Human civilizations are vulnerable in front of natural disasters, we have seen so many catastrophic events in our history. We always searching for methods that can monitor, mitigate the disaster. In this talk, I will talk about our efforts building an earthquake disaster platform that enable us to monitor, quantify the disaster. Many of the problems are hard to be addressed in the past, now can be solved by applying machine learning. I will start from the MyShake project, which is using the smartphone sensors to monitor and detect earthquakes, and end with more recent projects that I am working on to expand this disaster platform to pre- and post-disaster prevention and mitigation.
Two papers: https://advances.sciencemag.org/content/2/2/e1501055 and https://pubs.geoscienceworld.org/ssa/srl/article/567499/machine-learning-aspects-of-the-myshake-global.
Full details about this meeting will be posted here: https://bids.github.io/MLStatsForum/.
The Berkeley Statistics and Machine Learning Forum meets biweekly to discuss current applications across a wide variety of research domains and software methodologies. Hosted by UC Berkeley Physics Professor and BIDS Senior Fellow Uros Seljak, these active sessions bring together domain scientists, statisticians and computer scientists who are either developing state-of-the-art methods or are interested in applying these methods in their research. Practical questions about the meetings can be directed to BIDS Fellow Francois Lanusse. All interested members of the UC Berkeley and LBL communities are welcome and encouraged to attend. To receive email notifications about the meetings and upvote papers for discussion, please register here.
Speaker(s)
Qingkai Kong
Qingkai Kong is an assistant researcher at Berkeley Seismology Lab and Division of Data Sciences. He has a background of seismology, civil engineering and data science. His research interests are earthquake early warning, large scale low-cost sensor network, and data science in seismology. He created MyShake project during his PhD study and worked on the project ever since. In this project, he applies different machine learning algorithms to address core problems in building this global smartphone seismic network. He is now working on building a disaster platform that span before, during and after of the disaster using machine learning. Currently, he is also a visiting researcher in Google’s visiting faculty program. More details at: http://seismo.berkeley.edu/qingkaikong/.