WE1.R17.2

QUANTITATIVE ANALYSIS OF PRIMARY ATTRIBUTION EXPLAINABLE ARTIFICIAL INTELLIGENCE METHODS FOR REMOTE SENSING IMAGE CLASSIFICATION

Akshatha Mohan, Joshua Peeples, Texas A&M University, United States
Session:
WE1.R17: Opening the Black Box: Explainable AI/ML in Remote Sensing Analysis I Oral
Track:
Community-Contributed Sessions
Location:
Room 212/214
Presentation Time:
Wed, 19 Jul, 08:42 - 08:54 Pacific Time (UTC -7)
Session Co-Chairs:
Amanda Ziemann, Los Alamos National Laboratory and Eric Flynn, Los Alamos National Laboratory
Session Manager:
Mark Angelo Purio
Presentation
Not logged in.
Discussion
Not logged in.
Resources
No resources available.
Session WE1.R17
WE1.R17.1: HYPERSPECTRAL TARGET IDENTIFICATION USING PHYSICS-GUIDED NEURAL NETWORKS WITH EXPLAINABILITY AND FEATURE ATTRIBUTION
Natalie Klein, Adra Carr, Zigfried Hampel-Arias, Allison Zastrow, Amanda Ziemann, Eric Flynn, Los Alamos National Laboratory, United States
WE1.R17.2: QUANTITATIVE ANALYSIS OF PRIMARY ATTRIBUTION EXPLAINABLE ARTIFICIAL INTELLIGENCE METHODS FOR REMOTE SENSING IMAGE CLASSIFICATION
Akshatha Mohan, Joshua Peeples, Texas A&M University, United States
WE1.R17.3: ADVANCING SEA ICE CLASSIFICATION CAPABILITIES IN SAR IMAGERY VIA POLARIMETRIC ANALYSIS AND MACHINE LEARNING
Elena Reinisch, Lauren Castro, Amber Whelsky, Los Alamos National Lab, United States
WE1.R17.4: EXPLAINING THE ABSORPTION FEATURES OF DEEP LEARNING HYPERSPECTRAL CLASSIFICATION MODELS
Arthur Vandenhoeke, Lennert Antson, Guillem Ballesteros, Kuva Space, Finland; Jonathan Crabbé, University of Cambridge, United Kingdom; Michal Shimoni, Kuva Space, Finland
WE1.R17.5: EXPLAINING MULTIMODAL DATA FUSION: OCCLUSION ANALYSIS FOR WILDERNESS MAPPING
Burak Ekim, Michael Schmitt, University of the Bundeswehr Munich, Germany
Resources
No resources available.