EarthquakeNet estimates per-cell dispersion in negative binomial regression via spatial embeddings and MLP, delivering 8.6% lower mean pinball deviation and 12.5% better tail CRPS than a global-alpha GLM baseline in walk-forward tests.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.geo-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Neural Negative Binomial Regression for Weekly Seismicity Forecasting: Per-Cell Dispersion Estimation and Tail Risk Assessment
EarthquakeNet estimates per-cell dispersion in negative binomial regression via spatial embeddings and MLP, delivering 8.6% lower mean pinball deviation and 12.5% better tail CRPS than a global-alpha GLM baseline in walk-forward tests.