=2192-6395 |doi-access=free |arxiv=2303.06557 |bibcode=2024IJDRS..15..134S }}</ref><ref>{{Citation |last1=Sun |first1=Yuran |title=8 - AI for large-scale evacuation modeling: promises and challenges |date=1 January 2024 |work=Interpretable Machine Learning for the Analysis, Design, Assessment, and Informed Decision Making for Civil Infrastructure |pages=185–204 |editor-last=Naser |editor-first=M. Z. |url=https://www.sciencedirect.com/science/article/pii/B9780128240731000149 |access-date=19 May 2024 |series=Woodhead Publishing Series in Civil and Structural Engineering |publisher=Woodhead Publishing |isbn=978-0-12-824073-1 |last2=Zhao |first2=Xilei |last3=Lovreglio |first3=Ruggiero |last4=Kuligowski |first4=Erica |archive-date=19 May 2024 |archive-url=https://web.archive.org/web/20240519121547/https://www.sciencedirect.com/science/article/abs/pii/B9780128240731000149 |url-status=live }}</ref><ref>{{Cite journal |last1=Xu |first1=Ningzhe |last2=Lovreglio |first2=Ruggiero |last3=Kuligowski |first3=Erica D. |last4=Cova |first4=Thomas J. |last5=Nilsson |first5=Daniel |last6=Zhao |first6=Xilei |date=1 March 2023 |title=Predicting and Assessing Wildfire Evacuation Decision-Making Using Machine Learning: Findings from the 2019 Kincade Fire |url=https://doi.org/10.1007/s10694-023-01363-1 |journal=Fire Technology |language=en |volume=59 |issue=2 |pages=793–825 |doi=10.1007/s10694-023-01363-1 |issn=1572-8099 |access-date=19 May 2024 |archive-date=19 May 2024 |archive-url=https://web.archive.org/web/20240519121534/https://link.springer.com/article/10.1007/s10694-023-01363-1 |url-status=live |url-access=subscription }}</ref> Other applications have been focusing on pre evacuation decisions in building fires.<ref>{{Cite journal |last1=Wang |first1=Ke |last2=Shi |first2=Xiupeng |last3=Goh |first3=Algena Pei Xuan |last4=Qian |first4=Shunzhi |date=1 June 2019 |title=A machine learning based study on pedestrian movement dynamics under emergency evacuation |url=https://www.sciencedirect.com/science/article/pii/S037971121830376X |journal=Fire Safety Journal |volume=106 |pages=163–176 |doi=10.1016/j.firesaf.2019.04.008 |bibcode=2019FirSJ.106..163W |issn=0379-7112 |access-date=19 May 2024 |archive-date=19 May 2024 |archive-url=https://web.archive.org/web/20240519121539/https://www.sciencedirect.com/science/article/abs/pii/S037971121830376X |url-status=live |hdl=10356/143390 |hdl-access=free }}</ref><ref>{{Cite journal |last1=Zhao |first1=Xilei |last2=Lovreglio |first2=Ruggiero |last3=Nilsson |first3=Daniel |date=1 May 2020 |title=Modelling and interpreting pre-evacuation decision-making using machine learning |url=https://www.sciencedirect.com/science/article/pii/S0926580519313184 |journal=Automation in Construction |volume=113 |article-number=103140 |doi=10.1016/j.autcon.2020.103140 |hdl=10179/17315 |issn=0926-5805 |access-date=19 May 2024 |archive-date=19 May 2024 |archive-url=https://web.archive.org/web/20240519121548/https://www.sciencedirect.com/science/article/abs/pii/S0926580519313184 |url-status=live |hdl-access=free }}</ref>
Machine learning is also emerging as a promising tool in geotechnical engineering, where it is used to support tasks such as ground classification, hazard prediction, and site characterization. Recent research emphasizes a move toward data-centric methods in this field, where machine learning is not a replacement for engineering judgment, but a way to enhance it using site-specific data and patterns.<ref>{{Cite journal |last1=Phoon |first1=Kok-Kwang |last2=Zhang |first2=Wengang |date=2023-01-02 |title=Future of machine learning in geotechnics |url=https://www.tandfonline.com/doi/full/10.1080/17499518.2022.2087884 |journal=Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards |language=en |volume=17 |issue=1 |pages=7–22 |doi=10.1080/17499518.2022.2087884 |bibcode=2023GAMRE..17....7P |issn=1749-9518|url-access=subscription }}</ref>
== Limitations ==
| |||