报告题目：Data-driven site demarcation using tailored clustering

报告人：PHOON Kok-Kwang 教授

邀请人：李典庆 教授

时间：2025年8月9日（星期六）上午9:00

地点：水电科技楼A区202会议室

报告人简介：

方国光，新加坡工程院（SAEng）院士，新加坡国家科学院（SNAS）院士，新加坡政府科学顾问委员会成员，新加坡-天津经济贸易理事会成员，新加坡民航局董事会成员，曾任新加坡国立大学高级副教务长、新加坡总理公署国家研究基金会副首席科学顾问。

方教授长期从事数字岩土工程和机器学习方法研究。主要学术荣誉包括：2005年和2020年两次获得美国土木工程师学会（ASCE）诺曼奖章，2017年获洪堡研究奖，2023年获Harry Poulos Award奖，2024年获Alfredo Ang Award，《Georisk》期刊的创刊主编和《Geodata and AI》期刊主编，新加坡注册工程师和东盟特许专业工程师等。

报告简介：

One important challenge in data-driven site characterization (DDSC) is the “site recognition challenge”. It shares some similarities with the facial recognition challenge. The purpose of recognizing “similar” sites is to allow a target site data to be supplemented by relevant data collected elsewhere to improve decision making at the target site. This is already widely adopted in geotechnical engineering practice. The key difference is that “similar” sites are identified based on judgment. The problem with judgment is that it is restricted to local/regional data that an engineer is familiar with arising from prior experience working under similar ground conditions. It is impractical to exercise judgment on big data, say to process a trillion soil records.

The tailored clustering has been shown to be more effective than classical clustering (reference solution) in identifying “similar” sites from big indirect data (BID). However, all DDSC methods - including tailored clustering, hierarchical Bayesian model (Ching 2025), and Bayesian compressive sampling (Wang et al. 2025) - face a fundamental limitation: their reliance on geotechnical project boundaries as the primary site definition. This definition is purely based on convention as it is evident that project boundaries are not related to geology or geotechnical engineering. This paper shows that it is possible to redraw the boundaries of “similar” sites based on geology/geotechnical data so that decision making at a target site is optimized. The concept of a data-driven demarcated site is novel and may open new research directions for DDSC. 

A review of tailored clustering has been published in Phoon et al. (2025). Data-driven site demarcation has not been published.

Ching, J. 2025. Bayesian Machine Learning in Geotechnical Site Characterization, CRC Press.

Phoon, K. K., Y. Cai, and C. Tang. 2025. Geotechnical “facial recognition” challenge. ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering, 11 (3): 03125001.

Wang, Y., Zhao, T., Hu, Y., Guan, Z., and Phoon, K. K. 2025. Bayesian Compressive Sensing for Site Characterization, CRC Press.

欢迎相关专业教师和研究生的光临！