Environmental Modeling & Assessment - Call for Papers for a Special issue on Machine Learning in Environmental Modelling

In environmental modelling, the traditional physical process-based and statistical modelling-based approaches generally require significant input from practitioners with domain knowledge of the studied problem.  Frequently, this requirement constitutes an impediment to discovery. However, recent progress in computing and machine learning has been overwhelming and may potentially satisfy the detailed domain knowledge constraint. Nowadays, advanced machine learning algorithms can effectively approximate extremely complex systems with less prior knowledge. Especially, among deep learning approaches, convolutional neural networks and recurrent neural networks, demonstrated excellent performance for handling image data and time-series data.

Although advanced machine learning approaches are available for practice, researchers must formulate environmental problems in a mathematical language and localize machine learning approaches to make them work more effectively. This has been a challenge for practitioners in environmental modelling, and this growing focus on machine learning in environmental science in various applications has raised the need for a deep understanding of machine learning approaches for modelling environmental data.

Machine learning is rapidly gaining momentum as a new toolbox for analysing data. The literature of machine learning is abundant in many disciplines. However, ML applications in environmental science remain fragmented.  This special issue aims to publish novel approaches and applications in environmental modelling with machine learning. More specifically, this special issue focuses on formulating complex problems and developing machine learning approaches for different tasks (such as forecasting and optimization) in environmental science. Your work should excite other researchers in environmental modelling and assessment and excel them in machine learning approaches. Topic of interest include (but are not limited) to:

•    Temporal data modelling with machine learning in environmental science
•    Spatial data modelling with machine learning in environmental science
•    Anomaly detection with machine learning in environmental science
•    Clustering with machine learning in environmental science
•    Big data computing in environmental science
•    Climate Change (air or sea temperature, PM2.5, CO2 emission) and machine learning
 

Keywords:

Statistical learning, machine learning, deep learning, artificial intelligence-based method, big data, outliers, causality inference, data fusion, multi-view learning, forecasting, optimization.

Timeline:

Submission due date 31 March 2023

All submissions will be assessed in a manner commensurate with regular submissions to Environmental Modeling and Assessment. Since the topic is fast-evolving, special focus will be placed on rapid editorial decision for all submissions. Your early submission will prompt an early review process and hence our early decisions. Every effort will be made to finalize the peer review process prior to 30 August 2023 and to publish the issue before the end of 2023.

Guest editors:

Dr. You-Gan Wang

Institute for Learning Sciences & Teacher Education

Australian Catholic University, Brisbane, Australia

you-gan.wang@acu.edu.au (this opens in a new tab)

Dr. Jinran Wu

Institute for Learning Sciences & Teacher Education

Australian Catholic University, Brisbane, Australia

ryan.wu@acu.edu.au (this opens in a new tab)

How to submit:

All authors must follow the Submission Guidelines (this opens in a new tab) before submitting and select "Machine Learning in Environmental Modelling” as Article type.

Submit your article via Snapp (this opens in a new tab) or by clicking on the Submit manuscript button on the home page of Environmental Modeling and Assessment (this opens in a new tab). 

Environmental Modeling and Assessment is a hybrid open access journal. Authors can opt to make their research open access (OA) with Open Choice if they wish. More information can be found here (this opens in a new tab). Visit Springer Nature’s open access funding & support services (this opens in a new tab) for information about research funders and institutions that provide funding for APCs.