AO-PHLGJul 26, 2019

Analog forecasting of extreme-causing weather patterns using deep learning

arXiv:1907.11617v2176 citations
Originality Highly original
AI Analysis

This work addresses the challenge of accurate and fast extreme weather prediction for meteorologists and early warning systems, offering a novel deep learning approach that can augment traditional numerical models.

The paper tackles the problem of predicting extreme weather events like cold or heat waves using a data-driven analog forecasting framework with capsule neural networks, achieving accuracies of up to 80% and recalls up to 88% for forecasts 1-5 days ahead.

Numerical weather prediction (NWP) models require ever-growing computing time/resources, but still, have difficulties with predicting weather extremes. Here we introduce a data-driven framework that is based on analog forecasting (prediction using past similar patterns) and employs a novel deep learning pattern-recognition technique (capsule neural networks, CapsNets) and impact-based auto-labeling strategy. CapsNets are trained on mid-tropospheric large-scale circulation patterns (Z500) labeled $0-4$ depending on the existence and geographical region of surface temperature extremes over North America several days ahead. The trained networks predict the occurrence/region of cold or heat waves, only using Z500, with accuracies (recalls) of $69\%-45\%$ $(77\%-48\%)$ or $62\%-41\%$ $(73\%-47\%)$ $1-5$ days ahead. CapsNets outperform simpler techniques such as convolutional neural networks and logistic regression. Using both temperature and Z500, accuracies (recalls) with CapsNets increase to $\sim 80\%$ $(88\%)$, showing the promises of multi-modal data-driven frameworks for accurate/fast extreme weather predictions, which can augment NWP efforts in providing early warnings.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes