Published on Wed Mar 17 2021

Deep Learning based Extreme Heatwave Forecast

Valérian Jacques-Dumas, Francesco Ragone, Freddy Bouchet, Pierre Borgnat, Patrice Abry
0
0
0
Abstract

Forecasting the occurrence of heatwaves constitutes a challenging issue, yet of major societal stake, because extreme events are not often observed and (very) costly to simulate from physics-driven numerical models. The present work aims to explore the use of Deep Learning architectures as alternative strategies to predict extreme heatwaves occurrences from a very limited amount of available relevant climate data. This implies addressing issues such as the aggregation of climate data of different natures, the class-size imbalance that is intrinsically associated with rare event prediction, and the potential benefits of transfer learning to address the nested nature of extreme events (naturally included in less extreme ones). Using 1000 years of state-of-the-art PlaSim Planete Simulator Climate Model data, it is shown that Convolutional Neural Network-based Deep Learning frameworks, with large-class undersampling and transfer learning achieve significant performance in forecasting the occurrence of extreme heatwaves, at three different levels of intensity, and as early as 15 days in advance from the restricted observation, for a single time (single snapshoot) of only two spatial fields of climate data, surface temperature and geopotential height.

Wed May 04 2016
Computer Vision
Application of Deep Convolutional Neural Networks for Detecting Extreme Weather in Climate Datasets
Deep neural networks are able to learn high-level representations of a broad class of patterns from labeled data. Coupled with Bayesian based hyper-parameter optimization scheme, our deep CNN system achieves 89\%-99\% of accuracy in detecting extreme events.
0
0
0
Sun Jun 14 2020
Machine Learning
Sub-Seasonal Climate Forecasting via Machine Learning: Challenges, Analysis, and Advances
Sub-seasonal climate forecasting (SSF) focuses on predicting key climate variables such as temperature and precipitation in the 2-week to 2-month time spans. Skillful SSF would have immense societal value, in areas such as agricultural productivity, water resource management, transportation and emergency
0
0
0
Fri Jul 26 2019
Machine Learning
Analog forecasting of extreme-causing weather patterns using deep learning
Capsule neural networks, CapsNets, are trained on mid-tropospheric large-scale circulation patterns (Z500) labeled depending on the existence and geographical region of surface temperature extremes. The trained networks predict the occurrence/region of cold or heat
0
0
0
Fri Aug 16 2019
Machine Learning
Recurrent U-net: Deep learning to predict daily summertime ozone in the United States
The model captures well daily, seasonal and interannual variability in MDA8 ozone across the US. We used the model to evaluate recent trends in NO emissions in the US and found that the trend in the EPA emissions inventory produced the largest negative bias in predicted ozone. In both rural and urban regions the EPA trend resulted in the largest negative bias.
0
0
0
Tue Oct 01 2019
Computer Vision
A Three-dimensional Convolutional-Recurrent Network for Convective Storm Nowcasting
Very short-term convective storm forecasting, termed nowcasting, has long been an important issue. Existing methods rely principally on radar images and are limited in terms of storm initiation and growth. Real-time re-analysis of meteorological data supplied by numerical models provides valuable information.
0
0
0
Tue Feb 09 2021
Machine Learning
Sub-seasonal forecasting with a large ensemble of deep-learning weather prediction models
We present an ensemble prediction system using a Deep Learning WeatherPrediction (DLWP) model. This model uses convolutional neural networks on a cubed sphere grid to produce global forecasts. The approach is computationally efficient, requiring just three minutes on a single GPU to produce a 320-member set of six-week forecasts at 1.4°C.
0
0
0