Explainable Artificial Intelligence (XAI) in Remote Sensing Big Data

Dear Colleagues,

With the advent of the era of remote sensing big data, artificial intelligence (AI) has spread to almost all corners of the various remote sensing applications. In many cases, characteristics of remote sensing big data, such as multi-source, multi-scale, high-dimensional, dynamic state, isomer, and non-linear characteristics etc., are well learned by advanced AI algorithms. Data-driven methods, especially deep learning models, have achieved state-of-the-art results for most remote sensing image processing tasks (object detection, segmentation etc.) and even some remote sensing inverse tasks (atmosphere, vegetarian etc.). By using large labeled datasets, we can often make highly accurate predictions on remote sensing data.

However, current data-driven AI did not provide us clear physical or cognitive meaning of the internal features and representations of remote sensing big data. Most deep learning techniques do not disclose how the data features take effect and why the predictions are taken. Remote sensing big data exacerbated the problem of in-transparency and in-explainability of current AI. It is becoming a barrier between the latest AI techniques and some remote sensing applications. Many scientists in hydrology remote sensing, atmospheric remote sensing, and ocean remote sensing etc. even do not believe the prediction results from deep learning, since these communities are more inclined to believe models with a clear physical meaning. Explainable artificial intelligence (XAI) is widely acknowledged as a crucial step to the practical deployment of AI models in remote sensing communities.

This Special Issue seeks contributions on theory or applications of XAI in remote sensing big data. In particular, we seek research articles on the applications whose physical or cognitive models are represented by XAI, or articles addressing how the remote sensing big data drive the model based on XAI.

Topics of interest include, but are not limited to:

1. Theoretical and philosophical foundations of XAI
2. XAI for remote sensing image visual tasks such object detection, segmentation, change detection, fusion etc.
3. XAI for terrestrial remote sensing, atmospheric remote sensing, and ocean remote sensing etc.
4. XAI for unmanned aerial vehicle (UAV) remote sensing big data
5. XAI for simultaneous localization and mapping (SLAM) with remote sensing big data
6. XAI for global scale inversion problems, such as biomass, thermal emission, vegetarian etc.
7. XAI for high performance computation on large-scale remote sensing applications

Prof. Dr. Lizhe Wang
Prof. Dr. Jun Li
Dr. Peng Liu
Guest Editors

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 250 words) can be sent to the Editorial Office for assessment.

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-anonymized 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.