Weather4cast at NeurIPS 2022: Super-Resolution Rain Movie Prediction under Spatio-temporal Shifts

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F23%3A00368674" target="_blank" >RIV/68407700:21240/23:00368674 - isvavai.cz</a>

Výsledek na webu

<a href="https://proceedings.mlr.press/v220/gruca22a" target="_blank" >https://proceedings.mlr.press/v220/gruca22a</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Weather4cast at NeurIPS 2022: Super-Resolution Rain Movie Prediction under Spatio-temporal Shifts

Popis výsledku v původním jazyce

Weather4cast again advanced modern algorithms in AI and machine learning through a highly topical interdisciplinary competition challenge: The prediction of hi-res rain radar movies from multi-band satellite sensors, requiring data fusion, multi-channel video frame prediction, and super-resolution. Accurate predictions of rain events are becoming ever more critical, with climate change increasing the frequency of unexpected rainfall. The resulting models will have a particular impact where costly weather radar is not available. We here present highlights and insights emerging from the thirty teams participating from over a dozen countries. To extract relevant patterns, models were challenged by spatio-temporal shifts. Geometric data augmentation and test-time ensemble models with a suitable smoother loss helped this transfer learning. Even though, in ablation, static information like geographical location and elevation was not linked to performance, the general success of models incorporating physics in this competition suggests that approaches combining machine learning with application domain knowledge seem a promising avenue for future research. Weather4cast will continue to explore the powerful benchmark reference data set introduced here, advancing competition tasks to quantitative predictions, and exploring the effects of metric choice on model performance and qualitative prediction properties.

Název v anglickém jazyce

Weather4cast at NeurIPS 2022: Super-Resolution Rain Movie Prediction under Spatio-temporal Shifts

Popis výsledku anglicky

Weather4cast again advanced modern algorithms in AI and machine learning through a highly topical interdisciplinary competition challenge: The prediction of hi-res rain radar movies from multi-band satellite sensors, requiring data fusion, multi-channel video frame prediction, and super-resolution. Accurate predictions of rain events are becoming ever more critical, with climate change increasing the frequency of unexpected rainfall. The resulting models will have a particular impact where costly weather radar is not available. We here present highlights and insights emerging from the thirty teams participating from over a dozen countries. To extract relevant patterns, models were challenged by spatio-temporal shifts. Geometric data augmentation and test-time ensemble models with a suitable smoother loss helped this transfer learning. Even though, in ablation, static information like geographical location and elevation was not linked to performance, the general success of models incorporating physics in this competition suggests that approaches combining machine learning with application domain knowledge seem a promising avenue for future research. Weather4cast will continue to explore the powerful benchmark reference data set introduced here, advancing competition tasks to quantitative predictions, and exploring the effects of metric choice on model performance and qualitative prediction properties.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the NeurIPS 2022 Competitions Track

ISBN

—

ISSN

2640-3498

e-ISSN

2640-3498

Počet stran výsledku

21

Strana od-do

292-312

Název nakladatele

Proceedings of Machine Learning Research

Místo vydání

—

Místo konání akce

New Orleans

Datum konání akce

28. 11. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—