Submit to Atmosphere Review for Atmosphere Propose a Special Issue

Journal Menu

Journal Browser

Artificial Intelligence in Atmospheric Modelling, Prediction, and Data Assimilation

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Atmosphere (ISSN 2073-4433). This special issue belongs to the section "Atmospheric Techniques, Instruments, and Modeling".

Deadline for manuscript submissions: closed (15 October 2021) | Viewed by 33944

Share This Special Issue

Special Issue Editors

Dr. Amin Talei

E-Mail Website
Guest Editor

Discipline of Civil Engineering, School of Engineering, Monash University Malaysia, Jalan Lagoon Selatan, Bandar Sunway 47500, Selangor, Malaysia
Interests: sustainable urban water management; nature-based solutions for stormwater management; biofiltration systems; flood modeling and management
Special Issues, Collections and Topics in MDPI journals

Dr. Miodrag Rancic

E-Mail Website
Guest Editor

IMSG at NOAA/NWS/NCEP Environmental Modeling Center, College Park, MD 20740, USA
Interests: numerical methods; modeling; data assimilation; machine learning/artificial intelligence
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

To date, several computer-aided techniques have been developed for modeling, prediction, and data assimilation of atmospheric systems. These methods range from numerical models developed based on physical laws of the problem to statistical methods and data-driven techniques which are generally focused on associations between inputs and outputs. These techniques can help researchers in solving problems in atmospheric systems such as dynamic systems prediction, ensemble weather forecasting, climate data downscaling, etc. In the past two decades, through improvements in computing power, artificial intelligence techniques have attracted a lot of attention due to their automatic repetitive learning and recognition through data, unique capability in capturing complex associations between variables, and their power in analyzing big data.

This Special Issue aims to present some of the latest achievements in using AI techniques, including artificial neural networks (ANN), neurofuzzy systems (NFS), support vector machines (SVM), fuzzy reasoning, evolutionary computation techniques, etc. in atmospheric modeling, prediction, and data assimilation.

Dr. Amin Talei
Dr. Miodrag Rancic
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Atmosphere is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

Atmospheric modeling
Atmospheric prediction
Data assimilation
Artificial intelligence

Published Papers (4 papers)

Download All Papers

Research

16 pages, 1432 KiB

Open AccessArticle

Machine Learning in Weather Prediction and Climate Analyses—Applications and Perspectives

by Bogdan Bochenek and Zbigniew Ustrnul

Atmosphere 2022, 13(2), 180; https://doi.org/10.3390/atmos13020180 - 23 Jan 2022

Cited by 66 | Viewed by 24482

Abstract

In this paper, we performed an analysis of the 500 most relevant scientific articles published since 2018, concerning machine learning methods in the field of climate and numerical weather prediction using the Google Scholar search engine. The most common topics of interest in the abstracts were identified, and some of them examined in detail: in numerical weather prediction research—photovoltaic and wind energy, atmospheric physics and processes; in climate research—parametrizations, extreme events, and climate change. With the created database, it was also possible to extract the most commonly examined meteorological fields (wind, precipitation, temperature, pressure, and radiation), methods (Deep Learning, Random Forest, Artificial Neural Networks, Support Vector Machine, and XGBoost), and countries (China, USA, Australia, India, and Germany) in these topics. Performing critical reviews of the literature, authors are trying to predict the future research direction of these fields, with the main conclusion being that machine learning methods will be a key feature in future weather forecasting. Full article

(This article belongs to the Special Issue Artificial Intelligence in Atmospheric Modelling, Prediction, and Data Assimilation)

► Show Figures

Figure 1

20 pages, 6560 KiB

Open AccessEditor’s ChoiceArticle

A Novel Multi-Input Multi-Output Recurrent Neural Network Based on Multimodal Fusion and Spatiotemporal Prediction for 0–4 Hour Precipitation Nowcasting

by Fuhan Zhang, Xiaodong Wang and Jiping Guan

Atmosphere 2021, 12(12), 1596; https://doi.org/10.3390/atmos12121596 - 29 Nov 2021

Cited by 10 | Viewed by 2630

Abstract

Multi-source meteorological data can reflect the development process of single meteorological elements from different angles. Making full use of multi-source meteorological data is an effective method to improve the performance of weather nowcasting. For precipitation nowcasting, this paper proposes a novel multi-input multi-output recurrent neural network model based on multimodal fusion and spatiotemporal prediction, named MFSP-Net. It uses precipitation grid data, radar echo data, and reanalysis data as input data and simultaneously realizes 0–4 h precipitation amount nowcasting and precipitation intensity nowcasting. MFSP-Net can perform the spatiotemporal-scale fusion of the three sources of input data while retaining the spatiotemporal information flow of them. The multi-task learning strategy is used to train the network. We conduct experiments on the dataset of Southeast China, and the results show that MFSP-Net comprehensively improves the performance of the nowcasting of precipitation amounts. For precipitation intensity nowcasting, MFSP-Net has obvious advantages in heavy precipitation nowcasting and the middle and late stages of nowcasting. Full article

(This article belongs to the Special Issue Artificial Intelligence in Atmospheric Modelling, Prediction, and Data Assimilation)

► Show Figures

Figure 1

20 pages, 11443 KiB

Open AccessArticle

Model Sensitivity Evaluation for 3DVAR Data Assimilation Applied on WRF with a Nested Domain Configuration

by Mingchun Lam and Jimmy Chihung Fung

Atmosphere 2021, 12(6), 682; https://doi.org/10.3390/atmos12060682 - 26 May 2021

Cited by 2 | Viewed by 2393

Abstract

An initial condition that closely represents the true atmospheric state can minimize errors that propagate into the future, and could theoretically lead to improvements in the forecast. This study aims to evaluate and understand the impacts of 3DVAR on the state-of-the-art Weather Research and Forecasting (WRF) model with a two nested domains setup. The domain configuration of the model covers China with an emphasis on Guangdong province, with a resolution of 27 km, 9 km, and 3 km. Improvements in the forecasts for the Winter and Summer season of all the domains are systematically compared and are quantified in terms of 2 m temperature, 10 m wind speed, sea level pressure, and 2 m relative humidity. The results show that 3DVAR provides significant improvements in the winter case and surprisingly improvements were also found after the 48 h of the forecast. Evaluations of performance of 3DVAR in different domains and between two different seasons were done to further understand the reasons behind the discrepancies. Full article

(This article belongs to the Special Issue Artificial Intelligence in Atmospheric Modelling, Prediction, and Data Assimilation)

► Show Figures

Figure 1

27 pages, 1729 KiB

Open AccessArticle

Neural Network-Based Models for Estimating Weighted Mean Temperature in China and Adjacent Areas

by Fengyang Long, Wusheng Hu, Yanfeng Dong and Jinling Wang

Atmosphere 2021, 12(2), 169; https://doi.org/10.3390/atmos12020169 - 28 Jan 2021

Cited by 14 | Viewed by 2131

Abstract

The weighted mean temperature (

T_{m}

) is a key parameter when converting the zenith wet delay (ZWD) to precipitation water vapor (PWV) in ground-based Global Navigation Satellite System (GNSS) meteorology.

T_{m}

can be calculated via numerical integration with the atmospheric [...] Read more.

The weighted mean temperature (

T_{m}

) is a key parameter when converting the zenith wet delay (ZWD) to precipitation water vapor (PWV) in ground-based Global Navigation Satellite System (GNSS) meteorology.

T_{m}

can be calculated via numerical integration with the atmospheric profile data measured along the zenith direction, but this method is not practical in most cases because it is not easy for general users to get real-time atmospheric profile data. An alternative method to obtain an accurate

T_{m}

value is to establish regional or global models on the basis of its relations with surface meteorological elements as well as the spatiotemporal variation characteristics of

T_{m}

. In this study, the complex relations between

T_{m}

and some of its essentially associated factors including the geographic position and terrain, surface temperature and surface water vapor pressure were considered to develop

T_{m}

models, and then a non-meteorological-factor

T_{m}

model (NMFTm), a single-meteorological-factor

T_{m}

model (SMFTm) and a multi-meteorological-factor

T_{m}

model (MMFTm) applicable to China and adjacent areas were established by adopting the artificial neural network technique. The generalization performance of new models was strengthened with the help of an ensemble learning method, and the model accuracies were compared with several representative published

T_{m}

models from different perspectives. The results show that the new models all exhibit consistently better performance than the competing models under the same application conditions tested by the data within the study area. The NMFTm model is superior to the latest non-meteorological model and has the advantages of simplicity and utility. Both the SMFTm model and MMFTm model show higher accuracy than all the published

T_{m}

models listed in this study; in particular, the MMFTm model is about 14.5% superior to the first-generation neural network-based

T_{m}

(NN-I) model, with the best accuracy so far in terms of the root-mean-square error. Full article

(This article belongs to the Special Issue Artificial Intelligence in Atmospheric Modelling, Prediction, and Data Assimilation)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Artificial Intelligence in Atmospheric Modelling, Prediction, and Data Assimilation

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (4 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI