Can deep learning beat numerical weather prediction?

Schultz, Martin; Betancourt, Clara; Gong, Bing; Kleinert, Felix; Langguth, Michael; Leufen, Lukas Hubert; Mozaffari, Amirpasha; Stadtler, Scarlet

doi:10.1098/rsta.2020.0097

Cited by 262 publications

(177 citation statements)

References 120 publications

Supporting

Mentioning

174

Contrasting

Unclassified

Order By: Relevance

“…However, there were some difficulties in applying the proposed weather forecasting model. As reported in the literature [18], neural networks can be susceptible to learning false relationships between data. A pure data-based weather forecasting model may fail to respect basic physical principles and, thus, generate false forecasts because it does not take into consideration that every atmospheric process is affected by physical laws.…”

Section: Discussionmentioning

confidence: 99%

“…To objectively assess the performance of the implemented predictive model, we used two measures of the error committed by the network, such as the MAE, MSE, and R 2 , applied in the evaluation of the prediction accuracy of regressive models. To answer the question of why some weather variables were predicted better and others worse, we examined the relationships between the variables included in the model, since ML models are data-driven, and consequently the prediction accuracy naturally depends on the strength of these correlations [18].…”

Section: Methods To Evaluate the Effectiveness Of Regressive ML Models And To Measure The Correlations Between Variablesmentioning

confidence: 99%

“…Meteorologists use different methods to forecast the weather. Lewis Fry Richardson proposed the possibility of creating the first numerical weather prediction models in 1922 [18]. The practical use of numerical models began in 1955 due to the development of programmable electronic computers [19].…”

Section: The Essence Significance and Complexity Of Weather Forecastingmentioning

confidence: 99%

See 2 more Smart Citations

An ANN Model Trained on Regional Data in the Prediction of Particular Weather Conditions

et al. 2021

View full text Add to dashboard Cite

Artificial Neural Networks (ANNs) have proven to be a powerful tool for solving a wide variety of real-life problems. The possibility of using them for forecasting phenomena occurring in nature, especially weather indicators, has been widely discussed. However, the various areas of the world differ in terms of their difficulty and ability in preparing accurate weather forecasts. Poland lies in a zone with a moderate transition climate, which is characterized by seasonality and the inflow of many types of air masses from different directions, which, combined with the compound terrain, causes climate variability and makes it difficult to accurately predict the weather. For this reason, it is necessary to adapt the model to the prediction of weather conditions and verify its effectiveness on real data. The principal aim of this study is to present the use of a regressive model based on a unidirectional multilayer neural network, also called a Multilayer Perceptron (MLP), to predict selected weather indicators for the city of Szczecin in Poland. The forecast of the model we implemented was effective in determining the daily parameters at 96% compliance with the actual measurements for the prediction of the minimum and maximum temperature for the next day and 83.27% for the prediction of atmospheric pressure.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methods To Evaluate the Effectiveness Of Regressive ML Models And To Measure The Correlations Between Variablesmentioning

confidence: 99%

Section: The Essence Significance and Complexity Of Weather Forecastingmentioning

confidence: 99%

See 1 more Smart Citation

An ANN Model Trained on Regional Data in the Prediction of Particular Weather Conditions

et al. 2021

View full text Add to dashboard Cite

show abstract

“…A typical example is summertime rural areas downwind of larger city centers, where peak ozone values can often be observed (Xu et al, 2011). In the close vicinity of power plants or in city centers, NO x is often very high and low ozone levels are observed (Sillman, 1999).…”

Section: Interconnected Factorsmentioning

confidence: 99%

AQ-Bench: a benchmark dataset for machine learning on global air quality metrics

Betancourt¹,

Stomberg

Roscher

et al. 2021

Earth Syst. Sci. Data

Self Cite

View full text Add to dashboard Cite

Abstract. With the AQ-Bench dataset, we contribute to the recent developments towards shared data usage and machine learning methods in the field of environmental science. The dataset presented here enables researchers to relate global air quality metrics to easy-access metadata and to explore different machine learning methods for obtaining estimates of air quality based on this metadata. AQ-Bench contains a unique collection of aggregated air quality data from the years 2010–2014 and metadata at more than 5500 air quality monitoring stations all over the world, provided by the first Tropospheric Ozone Assessment Report (TOAR). It focuses in particular on metrics of tropospheric ozone, which has a detrimental effect on climate, human morbidity and mortality, as well as crop yields. The purpose of this dataset is to produce estimates of various long-term ozone metrics based on time-independent local site conditions. We combine this task with a suitable evaluation metric. Baseline scores obtained from a linear regression method, a fully connected neural network and random forest are provided for reference and validation. AQ-Bench offers a low-threshold entrance for all machine learners with an interest in environmental science and for atmospheric scientists who are interested in applying machine learning techniques. It enables them to start with a real-world problem relevant to humans and nature. The dataset and introductory machine learning code are available at https://doi.org/10.23728/b2share.30d42b5a87344e82855a486bf2123e9f (Betancourt et al., 2020) and https://gitlab.version.fz-juelich.de/esde/machine-learning/aq-bench (Betancourt et al., 2021). AQ-Bench thus provides a blueprint for environmental benchmark datasets as well as an example for data re-use according to the FAIR principles.

show abstract

“…The data-based approach has been recently applied to several aspects of weather forecasting [5]. Hurricane forecasting using data-based approaches have mainly been formulated as image processing problems in [6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

Forecasting the Evolution of North Atlantic Hurricanes: A Deep Learning Approach

Bose¹,

Pintar²,

Simiu³

2021

View full text Add to dashboard Cite

Accurate prediction of storm evolution from genesis onwards may be of great importance considering that billions of dollars worth of property damage and numerous casualties are inflicted each year all over the globe. In the present work, two classes of Recurrent Neural Network (RNN) models for predicting storm-eye trajectory have been developed. These models are trained on input features available in or derived from the North Atlantic hurricane database maintained by the National Hurricane Center (NHC). The models utilize historical data to estimate probabilities of storms passing through any location. Furthermore, inputs to the models are such so that the model development methodology is applicable to any oceanic basin in any part of the globe. Model forecasting errors have been analyzed in detail. The error analysis shows that the Many-To-Many class of models are appropriate for long-term forecasting while Many-To-One prediction models perform comparably well for 6 − hr predictions. Application of these models to predicting more than 40 test storms in the North Atlantic basin shows that, at least for forecasts of up to 12 hours, they outperform all data-based storm trajectory prediction models cited in the paper. Apart from providing very fast predictions, the RNN models require less information than models used in current practice. Because the models presented herein emulate the trajectory trends of historical storms, they are currently being used for the simulation of synthetic storm tracks and features and the subsequent estimation of extreme wind speeds with various mean recurrence intervals.

show abstract

Can deep learning beat numerical weather prediction?

Cited by 262 publications

References 120 publications

An ANN Model Trained on Regional Data in the Prediction of Particular Weather Conditions

An ANN Model Trained on Regional Data in the Prediction of Particular Weather Conditions

AQ-Bench: a benchmark dataset for machine learning on global air quality metrics

Forecasting the Evolution of North Atlantic Hurricanes: A Deep Learning Approach

Contact Info

Product

Resources

About