The main aim of the field of Atmospheric and Oceanic Sciences (AOS) is to describe, understand, represent and simulate the processes of the atmosphere and oceans, and ultimately to forecast related phenomena. Traditional physics-based approaches have achieved great successes, reaching a stage where weather and climate can be forecast in advance to some extent. However, considerable uncertainties and model biases in weather and climate predictions still exist. Recent advances in machine learning have led to its emergence as a powerful approach in solving problems in AOS, particularly by providing new opportunities with a data-driven approach to explore atmospheric and oceanic phenomena and processes. Indeed, machine learning techniques have already been widely applied to AOS, and have shown great potential for improving weather forecasts and climate predictions. As such, there is growing interest in integrating new machine learning techniques and traditional physics-based approaches for advancing AOS.

Within this context, we [Atmospheric and Oceanic Science Letters (AOSL)] invite submissions focusing on machine learning techniques and/or their hybrid combinations with traditional approaches in improving weather forecasts and climate predictions across various spatiotemporal scales, and in understanding and reducing their uncertainties and model biases. This special issue will provide an opportunity for scientists to disseminate their recent research progress in the field of machine learning for AOS. We welcome papers related, but not limited to, the following topics:

1) Data-driven machine learning algorithms for AOS;

2) Physics-informed machine learning for parameterizations;

3) Machine learning–based weather forecasts and climate predictions;

4) Data-driven and physics-inferred fusion and hybrid approaches;

5) Machine learning applications for atmospheric and oceanic signal processing.

Submission Deadline:  2022/10/31

Submission Instructions:

The submission website for this journal is https://mc03.manuscriptcentral.com/aosl.

On the submission page, please select Manu Type as “Special Issue: Machine Learning for Atmospheric and Oceanic Sciences” from the menu.

Author guidelines and manuscript preparation instructions for AOSL can be found at http://aosl.iapjournals.ac.cn/EN/column/column317.shtml.

Special Issue Editors

Lead Editor:

Prof. Rong-Hua Zhang

School of Marine Sciences, Nanjing University of Information Science & Technology

Email: rzhang@qdio.ac.cn; 003556@nuist.edu.cn

Guest Editors:

Prof. Jing-Jia Luo

Institute for Climate and Application Research (ICAR), Nanjing University of Information Science & Technology

Email: jjluo@nuist.edu.cn

Prof. Qingshan Liu

School of Computer Science, Nanjing University of Information Science & Technology

Email: qsliu@nuist.edu.cn

Contact:

Editorial Office of Atmospheric and Oceanic Science Letters

Institute of Atmospheric Physics, Chinese Academy of Sciences

Email: aosl@mail.iap.ac.cn

http://aosl.iapjournals.ac.cn/;
https://www.sciencedirect.com/journal/Atmospheric-and-Oceanic-Science-Letters

About AOSL

Atmospheric and Oceanic Science Letters (AOSL) is an international peer-reviewed journal for the publication of original letters related to all aspects of the atmospheric sciences and physical oceanography. The journal provides a rigorous peer-review process, rapid publication speeds, and maintains high standards in the quality of accepted manuscripts. The journal includes Original Article, Review (invited), Perspective, Report, Data Description, and Progress and Views. AOSL is published Open Access by Elsevier on behalf of KeAi, and indexed by ESCI, Scopus, GEOBASE, DOAJ, CSCD, etc.