Deep learning for twelve hour precipitation forecasts

Espeholt, Lasse; Agrawal, Shreya; Sønderby, Casper Kaae; Kumar, Manoj; Jonathan, Heek,; Bromberg, Carla; Gazen, Cenk; Carver, Rob; Andrychowicz, Marcin; Hickey, Jason; Bell, Aaron; Kalchbrenner, Nal

doi:10.1038/s41467-022-32483-x

Cited by 69 publications

(19 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the non-recurrent nature of the architecture and the lead times considered, it is crucial to achieve a fully receptive field if we want to capture long-range dependencies and teleconnections (Espeholt et al 2022). A fully receptive field is realized through two design characteristics of the proposed architecture, which is sketched in Figure 2.…”

Section: A Receptive Fieldmentioning

confidence: 99%

Global Extreme Heat Forecasting Using Neural Weather Models

Lopez‐Gomez

McGovern

Agrawal

et al. 2023

Artificial Intelligence for the Earth Systems

View full text Add to dashboard Cite

Heat waves are projected to increase in frequency and severity with global warming. Improved warning systems would help reduce the associated loss of lives, wildfires, power disruptions, and reduction in crop yields. In this work, we explore the potential for deep learning systems trained on historical data to forecast extreme heat on short, medium and subseasonal timescales. To this purpose, we train a set of neural weather models (NWMs) with convolutional architectures to forecast surface temperature anomalies globally, 1 to 28 days ahead, at ~ 200 km resolution and on the cubed sphere. The NWMs are trained using the ERA5 reanalysis product and a set of candidate loss functions, including the mean squared error and exponential losses targeting extremes. We find that training models to minimize custom losses tailored to emphasize extremes leads to significant skill improvements in the heat wave prediction task, compared to NWMs trained on the mean squared error loss. This improvement is accomplished with almost no skill reduction in the general temperature prediction task, and it can be efficiently realized through transfer learning, by re-training NWMs with the custom losses for a few epochs. In addition, we find that the use of a symmetric exponential loss reduces the smoothing of NWM forecasts with lead time. Our best NWM is able to outperform persistence in a regressive sense for all lead times and temperature anomaly thresholds considered, and shows positive regressive skill compared to the ECMWF subseasonal-to-seasonal control forecast after two weeks.

show abstract

Section: A Receptive Fieldmentioning

confidence: 99%

Global Extreme Heat Forecasting Using Neural Weather Models

Lopez‐Gomez

McGovern

Agrawal

et al. 2023

Artificial Intelligence for the Earth Systems

View full text Add to dashboard Cite

show abstract

“…C. ML for dynamical systems assisted by DA Except for ML surrogate models that learn directly from the state variables (see Section II-D2 and IV-B), there are several examples of data-driven models derived from observations that show forecasting abilities [239], [240]. Those models can take various forms (e.g.…”

Section: B ML and Da With Rommentioning

confidence: 99%

Machine learning with data assimilation and uncertainty quantification for dynamical systems: a review

Cheng¹,

Quilodran-Casas²,

Ouala³

et al. 2023

Preprint

View full text Add to dashboard Cite

Data Assimilation (DA) and Uncertainty quantification (UQ) are extensively used in analysing and reducing error propagation in high-dimensional spatial-temporal dynamics. Typical applications span from computational fluid dynamics (CFD) to geoscience and climate systems. Recently, much effort has been given in combining DA, UQ and machine learning (ML) techniques. These research efforts seek to address some critical challenges in high-dimensional dynamical systems, including but not limited to dynamical system identification, reduced order surrogate modelling, error covariance specification and model error correction. A large number of developed techniques and methodologies exhibit a broad applicability across numerous domains, resulting in the necessity for a comprehensive guide. This paper provides the first overview of the state-of-the-art researches in this interdisciplinary field, covering a wide range of applications. This review aims at ML scientists who attempt to apply DA and UQ techniques to improve the accuracy and the interpretability of their models, but also at DA and UQ experts who intend to integrate cutting-edge ML approaches to their systems. Therefore, this article has a special focus on how ML methods can overcome the existing limits of DA and UQ, and vice versa. Some exciting perspectives of this rapidly developing research field are also discussed.

show abstract

“…Environmental science examples: Attention-based methods have already found application for precipitation mapping (Sønderby et al, 2020;Espeholt et al, 2022), estimating visibility due to coastal fog (Kamangir et al, 2021), generating super-resolution imagery (Liu et al, 2018), wildfire estimation (Monaco et al, 2021), population density estimation (Savner and Kanhangad, 2023), damage assessment (Hao et al, 2021), and land cover estimation (Ghosh et al, 2021;Wang and Sertel, 2021). Many additional examples are provided in the following section.…”

Section: A New Generation Of Neural Networkmentioning

confidence: 99%

Leveraging spatiotemporal information in meteorological image sequences: From feature engineering to neural networks

Bansal

Lee

Hilburn

et al. 2023

Environ. Data Science

View full text Add to dashboard Cite

Atmospheric processes involve both space and time. Thus, humans looking at atmospheric imagery can often spot important signals in an animated loop of an image sequence not apparent in an individual (static) image. Utilizing such signals with automated algorithms requires the ability to identify complex spatiotemporal patterns in image sequences. That is a very challenging task due to the endless possibilities of patterns in both space and time. Here, we review different concepts and techniques that are useful to extract spatiotemporal signals from meteorological image sequences to expand the effectiveness of AI algorithms for classification and prediction tasks. We first present two applications that motivate the need for these approaches in meteorology, namely the detection of convection from satellite imagery and solar forecasting. Then we provide an overview of concepts and techniques that are helpful for the interpretation of meteorological image sequences, such as (a) feature engineering methods using (i) meteorological knowledge, (ii) classic image processing, (iii) harmonic analysis, and (iv) topological data analysis; (b) ways to use convolutional neural networks for this purpose with emphasis on discussing different convolution filters (2D/3D/LSTM-convolution); and (c) a brief survey of several other concepts, including the concept of “attention” in neural networks and its utility for the interpretation of image sequences and strategies from self-supervised and transfer learning to reduce the need for large labeled datasets. We hope that presenting an overview of these tools—many of which are not new but underutilized in this context—will accelerate progress in this area.

show abstract

Deep learning for twelve hour precipitation forecasts

Cited by 69 publications

References 9 publications

Global Extreme Heat Forecasting Using Neural Weather Models

Global Extreme Heat Forecasting Using Neural Weather Models

Machine learning with data assimilation and uncertainty quantification for dynamical systems: a review

Leveraging spatiotemporal information in meteorological image sequences: From feature engineering to neural networks

Contact Info

Product

Resources

About