Deep learning for multi-year ENSO forecasts

Ham, Yoo‐Geun; Kim, Jeong‐Hwan; Luo, Jing–Jia

doi:10.1038/s41586-019-1559-7

Cited by 696 publications

(579 citation statements)

References 35 publications

Supporting

Mentioning

550

Contrasting

Unclassified

Order By: Relevance

“…The proposed models could achieve high ACC skills for long lead times. These ACC skills are comparable to the ACC skills reported for the CNN in Ham et al (). For this, compare Figure 2a in Ham et al () and Figure S9.…”

Section: Resultssupporting

confidence: 85%

See 1 more Smart Citation

Probabilistic Forecasting of El Niño Using Neural Network Models

Petersik

Dijkstra

2020

Geophysical Research Letters

View full text Add to dashboard Cite

We apply Gaussian density neural network and quantile regression neural network ensembles to predict the El Niño–Southern Oscillation. Both models are able to assess the predictive uncertainty of the forecast by predicting a Gaussian distribution and the quantiles of the forecasts, respectively. This direct estimation of the predictive uncertainty for each given forecast is a novel feature in the prediction of the El Niño–Southern Oscillation by statistical models. The predicted mean and median, respectively, show a high‐correlation skill for long lead times (r=0.5, 12 months) for the 1963–2017 evaluation period. For the 1982–2017 evaluation period, the probabilistic forecasts by the Gaussian density neural network can better estimate the predictive uncertainty than a standard method to assess the predictive uncertainty of statistical models.

show abstract

Section: Resultssupporting

confidence: 85%

“…These ACC skills are comparable to the ACC skills reported for the CNN in Ham et al (). For this, compare Figure 2a in Ham et al () and Figure S9. The ACC of Ham et al falls below 0.5 for the 17‐month lead time with respect to an evaluation period between 1984 and 2017.…”

Section: Resultssupporting

confidence: 85%

Probabilistic Forecasting of El Niño Using Neural Network Models

Petersik

Dijkstra

2020

Geophysical Research Letters

View full text Add to dashboard Cite

show abstract

“…The proposed dataset -ClimateNet -and end-to-end infrastructure provides several unique capabilities: (i) it enables us to perform fine-grained highly precise data analytics, such as examining changes in frequency and intensity of weather patterns at specific geographic locations across the globe; (ii) it can be applied to different climate scenarios and different datasets without tuning since it does not rely on threshold conditions unlike heuristic algorithms currently used in the community; (iii) the method is suitable for rapidly analyzing large amounts of climate model output. Further, the method can likely be used directly with reanalyses products or observational data using transfer learning, as shown successfully for a similar DL-based method by Ham et al (2019). While we do not explicitly test the transferability of this model to observations and reanalyses products, we intend to pursue this in future work.…”

Section: Atmospheric River Precipitation In Californiamentioning

confidence: 99%

“…2017). To highlight one success, Ham et al (2019) demonstrated the skill of DL on forecasting El Niño states and found DL to forecast with superior leadtimes than state-of-theart dynamical models. Many of the ML and DL techniques used, again rely on the availability and quality of labeled data.…”

Section: Introductionmentioning

confidence: 99%

ClimateNet: an expert-labelled open dataset and Deep Learning architecture for enabling high-precision analyses of extreme weather

Kashinath¹,

Mudigonda²,

Kim³

et al. 2020

Preprint

View full text Add to dashboard Cite

Abstract. Identifying, detecting and localizing extreme weather events is a crucial first step in understanding how they may vary under different climate change scenarios. Pattern recognition tasks such as classification, object detection and segmentation have remained challenging problems in the weather and climate sciences. While there exist many empirical heuristics for detecting extreme events, the disparities between the output of these different methods even for a single event are large and often difficult to reconcile. Given the success of Deep Learning (DL) in tackling similar problems in computer vision, we advocate a DL-based approach. DL, however, works best in the context of supervised learning; when labeled datasets are readily available. Reliable, labeled training data for extreme weather and climate events is scarce. We create ClimateNet – an open, community-sourced human expert-labeled curated dataset – that captures tropical cyclones (TCs) and atmospheric rivers (ARs) in high-resolution climate model output from a simulation of a recent historical period. We use the curated ClimateNet dataset to train a state-of-the-art DL model for pixel-level identification, i.e. segmentation, of TCs and ARs. We then apply the trained DL model to historical and climate change scenarios simulated by the Community Atmospheric Model (CAM5.1) and show that the DL model accurately segments the data into TCs, ARs or the background at a pixel level. Further, we show how the segmentation results can be used to conduct spatially and temporally precise analytics by quantifying distributions of extreme precipitation conditioned on event types (TC or AR) at regional scales. The key contribution of this work is that it paves the way for DL-based automated, hi-fidelity and highly precise analytics of climate data using a curated expert-labelled dataset – ClimateNet. ClimateNet and the DL-based segmentation method provide several unique capabilities: (i) they can be used to calculate a variety of TC and AR statistics at a fine-grained level; (ii) they can be applied to different climate scenarios and different datasets without tuning as they do not rely on threshold conditions; and (iii) the proposed DL method is suitable for rapidly analyzing large amounts of climate model output. While our study has been conducted for two important extreme weather patterns (TCs and ARs) in simulation datasets, we believe that this methodology can be applied to a much broader class of patterns, and applied to observational and reanalysis data products via transfer learning.

show abstract

“…In recent years, owing to the rapid development of deep learning techniques, we have witnessed a lot of groundbreaking results [27][28][29]. As the most common used network in deep learning, the convolutional neural network (CNN) has been widely applied to computer vision tasks and gains remarkable popularity.…”

Section: Introductionmentioning

confidence: 99%

UVI Image Segmentation of Auroral Oval: Dual Level Set and Convolutional Neural Network Based Approach

Tian

Yang

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

The auroral ovals around the Earth’s magnetic poles are produced by the collisions between energetic particles precipitating from solar wind and atoms or molecules in the upper atmosphere. The morphology of auroral oval acts as an important mirror reflecting the solar wind-magnetosphere-ionosphere coupling process and its intrinsic mechanism. However, the classical level set based segmentation methods often fail to extract an accurate auroral oval from the ultraviolet imager (UVI) image with intensity inhomogeneity. The existing methods designed specifically for auroral oval extraction are extremely sensitive to the contour initializations. In this paper, a novel deep feature-based adaptive level set model (DFALS) is proposed to tackle these issues. First, we extract the deep feature from the UVI image with the newly designed convolutional neural network (CNN). Second, with the deep feature, the global energy term and the adaptive time-step are constructed and incorporated into the local information based dual level set auroral oval segmentation method (LIDLSM). Third, we extract the contour of the auroral oval through the minimization of the proposed energy functional. The experiments on the UVI image data set validate the strong robustness of DFALS to different contour initializations. In addition, with the help of deep feature-based global energy term, the proposed method also obtains higher segmentation accuracy in comparison with the state-of-the-art level set based methods.

show abstract

Deep learning for multi-year ENSO forecasts

Cited by 696 publications

References 35 publications

Probabilistic Forecasting of El Niño Using Neural Network Models

Probabilistic Forecasting of El Niño Using Neural Network Models

ClimateNet: an expert-labelled open dataset and Deep Learning architecture for enabling high-precision analyses of extreme weather

UVI Image Segmentation of Auroral Oval: Dual Level Set and Convolutional Neural Network Based Approach

Contact Info

Product

Resources

About