Short‐Term Precipitation Prediction for Contiguous United States Using Deep Learning

Chen, Guoxing; Wang, Wei‐Chyung

doi:10.1029/2022gl097904

Cited by 32 publications

(20 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to Bi et al (2022), one year ( 2003) is used for validation, three years (2008, 2013, and 2018) for testing, and the rest for training. However, unlike Bi et al (2022), this study uses a discontinuous selection strategy, which can avoid different climate change signals due to different periods of the training and testing datasets (Chen & Wang, 2022;. The proposed GAN-UNet framework is composed of four main components (Steps 1-4), as illustrated in Figure 1.…”

Section: The Proposed Model Architectures and Related Parametersmentioning

confidence: 99%

East Asia Atmospheric River Forecast With a Deep Learning Method: GAN‐UNet

Tian,

Zhao,

et al. 2024

JGR Atmospheres

View full text Add to dashboard Cite

Accurate forecasting of atmospheric rivers (ARs) holds significance in preventing losses from extreme precipitation. However, traditional numerical weather prediction (NWP) models are computationally expensive and can be limited in accuracy due to inaccurate physical parameter settings. To overcome these limitations, we propose a deep learning (DL) model, called GAN‐UNet, to forecast the AR occurrence, position, and intensity in East Asia. GAN‐UNet can capture the complex nonlinear relationship between the inputs at the past moment, including the vertically integrated water vapor transport (IVT), zonal wind at 850 hPa (U850), and meridional wind at 850 hPa (V850), and the forecast output (IVT, U850, or V850), whose results are comparable to NWP models. In addition, the average model (AM) by integrating the results generated by GAN‐UNet and European Centre for Medium‐Range Weather Forecasts (ECMWF) outperforms all the NWP models selected in this study, demonstrating its potential to improve the performance of NWP through the DL method. Specifically, the 5‐day average F1 scores of the AM are 0.777 and 0.845, whose values are significantly better than those obtained by ECMWF (0.712 and 0.794) in the two key regions of East Asia; The AM 5‐day average intersection over unions are 0.706 and 0.688 while the values of ECMWF are 0.675 and 0.64; in terms of intensity forecast, GAN‐UNet and AM exhibited lower differences in most of the intensity bins, except for the final bin with IVT more than 825 kg m−1 s−1. With this thorough analysis, GAN‐UNet is shown as an effective model to forecast ARs.

show abstract

Section: The Proposed Model Architectures and Related Parametersmentioning

confidence: 99%

East Asia Atmospheric River Forecast With a Deep Learning Method: GAN‐UNet

Tian,

Zhao,

et al. 2024

JGR Atmospheres

View full text Add to dashboard Cite

show abstract

“…This selection strategy is based on the following considerations. First, it can avoid different climate change signals due to different periods of the training and testing data sets (Chen & Wang, 2022; Ravuri et al., 2021). Second, if all the 459 samples are completely shuffled and randomly selected, it is difficult to show the specific date chosen, which may result in readers who want to reproduce our work not being able to achieve exactly the same results.…”

Section: Data Sets and Ar‐related Definitionsmentioning

confidence: 99%

A Deep‐Learning Ensemble Method to Detect Atmospheric Rivers and Its Application to Projected Changes in Precipitation Regime

et al. 2023

View full text Add to dashboard Cite

This study aims to detect atmospheric rivers (ARs) around the world by developing a deep‐learning ensemble method using AR catalogs of the ClimateNet data set. The ensemble method, based on 20 semantic segmentation algorithms, notably reduces the bias of the testing data set, with its intersection over union score being 1.7%–10.1% higher than that of individual algorithms. This method is then applied to the Coupled Model Intercomparison Project Phase 6 (CMIP6) datasets to quantify AR frequency and its related precipitation in the historical period (1985–2014) and future period (2070–2099) under the Shared Socioeconomic Pathways 5–8.5 warming scenario. The six key regions, which are distributed in different continents of the globe and greatly influenced by ARs, are particularly highlighted. The results show that CMIP6 multi‐model mean with the deep‐learning ensemble method reasonably reproduces the observed AR frequency. In most key regions, both heavy precipitation (90–99 percentile) and extremely heavy precipitation (>99 percentile) are projected to increase in a warming climate mainly due to the increased AR‐related precipitation. The AR contributions to future heavy and extremely heavy precipitation increase range from 145.1% to 280.5% and from 36.2% to 213.5%, respectively, indicating that ARs should be taken into account to better understand the future extreme precipitation changes.

show abstract

“…Machine learning is used to predict different weather phenomena, such as hurricane trajectory and intensity (Boussioux et al, 2020), using novel multimodal combined gradientboosted trees, encoders, convolutional neural networks (CNN), and transformer components. In addition, machine learning is used in air-quality forecasts (Lin et al, 2018), short term precipitation prediction (Chen and Wang, 2021), and for improving precipitation prediction in numerical weather prediction (NWP) systems (Singh et al, 2021).…”

Section: Accepted Manuscriptmentioning

confidence: 99%

Machine Learning Applications to Dust Storms: A Meta-Analysis

Alshammari

Alrwais

Aksoy

2022

Aerosol Air Qual. Res.

View full text Add to dashboard Cite

Dust storms are natural hazards that affect both people and properties. Therefore, it is important to mitigate their risks by implementing an early notification system. Different methods are used to predict dust storms, such as observing satellite images, analyzing meteorological data, and using numerical weather prediction model forecasts. However, recent studies have shown that machine learning algorithms have higher capacities to predict dust storms in less time and with fewer processing operations compared to numerical weather models. This paper conducted a meta-analysis review to examine studies that addressed the areas associated with the application of machine learning to dust storm prediction. It aims to compare the applied models and the types of data used in the literature under study. Given that the location of a dust storm event is essential, the properties of dust storms are discussed in relation to the region. The output classes and the various performance metrics observed in each reviewed paper are also summarized. Subsequently, the present paper offers a detailed analysis highlighting the capabilities of machine learning models in predicting dust storms. The analysis shows two main categories: early detection and dust storm prediction. Most models used for dust storm early detection from satellite images are support vector machines (SVM). In contrast, the most used models for dust storm prediction are SVM and random forests that predict the occurrence of dust storms from meteorological data. Finally, the paper highlights the challenges and future trends in the field, illustrating the potential directions for applying deep learning algorithms and providing longrange predictions with assessments of dust storm duration and intensity.

show abstract

Short‐Term Precipitation Prediction for Contiguous United States Using Deep Learning

Cited by 32 publications

References 45 publications

East Asia Atmospheric River Forecast With a Deep Learning Method: GAN‐UNet

East Asia Atmospheric River Forecast With a Deep Learning Method: GAN‐UNet

A Deep‐Learning Ensemble Method to Detect Atmospheric Rivers and Its Application to Projected Changes in Precipitation Regime

Machine Learning Applications to Dust Storms: A Meta-Analysis

Contact Info

Product

Resources

About