IJCAI 2022 China Workshop on AI for Climate Change (AI4ClimiateChange)

      Dr. Hengshu Zhu is currently a principal architect & scientist and the head of Talent Intelligence Center (TIC) of Baidu. His general research interests are data mining and machine learning, with a focus on developing fair, effective and efficient data analysis techniques for innovative business applications. He has filed more than 100+ patents, and published 100+ research papers in refereed top-tier journals (e.g., Nature Communications, IEEE TKDE, IEEE TMC, ACM TKDD, ACM TIST) and conference proceedings (e.g., ACM SIGKDD, ACM SIGIR, WWW, NeurIPS, IJCAI, AAAI). He was the recipient of the Best Student Paper Award of KSEM-2011, WAIM-2013, CCDM-2014, and the Best Paper Nomination of IEEE ICDM-2014. Due to his research achievements on data mining for business intelligence, he received the Distinguished Dissertation Award of Chinese Academy of Sciences (2016), the Distinguished Dissertation Award of China Association for Artificial Intelligence (2016), and the Special Prize of President Scholarship of Chinese Academy of Sciences (2014), and has been named as a KDD Top 20 Rising Star by Microsoft Bing Academic Search (2016) He is the Senior Member of ACM, CAAI, CCF and IEEE, and the committee member of CCF Task Force on Big Data. He is the chair of IEEE SA Talent Service and Management Working Group (TSMWG), leading the development of IEEE Standard P3154.

       演讲主题：When Search Engine Meets Earthquake

       Online search engine has been widely regarded as the most convenient approach for information acquisition. Indeed, the intensive information-seeking behaviors of search engine users make it possible to exploit search engine queries as effective “crowd sensors” for event monitoring. While some researchers have investigated the feasibility of using search engine queries for coarse-grained event analysis, the capability of search engine queries for real-time event detection has been largely neglected. To this end, in this talk we will introduce a large-scale and systematic study on exploiting real-time search engine queries for outbreak event detection, with a focus on earthquake rapid reporting. In particular, we propose a realistic system of real-time earthquake detection through monitoring millions of queries related to earthquakes from a dominant online search engine in China. Specifically, we first investigate a large set of queries for selecting the representative queries that are highly correlated with the outbreak of earthquakes. Then, based on the real-time streams of selected queries, we design a novel machine learning–enhanced two-stage burst detection approach for detecting earthquake events. Meanwhile, the epicenter and felt area of an earthquake can be accurately estimated based on the spatial-temporal distribution of search engine queries. Finally, extensive experiments with earthquake catalogs from China Earthquake Networks Center (CENC) have clearly validated the effectiveness of our system.