Machine Learning Applications in Earth Science Big Data Analysis

Dear Colleagues,

Earth science research encompasses a wide gamut of study areas. These include studies of the Earth’s interior to its atmosphere, hydrosphere, and biosphere. The research community has continuously strived to understand and model the governing physics behind the observed phenomena and processes representing the complex space–time dynamics. This process benefited from an ever-growing suite of tools and data measured from ground-based instruments, space-borne sensors, and model-generated insights. Theoretical advancements in physics-based modeling, information theory, image understanding, pattern recognition and machine learning have already seen applications in Earth sciences over the last three decades. The open availability of consistently large datasets from multiple measurement systems now provides a unique opportunity to innovate and devise new ways to analyze and process these datasets to obtain valuable insights. These insights have implications for policymakers, stakeholders and for engineering new approaches in managing natural resources and/or for mitigating the impact of changes in climate or other natural disasters.

This Special Issue focuses on applying novel machine learning algorithms and paradigms, including new methodologies (e.g., deep neural networks) for analyzing spatiotemporal datasets to derive new insights or mimic traditional physics-based model-generated output. Traditional machine learning models, in terms of applicability, have been limited by a number of factors. These include a lack of model complexity in representing large non-linear systems, ability to parse through large volumes of data, computational runtime, lack of training data, and use of domain knowledge in influencing the "input" states of model architecture. In order to achieve wider applicability and acceptability, machine learning models will need to embed uncertainty quantification, encapsulate or work in tandem with known physics while offering new insights, account for correlations or nonlinear dependence and ideally persistence and teleconnection. They should remain open to scientific and data-driven interpretations and scale to a wide variety of problems solvable in desktop environments to high performance computing architectures. Novel machine learning models show promise across diverse disciplines as evidenced by a plethora of publications in the last few years in outperforming established benchmarks in prediction, forecasting, classification, and recommendations. Authors are encouraged to understand and evaluate their applicability, including whether such approaches may be combined with physics-based computer models to increase the accuracy of model predictions and at the same time leverage the growing volume of data in a way that new evolving technologies in hardware and storage are leveraged to address optimization, scalability, and portability.

This special issue encourages submissions to the following topics, but not limited to:

• Newer architectures for image semantic segmentation in Earth sciences (e.g., deep convolutional neural networks)
• New approaches for data downscaling and data fusion from multiple sources (e.g., optical with radar)
• Model reproducibility towards physics-based simulations and hybrid approaches for biophysical data retrieval
• New methodologies for feature engineering, image pre-processing and feature ranking as relevant to machine learning models
• Object identification, change detection and unknown pattern synthesis from both ground-based and over-the-top imagery systems
• New unsupervised approaches for training data generation
• New methods for time series forecasting, anomaly detection, precursor analysis and gap filling
• Model scaling, generalization, ensemble learning and transfer learning approaches
• Embedded AI for Unmanned Aircraft Systems (UAS), airborne missions or SmallSats

As part of this special issue and in the process of manuscript acceptance, authors are also encouraged to submit their own Github repositories and/or containers (e.g. Docker) for other researchers to replicate model results, workflows and in essence encourage a collaborative mechanism for sharing research results.

Authors are requested to check and follow the Instructions to Authors, see https://www.mdpi.com/journal/remotesensing/instructions.

We look forward to receiving your submissions in this interesting area of specialization.

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. Remote Sensing is an international peer-reviewed open access semimonthly 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 2700 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.