============
Aim & Scope
============

Environmental data are growing steadily in volume, complexity and diversity to Big Data, mainly driven by advanced sensor technology. Machine Learning offers new techniques for unravelling complexity and knowledge discovery from Big Data in environmental sciences.

The aim of the SI is to provide a state-of-the-art survey of environmental research topics that can benefit from Machine Learning methods and techniques.

To this purpose, the SI welcomes papers on successful environmental applications of machine learning and pattern recognition techniques to diverse domains of environmental research, that demonstrate how Machine Learning improves our understanding of natural systems, socio-environmental interactions, or tackling the inherent complexity of environmental Big Data. Application domains may vary, and include for instance recognition of biodiversity in thermal, photo and acoustic images, natural hazards analysis and prediction, environmental remote sensing, estimation of environmental risks, prediction of the concentrations of pollutants in geographical areas, environmental threshold analysis and predictive modelling, estimation of Genetical Modified Organisms (GMO) effects on non-target species. Contributions are expected to have a strong methodological contribution to environmental sciences research, and applications of known methods in new case studies will not be considered.

The SI offers a place for Machine Learning and Environmental research communities to interact, and demonstrate the advances of Machine Learning for the Environmental Sciences. Prospective contributions should clearly indicate their contribution in tackling open problems in environmental research that still have not properly benefited from Machine Learning.

The SI is inspired by the first Workshop on Machine Learning Advances Environmental Science (MAES) held at International Conference on Pattern Recognition (ICPR) 2020, held on January 10-15, 2021.

Αuthors should consult the general author guidelines of the journal [1] and submit their articles through the Editorial Manager submission system [2].
When submitting the manuscript, select as article type “VSI-Mach.Learn.Adv.Env.Sc”.
[1]: https://www.elsevier.com/journals/environmental-modelling-and-software/1364-8152/guide-for-authors
[2]: https://www.editorialmanager.com/envsoft/default.aspx

==========
Timetable
==========

01 Feb 2021 - Open for submissions
01 July 2021 - ***Submission deadline***
July-August 2021 - Author notifications & revisions
September 2021 - Final editorial decisions
December 2021 - Publication

================
Editor-in-Chief
================

D.P. Ames, Brigham Young University, Provo, Utah, United States

==============
Guest Editors
==============

Ioannis N. Athanasiadis, Wageningen University and Research, The Netherlands
Francesco Camastra, University of Naples Parthenope, Italy
Friedrich Recknagel, University of Adelaide, Australia
Antonino Staiano, University of Naples Parthenope, Italy