On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “ENSO”

Distillation and Interpretability of Ensemble Forecasts of ENSO Phase using Entropic Learningphysics.comp-ph

Paper distills ensemble ENSO forecasts into simpler models for better diagnostics.

problem Interpreting complex ensemble ENSO forecasts.

method Aggregates eSPA ensemble members that correctly predict ENSO phase.

result Compact distilled models maintain forecast performance and enable diagnostics.

ENSO forecast ensemble distillation interpretability

2026-02-15abs ↗pdf ↗

Graph Neural Networks for Improved El Niño Forecastingcs.LG

Graph Neural Networks improve El Niño forecasts.

problem Improving seasonal forecasting models for ENSO.

method Application of spatiotemporal Graph Neural Networks.

result Preliminary results outperform state-of-the-art systems for 1 and 3-month projections.

Graph Neural Networks El Niño Forecasting Spatiotemporal Models Seasonal Forecasting ENSO

2020-12-02abs ↗pdf ↗

The World as a Graph: Improving El Niño Forecasts with Graph Neural Networkscs.LG

Graph neural networks improve El Niño forecasts.

problem Improving seasonal forecasting accuracy for El Niño-Southern Oscillation.

method Designing a novel graph connectivity learning module to model large-scale spatial interactions with ENSO forecasting.

result Our model \graphino outperforms state-of-the-art models for forecasts up to six months ahead.

El Niño Southern Oscillation Graph Neural Networks Seasonal Forecasting Deep Learning

2021-04-11abs ↗pdf ↗

Changepoint Detection As Model Selection: A General Frameworkstat.ME

A new framework detects changepoints in complex data.

problem Detecting structural changes in data with various patterns and trends.

method Iteratively Reweighted Fused Lasso (IRFL) for L0 model selection.

result IRFL achieves accurate changepoint detection across various challenging scenarios.

changepoint detection model selection L0 penalty Bayesian Information Criterion (BIC)seasonal patterns

2026-01-30abs ↗pdf ↗

Modeling Spatio-temporal Extremes via Conditional Variational Autoencodersstat.ML

Paper models spatio-temporal extremes using conditional variational autoencoders.

problem Modeling co-occurrence of extreme weather events under changing climate conditions.

method Conditional Variational Autoencoder (cXVAE) with CNN integration.

result Accurately emulates spatial fields and recovers extremal dependence with low computational cost.

spatio-temporal extremes conditional variational autoencoder climate indices fire weather index El Niño/Southern Oscillation

2025-12-06abs ↗pdf ↗