Prof. Yi Wang is a professor and doctoral supervisor at China University of Geosciences (Wuhan). He is the head of the Hubei Provincial First-class Undergraduate Major "Geo-information Science and Technology". He was selected into the "Cradle Plan Talent" of China University of Geosciences in 2011, "Wuhan Chenguang Young Scientific and Technological Talent Plan" in 2013, and "Daxue Scholar" Young Top-notch Talent in 2020. He was selected into the World's Top 2% Scientists list for two consecutive years (2023-2024). His main research directions include disaster remote sensing, spatiotemporal analysis and prediction of geological hazards, intelligent processing of geoscience information, and geological environment remote sensing monitoring. He has published more than 60 papers in IEEE TIP, IEEE TGRS, JOH, IJGIS, CATENA and other journals, with more than 40 SCI papers as first/corresponding author, and total citations exceeding 4000 (Google Scholar, H-Index=30). 9 papers are ESI Global Top 1% highly cited papers. He has been awarded the Elsevier "Most Cited Paper Award 2021", Hubei Provincial Excellent Geoscience Academic Paper First Prize, and other awards.

Abstract: This talk presents innovative AI methods for landslide identification using remote sensing data and the construction of open datasets. It covers deep learning-based approaches for automatic landslide detection from satellite imagery, the development of benchmark datasets for model training and evaluation, and the application of these methods in real-world scenarios for disaster prevention and mitigation.

Prof. Jisheng Xia is a Professor and Doctoral Supervisor, currently serving as the Party Committee Secretary of the School of Earth Sciences at Yunnan University. He holds several academic and professional roles, including member of the Education and Popularization Committee of the National GIS Association, Vice Chairman of the Yunnan Provincial Society of Surveying, Mapping and Geoinformation, and standing council member of the Yunnan Geographical Society. He has been recognized as a leading young academic scholar in Kunming. Since joining Yunnan University in April 2002, he has been engaged in teaching and research focusing on GIS applications, watershed eco-environment informatization, mountain environmental change and simulation, and LiDAR remote sensing. He has received multiple awards, such as the Third Prize of the Yunnan Provincial Science and Technology Award, the Second Prize of the Ministry of Education Science and Technology Award, the First and Second Prizes of the China Nonferrous Metals Industry Science and Technology Award, teaching achievement awards from Yunnan University, and the Yunnan University Wu Daguan Outstanding Teacher Award. Professor Xia has led three projects funded by the National Natural Science Foundation of China. He has authored over 80 academic papers published in journals including GIScience & Remote Sensing, Geosphere, Remote Sensing, Geomatics, Natural Hazards and Risk, Landscape Ecology, Geographical Science, and Resources and Environment in the Yangtze Basin. Among these, 20 papers are SCI-indexed with him as the first or corresponding author. He has also published four academic monographs and textbooks.

Abstract: This study proposes an estimation method for forests aboveground biomass in complex terrain areas by integrating ICESat-2 photon counting lidar data with multi-source remote sensing data. The method addresses the challenges of biomass estimation in mountainous regions with complex topography and heterogeneous vegetation, providing a new technical approach for accurate carbon stock assessment.

Prof. Faming Huang is an Associate Professor at Nanchang University. He is the principal investigator of the National Natural Science Foundation of China general program, and the recipient of the Jiangxi Provincial "Double Thousand Plan" Young High-end Innovative Talent Program and other major scientific research projects. He has been selected into the Stanford University Global Top 2% Scientists Annual Impact List for three consecutive years (2022-2024), and was rated as a CNKI Highly Cited Scholar (TOP 1%) in 2024. He is the recipient of the Jiangxi Provincial Outstanding Young Scientist Fund. His research focuses on landslide risk assessment, intelligent early warning systems, and semi-supervised learning methods for imbalanced data.

Abstract: This presentation introduces the intelligent early warning system for landslide risk, covering the theoretical foundations of semi-supervised imbalanced learning, algorithm development, and practical software implementation. It demonstrates how advanced machine learning theories can be transformed into operational tools for landslide disaster prevention and risk management.

Prof. Khairul Nizam Abdul Maulud holds a Bachelor's and Master's degree in Geoinformatics from Universiti Teknologi Malaysia and a PhD in Civil Structures from Universiti Kebangsaan Malaysia. Since 2001, he has been serving at Universiti Kebangsaan Malaysia, currently as an Associate Professor at the Faculty of Engineering and Built Environment and Director of the Earth Observation Centre at the Institute of Climate Change. He has led over 50 research grant projects and 33 consultancy works in Malaysia. He has supervised 13 PhD students, 6 master's students, and 19 undergraduate students. His expertise covers GIS and surveying, with nearly 20 years of research and consulting experience. He has successfully completed approximately 17 water-related projects, including sea level rise, geospatial analysis, land use change, water quality research, coastal erosion, and GIS-based water resource management and coastal vulnerability index assessment. Currently, he leads high-impact research in climate change, focusing on natural and economic impacts. He has published 86 journal papers, 28 books and book chapters, and 78 conference proceedings.

Abstract: This talk explores the integration of LiDAR-driven Triangulated Irregular Network (TIN) data to enhance urban terrain accuracy for 3D city modeling and flood risk assessment. It covers the technical approaches for combining LiDAR point cloud data with TIN structures, the improvement of terrain representation in urban environments, and the application of these models in flood simulation and risk evaluation.