MO4.R6.4
REFINEMENT OF HIGH-RISK AREA ESTIMATION IN LANDSLIDE SUSCEPTIBILITY ASSESSMENT BASED ON POSITIVE-UNLABELED LEARNING
Kosuke Kinoshita, Yukihiro Yano, Takahiro Kumura, NEC Corporation, Japan
Session:
MO4.R6: Advanced Satellite Remote Sensing and AI-driven Strategies for Multi-hazard Monitoring and Risk Prediction Oral
Track:
Community Contributed Themes
Location:
TBD
Presentation Time:
Mon, 10 Aug, 17:00 - 17:15
Presentation
Discussion
Resources
No resources available.
Session MO4.R6
MO4.R6.1: An Agentic AI-based Platform for multi-hazard ground motion monitoring
Gianmarco Pantozzi, Federica Topazio, Aldo Nasti, Francesco Valente, e-GEOS Spa, Italy
MO4.R6.2: CLASSIFYING INSAR DISPLACEMENT TRENDS USING SPATIOTEMPORAL GRAPH NEURAL NETWORKS
Regula Frauenfelder, Gard Pavel Høivang, Malte Vöge, Ole Kristian Rustebakke, Nellie Sofie Body, Norwegian Geotechnical Institute, Norway
MO4.R6.3: Advantages of satellite-borne L-band InSAR for subsidence monitoring in a humid temperate region with heterogeneous land cover
Hiroki HASHIMOTO, Takashi SHIBAYAMA, Jun SUGIMOTO, PASCO CORPORATION, Japan
MO4.R6.4: REFINEMENT OF HIGH-RISK AREA ESTIMATION IN LANDSLIDE SUSCEPTIBILITY ASSESSMENT BASED ON POSITIVE-UNLABELED LEARNING
Kosuke Kinoshita, Yukihiro Yano, Takahiro Kumura, NEC Corporation, Japan
MO4.R6.5: ASSESSING THE GENERALIZATION ABILITY OF ADF-NET FOR BUILDING CHANGE DETECTION
Qing ZHAO, Weiwei Fang, Taotao Zheng, East China Normal University, China; Pietro Mastro, IREA, National Research Council of Italy, China
Contacts