Advances in Deep Learning Techniques for the Analysis of Remote Sensing Time Series

Dear Colleagues,

New sensors are now acquiring massive and dense remote sensing time series of the Earth’s surface at a large scale. The joint use of different sensors provides a rich description of a phenomenon or a scene in various modalities (optical, radar, hyperspectral, lidar, street views, etc.). For example, both Sentinel-1 and Sentinel-2 constellations’ sensors (from the European Copernicus programme) acquire satellite images about every five days, at a medium spatial resolution, of all emerged surfaces in radar and optical domains, respectively. The availability of this unprecedented quantity of remote sensing time series data opens new opportunities in many applications such as land use land cover mapping, crop mapping, change detection, yield estimation, characterization of urban growth, and forest and soil monitoring. They also offer the possibility to track land surface dynamics through long-term analysis and in near real-time.

In recent years, deep learning techniques have arisen as an efficient tool for processing (remote sensing) time series data in various tasks (classification, clustering, forecasting, or regression). Although these approaches can handle the massive quantity of time series data acquired by remote sensors, they require much high-quality labelled data to be applied at regional or continental scales. This is not always available in remote sensing because it is hard to label large areas of the Earth at a high resolution and land cover changes more frequently than the labels are updated. Other difficulties to apply deep learning techniques developed in computer vision come from the complexity and specificity of remote sensing time series data that are massive, multivariate, noisy, and irregularly sampled. Furthermore, decisions and predictions from those models cannot be easily explained, which prevents a meaningful understanding of the dynamic phenomena observed.

This Special Issue will feature significant and innovative contributions on topics such as the following:

• Innovative deep learning algorithms that handle the complexity and specificity of remote sensing time series (spatio-temporal data cubes, multivariate, noisy, and irregular sampled) and their processing (gap-filling, time series segmentation, super-resolution).
• Multi-sensor data fusion techniques, which efficiently combine EO time series acquired by several sensors in various modalities.
• Novel frameworks to deal with the scarcity and/or the low quality of labelled data including unsupervised, semi-supervised, self-supervised, active, adversarial, and transfer learning.
• Explainable deep learning approaches to improve the understanding of soil surface dynamics.
• Long-term and data stream analyses in the scope of land cover mapping, land use land cover change detection, yield estimation, crop and forest mapping, urban growth.
• New datasets to benchmark deep learning for remote sensing time series analysis.

Dr. Charlotte Pelletier
Guest Editor

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.

• Time series analysis
• Satellite Image Time Series
• Deep learning
• Data fusion
• Data stream
• Explainability
• Unsupervised and semi-supervised domain adaptation
• Multi-sensors
• Long term analysis
• Large scale analysis
• Land cover mapping
• Land use land cover
• Change detection
• Benchmarked datasets