remotesensing-logo

Journal Browser

Journal Browser

Deep Learning and Explainable AI (XAI) for Next Level Information Extraction from Remote Sensing Imagery

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Remote Sensing Image Processing".

Deadline for manuscript submissions: closed (31 January 2024) | Viewed by 5849

Special Issue Editors

1. Helmholtz-Zentrum Dresden-Rossendorf (HZDR), Helmholtz Institute Freiberg for Resource Technology, 09599 Freiberg, Germany
2. Institute of Advanced Research in Artificial Intelligence (IARAI), 1030 Vienna, Austria
Interests: machine (deep) learning; image and signal processing; multisensor data fusion
Special Issues, Collections and Topics in MDPI journals
Institute for Risk and Disaster Reduction, University College London, London, UK
Interests: machine\deep learning; explainable AI; digital twins
Research Center for Digital Mountain and Remote Sensing Application, Institute of Mountain Hazards and Environment, Chinese Academy of Sciences, Chengdu 610041, China
Interests: land cover/use mapping; natural hazards assessment; environmental management; google earth engine; machine learning

E-Mail Website
Guest Editor Assistant
Centre Eau Terre Environnement, Institut National de la Recherche Scientifique (INRS), Quebec City, QC G1K 9A9, Canada
Interests: object-based image analysis; object detection; machine learning; deep learning

Special Issue Information

Dear Colleagues,

This Special Issue focuses on developments and innovative ideas and techniques relating to deep learning (DL) and explainable AI (XAI) in information extraction from remote sensing (RS) imagery. We especially encourage contributions that present methods and ongoing research, such as algorithm developments and implementations.

Information extraction is known as the interpretation and extraction of qualitative and quantitative information from RS data. DL can be directly employed for information extraction, while XAI can be used to disentangle causality from correlation in the data for next-level information extraction by explaining the outputs of DL. Classification, change detection, physical quantity extraction, index extraction, and the identification of specific features are the five main categories of information extraction in RS. Information extraction accuracy may be impacted by a variety of factors, including inappropriate satellite imagery selection, noise in the satellite imagery, insufficient resolution of the data for extracting particular information, atmospheric errors, and many more.

The advent of new high-performance cloud computing platforms (e.g., Google Earth Engine) and advancements in state-of-the-art machine learning approaches offer a unique capability to extract accurate and reliable information from RS imagery. DL and XAI methods, in particular, have become a fast-growing trend in the automatic extraction of various RS applications (e.g., water body extraction, road extraction, landslide detection, flood monitoring, and damage evaluations) and interpretation of the DL outcomes, respectively. However, the usage of DL and XAI algorithms in information extraction from RS imagery is still in its infancy, and needs more investigation from scholars. 

This Special Issue aims to clarify how DL and XAI methods can be designed and applied in accurate and next-level information extraction for various RS applications. To highlight new solutions of DL and XAI, integrated or solely, for information extraction, manuscript submissions are encouraged from a broad range of RS topics, which may include, but are not limited to, the following activities:

  • Image processing and classification
  • Change detection and monitoring
  • Scene recognition
  • Data fusion
  • Damage and recovery assessments
  • Water body extraction
  • Landslide detection
  • Vegetation monitoring
  • Flood monitoring
  • Forest monitoring
  • Extraction of archaeological features
  • Coastline extraction

Dr. Omid Ghorbanzadeh
Dr. Pedram Ghamisi
Dr. Saman Ghaffarian
Dr. Amin Naboureh
Guest Editors

Hejar Shahabi
Guest Editor Assistant

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.

Keywords

  • remote sensing
  • information extraction
  • artificial intelligence
  • machine learning
  • deep learning
  • explainable AI
  • classification
  • change detection
  • feature extraction

Published Papers (3 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

24 pages, 12379 KiB  
Article
An Integration of Deep Learning and Transfer Learning for Earthquake-Risk Assessment in the Eurasian Region
Remote Sens. 2023, 15(15), 3759; https://doi.org/10.3390/rs15153759 - 28 Jul 2023
Viewed by 1160
Abstract
The problem of estimating earthquake risk is one of the primary themes for researchers and investigators in the field of geosciences. The combined assessment of spatial probability and the determination of earthquake risk at large scales is challenging. To the best of the [...] Read more.
The problem of estimating earthquake risk is one of the primary themes for researchers and investigators in the field of geosciences. The combined assessment of spatial probability and the determination of earthquake risk at large scales is challenging. To the best of the authors’ knowledge, there no updated earthquake-hazard-and-risk assessments for the Eurasia region have been published since 1999. Considering that Eurasia is characterized by a seismically active Alpine–Himalayan fault zone and the Pacific Ring of Fire, which are frequently affected by devastating events, a continental-scale risk assessment for Eurasia is necessary to check the global applicability of developed methods and to update the earthquake-hazard, -vulnerability, and -risk maps. The current study proposes an integrated deep-transfer-learning approach called the gated recurrent unit–simple recurrent unit (GRU–SRU) to estimate earthquake risk in Eurasia. In this regard, the GRU model estimates the spatial probability, while the SRU model evaluates the vulnerability. To this end, spatial probability assessment (SPA), and earthquake-vulnerability assessment (EVA) results were integrated to generate risk A, while the earthquake-hazard assessment (EHA) and EVA were considered to generate risk B. This research concludes that in the case of earthquake-risk assessment (ERA), the results obtained for Risk B were better than those for risk A. Using this approach, we also evaluated the stability of the factors and interpreted the interaction values to form a spatial prediction. The accuracy of our proposed integrated approach was examined by means of a comparison between the obtained deep learning (DL)-based results and the maps generated by the Global Earthquake Model (GEM). The accuracy of the SPA was 93.17%, while that of the EVA was 89.33%. Full article
Show Figures

Graphical abstract

26 pages, 15826 KiB  
Article
Explainable Artificial Intelligence (XAI) Model for Earthquake Spatial Probability Assessment in Arabian Peninsula
Remote Sens. 2023, 15(9), 2248; https://doi.org/10.3390/rs15092248 - 24 Apr 2023
Cited by 4 | Viewed by 2401
Abstract
Among all the natural hazards, earthquake prediction is an arduous task. Although many studies have been published on earthquake hazard assessment (EHA), very few have been published on the use of artificial intelligence (AI) in spatial probability assessment (SPA). There is a great [...] Read more.
Among all the natural hazards, earthquake prediction is an arduous task. Although many studies have been published on earthquake hazard assessment (EHA), very few have been published on the use of artificial intelligence (AI) in spatial probability assessment (SPA). There is a great deal of complexity observed in the SPA modeling process due to the involvement of seismological to geophysical factors. Recent studies have shown that the insertion of certain integrated factors such as ground shaking, seismic gap, and tectonic contacts in the AI model improves accuracy to a great extent. Because of the black-box nature of AI models, this paper explores the use of an explainable artificial intelligence (XAI) model in SPA. This study aims to develop a hybrid Inception v3-ensemble extreme gradient boosting (XGBoost) model and shapely additive explanations (SHAP). The model would efficiently interpret and recognize factors’ behavior and their weighted contribution. The work explains the specific factors responsible for and their importance in SPA. The earthquake inventory data were collected from the US Geological Survey (USGS) for the past 22 years ranging the magnitudes from 5 Mw and above. Landsat-8 satellite imagery and digital elevation model (DEM) data were also incorporated in the analysis. Results revealed that the SHAP outputs align with the hybrid Inception v3-XGBoost model (87.9% accuracy) explanations, thus indicating the necessity to add new factors such as seismic gaps and tectonic contacts, where the absence of these factors makes the prediction model performs poorly. According to SHAP interpretations, peak ground accelerations (PGA), magnitude variation, seismic gap, and epicenter density are the most critical factors for SPA. The recent Turkey earthquakes (Mw 7.8, 7.5, and 6.7) due to the active east Anatolian fault validate the obtained AI-based earthquake SPA results. The conclusions drawn from the explainable algorithm depicted the importance of relevant, irrelevant, and new futuristic factors in AI-based SPA modeling. Full article
Show Figures

Graphical abstract

18 pages, 16477 KiB  
Article
Panoptic SwiftNet: Pyramidal Fusion for Real-Time Panoptic Segmentation
Remote Sens. 2023, 15(8), 1968; https://doi.org/10.3390/rs15081968 - 07 Apr 2023
Cited by 2 | Viewed by 1138
Abstract
Dense panoptic prediction is a key ingredient in many existing applications such as autonomous driving, automated warehouses, or remote sensing. Many of these applications require fast inference over large input resolutions on affordable or even embedded hardware. We proposed to achieve this goal [...] Read more.
Dense panoptic prediction is a key ingredient in many existing applications such as autonomous driving, automated warehouses, or remote sensing. Many of these applications require fast inference over large input resolutions on affordable or even embedded hardware. We proposed to achieve this goal by trading off backbone capacity for multi-scale feature extraction. In comparison with contemporaneous approaches to panoptic segmentation, the main novelties of our method are efficient scale-equivariant feature extraction, cross-scale upsampling through pyramidal fusion and boundary-aware learning of pixel-to-instance assignment. The proposed method is very well suited for remote sensing imagery due to the huge number of pixels in typical city-wide and region-wide datasets. We present panoptic experiments on Cityscapes, Vistas, COCO, and the BSB-Aerial dataset. Our models outperformed the state-of-the-art on the BSB-Aerial dataset while being able to process more than a hundred 1MPx images per second on an RTX3090 GPU with FP16 precision and TensorRT optimization. Full article
Show Figures

Figure 1

Back to TopTop