[AISWorld] Contributing a chapter for a Springer Book on XAI in Remote Sensing: Theories, Challenges and Applications

[mohamed Lahby]

Contributing a chapter for a Springer Book on XAI in Remote Sensing:
Theories, Challenges and Applications
Dear colleague,
We are editing a Springer Book entitled “Explainable artificial
intelligence (XAI) in Remote Sensing: Theories, Challenges and
Applications”. The Book will be indexed by Scopus and ISI.
I cordially invite you to contribute a chapter. The full chapter is due
later this year but for now, I will just need the following:
- Author List
- Chapter Title
- Abstract (between 2 and 6 sentences)
The last deadline to submit your short abstract directly at lahby at ieee.org
is Oct, 10th, 2021
SCOPE:
With the advent of the big data era in remote sensing, artificial
intelligence (AI) has spread to almost every corner of various remote
sensing applications. In many cases, the characteristics of remote sensing
big data, such as multi-source, multi-scale, high-dimensional, dynamic
state, isomeric, and non-linear features, 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 some
inverse remote sensing tasks (atmosphere, vegetation, etc.). Using large
labeled datasets, we can often make very accurate predictions on remote
sensing data.
However, current data-driven AI has not provided us with clear physical or
cognitive meaning of remote sensing data's internal features and
representations. Most deep learning techniques do not reveal how data
features take effect and why predictions are made. Remote sensing data has
exacerbated the problem of opacity and inexplicability of current AI. It
becomes a barrier between the latest AI techniques and some remote sensing
applications. Many scientists in hydrological remote sensing, atmospheric
remote sensing, oceanic remote sensing, etc. do not even believe the
results of deep learning predictions, as these communities are more
inclined to believe models with clear physical meaning. Explainable
Artificial Intelligence (XAI) is widely recognized as a crucial step for
the practical deployment of AI models in remote sensing communities.
This forthcoming book seeks contributions to the theory or applications of
XAI in remote sensing data. In particular, we are looking for research
papers on applications with physical or cognitive models represented by
XAI, or papers dealing with how remote sensing data drives the XAI-based
model.
Topics of interest include, but are not limited to:
Part A: Fundamental Concepts of Explainable Artificial Intelligence
Part B: Fundamental Concepts of Big Data Mining
Part C: Artificial Intelligence for Remote Sensing
Part D: Explainable Artificial Intelligence for Remote Sensing
Part E: Futuristic Ideas
Editors:
Mohamed Lahby, Hassan II University, Casablanca Morocco
Yassine Maleh, Sultan Moulay Slimane University, Morocco
Mohammed Al-Sarem, Taibah University, Medina, Saudi ArabiaAla
Al-Fuqaha, Hamad Bin Khalifa University, Qatar