TU2.M1.4
Uncertainty-Aware Deep Learning for Large-Scale Precipitation Type Classification: A Multi-Year Global Study
Marko Orescanin, Naval Postgraduate School, United States; Veljko Petkovic, University of Maryland, United States; Dalton Duvio, Naval Postgraduate School, United States
Session:
TU2.M1: Probabilistic Machine Learning for Earth Observation Oral
Track:
Community-Contributed Sessions
Location:
Room M1
Presentation Time:
Tuesday, 5 August, 11:15 - 11:30
Session Co-Chairs:
Francisco Mena, University of Kaiserslautern-Landau and Miro Miranda Lorenz, German Research Center for Artificial Intelligence
Presentation
Discussion
Resources
No resources available.
Session TU2.M1
TU2.M1.1: UA-VSTN: Uncertainty-aware Variational Spatiotemporal Network for Traffic State Prediction
Yanhong Ma, Yuxi Duan, Chao Zhang, State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, China
TU2.M1.2: Scaling Uncertainty Quantification From Patches to Scenes Through Discontinuity-Aware Stitching
Stephen Steckler, Marko Orescanin, Scott Powell, Pedro Ortiz, Naval Postgraduate School, United States; Veljko Petkovic, University of Maryland, United States
TU2.M1.3: regDiff: Regression Diffusion for Earth Observation
Miro Miranda, Ashutosh Dinesh, Duway Nicolas Lesmes-Leon, Francisco Mena, Marcela Charfuelan, Andreas Dengel, German Research Center for Artifical Intelligence, Germany
TU2.M1.4: Uncertainty-Aware Deep Learning for Large-Scale Precipitation Type Classification: A Multi-Year Global Study
Marko Orescanin, Naval Postgraduate School, United States; Veljko Petkovic, University of Maryland, United States; Dalton Duvio, Naval Postgraduate School, United States
TU2.M1.5: Uncertainty-Guided Continuous Adaptation of Deep Learning Models in Dynamic Remote Sensing Environments
Mohammed El Amin LARABI, Meziane Iftene, Algerian Space Agency, Algeria; OMAR ALIKARA, Algerian Sapce Agency, Algeria
Resources
No resources available.