About Machine Learning: Earth
Scope
Machine Learning: Earth™ is a multidisciplinary open access journal dedicated to the application of machine learning (ML), artificial intelligence (AI) and data-driven computational methods across all areas of earth, environmental and climate sciences including efforts to ensure a sustainable future. The journal publishes research reporting data-driven approaches that advance our knowledge of the Earth system, and of the interactions between biosphere, hydrosphere, cryosphere, atmosphere and geosphere. The journal also publishes research that presents methodological, theoretical, or conceptual advances in machine learning and AI with applications to earth, environmental and climate science.
Particular areas of application include (but are not limited to) the following:
- Global change and environmental sustainability
- Energy systems
- Ecology
- Climate mitigation and adaptation
- Climate change
- Carbon capture
- Weather prediction, nowcasting, and forecasting
- Pollution monitoring and prediction
- Environmental (soil, air and water quality) monitoring
- Land surface modelling
- Geologic processes and ecosystem transformations
- Earthquake detection and prediction
- Costal erosion and deposition
- Natural hazards (landslides, rockfalls, avalanches, wildfires) assessment, mapping, and prediction
- Ocean (currents, tides, waves) dynamics
- Ground and surface water (Ice and snow dynamics)
- Paleoclimatology and paleoceanography
- Plant disease recognition
- Food (Crop and supply chain)
- Wildlife conservation and monitoring
- Data equity and data privacy
- Space and planetary science with implications for Earth systems
Why should you publish in Machine Learning: Earth?
- Inclusive Scope: Machine Learning: Earth is a multidisciplinary open access journal dedicated to the application of machine learning (ML), artificial intelligence (AI) and data-driven computational methods across all areas of earth, environmental and climate sciences including efforts to ensure a sustainable future. The journal publishes research reporting data-driven approaches that advance our knowledge of the Earth system, and of the interactions between biosphere, hydrosphere, cryosphere, atmosphere and geosphere. The journal also publishes research that presents methodological, theoretical, or conceptual advances in machine learning and AI with applications to earth, environmental and climate science.
- Open access: Your paper will be published under a CC BY licence, enabling immediate and perpetual access, and permitting the widest possible dissemination and reuse of your research.
- High quality peer review: All articles will be rigorously peer reviewed by IOP Publishing’s global network of expert reviewers, supported by our top-level Editorial Board.
- Fast publication: We are committed to providing you with a fast, professional service to ensure rapid first decision, acceptance and publication. Once accepted, your article will be accessible to readers within 24 hours and will include a citable DOI.
- Pre-print friendly: You are encouraged to post on community pre-print platforms.
- Data and code: Research published in Machine Learning: Earth can include citable datasets and programmable code.
- Society owned: IOP Publishing is a leading society publisher of advanced physics research. Any profits generated by IOP Publishing are invested in the Institute of Physics, helping to support research, education and outreach around the world.
Article types
Machine Learning: Earth welcomes submissions of the following article types:
- Research papers: Articles of unlimited length that report quality original research with conclusions representing a significant advance in the field.
- Letters: Concise (max 5,000 words), high-impact original research articles that report a significant development in the field that deserves priority treatment and rapid publication. Authors submitting letters should provide justification as to why rapid publication is essential.
- Dataset Articles: Dataset Articles describe new curated datasets -or significant extensions of existing datasets that are available in an approved data repository, providing details of its collection, processing, file formats etc. The articles focus on helping others to understand and reuse data, rather than testing hypotheses, or presenting new interpretations, methods or in-depth analyses.
- Perspectives: Commentaries on the impact of previously published work, or authoritative discussions on the future direction of a field, that are of notable interest to the community.
- Topical reviews: Written by leading researchers, these articles present the background, an overview, and the current state of the art of a particular field or application.
- Benchmarks: Benchmarks seek to present examples of differing methods/models/codes/algorithms/software as applied to a consistent problem or dataset, report on the effectiveness of their performance, and include comparative analysis of the outcomes
- Challenges: Challenges report on community-led initiatives centred around solving a specific scientific problem through the creation of new algorithms, datasets, and/or workflows
- Roadmaps: Overarching, collaboratively authored short perspectives on the status, challenges, and outlook for a broad and highly topical research area. They are normally comprised of 10 to 20 sections, each written by different authors.
- Comments and replies: Comments on, or criticisms of, work previously published in the journal. The authors of the original article will be invited to submit a reply.
Special requirements
Code
We strongly support the principles of Open Source software. We encourage all authors of new code to comply with the Open Source Initiative. Where possible, code should be free to redistribute, and freely available as both source code and a compiled form. Authors should submit their code as supplementary material or provide links to an external repository.
Peer review
The following summary describes the peer review process for Machine Learning: Earth, using the ANSI/NISO Standard Terminology for Peer Review:
- Identity transparency: single-anonymous, double-anonymous (author choice)
- Reviewer interacts with: Editor
- Review information published: review reports (author and reviewer opt in), author/editor communication, reviewer identities (reviewer opt in)
Our Publishing Support website provides more information on our reviewing process as well as checklists in both English and Chinese language to help authors prepare their manuscripts for submission.
If an article is not accepted for publication, we may offer the author the opportunity to transfer their submission to other suitable journals we publish.
Inclusivity and diversity
IOP Publishing recognises that there are inequalities within the scientific publishing and research ecosystems. We are committed to a progressive approach to inclusivity and diversity, and are working hard to eliminate discrimination to foster an equitable and welcoming publishing environment for all.
IOP Publishing follows Guidelines on Inclusive Language and Images in Scholarly Communication to ensure that journal articles use bias-free and culturally sensitive communication. We ask authors to please follow these guidelines in their manuscript submissions.
More information about our work on inclusivity is available on our Open Physics hub.
Ethics
Machine Learning: Earth maintains the highest standards of publication and research ethics. Authors are expected to comply with IOP Publishing’s Ethical Policy.
Research data
Please note that this policy requires authors to include a data availability statement in their article.
For any questions about the policy please contact the journal.
Many research funders now require authors to make all data related to their research available in an online repository. Please refer to the policy for further information about research data, data repositories and data citation.
Open access
For more information on IOP Publishing’s open access policies please see our Open access page.
Members of the Institute of Physics (IOP) are eligible to receive a 25% discount on the article publication charge (APC) for this journal (applicable once per article). The discount can be selected during article submission.
Publication charges
Machine Learning: Earth has no subscription charges and the costs of publication are fully funded by article publication charges (APC).
As part of our commitment to open science, IOP Publishing is currently paying the APC for all articles submitted to the journal.
The list prices shown below will not be charged if your article is accepted for publication.
| GBP | EUR | USD | |
| Article publication charge* | £2500 | €3000 | $3125 |
| Reduced article publication charge* for Group B countries** | £500 | €575 | $675 |
| Reduced article publication charge for Group A countries** | £0 | €0 | $0 |
*excluding VAT where applicable
**eligibility criteria can be found here
APCs only apply to articles accepted for publication; there are no submission charges.
There are no other charges for publishing in Machine Learning: Earth
Paying for open access
Various discounts, waivers and funding arrangements are available to support our authors. Visit our Paying for open access page for further details.
Abstracting and indexing services
We work with our authors to help make their work as easy to discover as possible. Articles published in Machine Learning: Earth will be available in relevant indexing services and databases when appropriate.