SAE-Xplainers: Rule-Based Feature Interpretation for Extreme Earth Events
The emergence of large-scale Weather and Climate (W&C) datasets offers new opportunities for modeling extreme Earth events (ExEE) and their impacts using deep learning. However, their adoption in operational settings remains limited by the lack of models' interpretability. While for conventional text and image modalities, tools such as Sparse Autoencoders (SAEs) have proven effective for extracting human-understandable concepts, their use for the analysis of ExEE remains challenging due to the nature of W&C data. To address this, we introduce (i) a geographic location-based modulation of the i
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 52%A unifying framework from neural superposition to sparse interpretable codes →
- PossiblePossibly related (embedding) · 50%Can Machine Learning Help Us Predict San Diego's Next Wildfire? - Earth.Org →
- PossiblePossibly related (embedding) · 48%A unifying framework from neural superposition to sparse interpretable codes - Nature →
- LinkedLinked via arxiv author · 85%Hugo Porta →
“SAE-Xplainers: Rule-Based Feature Interpretation for Extreme Earth Events”
- LinkedLinked via arxiv author · 85%Emanuele Dalsasso →
“SAE-Xplainers: Rule-Based Feature Interpretation for Extreme Earth Events”
- LinkedLinked via arxiv author · 85%Chang Xu →
“SAE-Xplainers: Rule-Based Feature Interpretation for Extreme Earth Events”
- LinkedLinked via arxiv author · 85%Theo Gnassounou →
“SAE-Xplainers: Rule-Based Feature Interpretation for Extreme Earth Events”
- LinkedLinked via arxiv author · 85%Devis Tuia →
“SAE-Xplainers: Rule-Based Feature Interpretation for Extreme Earth Events”