Workshop description
The Explainable AI in Space (EASi) workshop addresses a critical intersection between Explainable Artificial Intelligence (XAI) and Space applications, offering broad relevance to multiple research and industrial communities beyond traditional computer vision and pattern recognition domains. As space exploration and Earth observation increasingly rely on AI for mission critical tasks such as satellite operations, data analysis, and decision-making, ensuring the reliability, interpretability, and accountability of these AI systems becomes paramount. The workshop directly addresses these concerns by promoting methods to make AI models more explainable and transparent, particularly in safety-critical and high-stakes environments like space.
The topics covered in the workshop include, but are not limited to:
Where XAI meets space
Counterfactual explanations in Space applications
Explainable on-board AI for critical and non-critical Space applications
Explaining AI models for Earth observation and satellite operations
Physics-aware AI for Earth observation and satellite operations
Realistic generative AI models for optical and radar Earth observation
AI specific Cal/Val paradigms
Theoretical bound for AI methods in Space applications
Exploring the potential impact of incorrect explanations in Space applications
Multimodal XAI methods for Space applications
Simple, fast, low power, low bit rate AI for Space applications
Non-technical presentation of AI explanations in Space operations
On-board explainable AI for Earth observation and satellite operations
Optimization of AI models using XAI for Space applications
Presentation and interpretation of AI explanations in Space applications
Safety of AI models for Space applications (Earth observation, mission-critical)
Techniques for assessing the quality of explanations in Space applications
Trustworthiness of AI systems in Space applications
Verification and validation of AI in Space applications
XAI methods for explaining adversarial attacks in Space
XAI methods for signal and image processing for Space applications
XAI methods for risk assessment in critical Space applications
XAI methods for explaining federated and continual learning in Space
XAI methods for privacy-preserving Space systems
XAI methods for model governance in Space applications
XAI methods for situational awareness in Space
XAI methods for ensuring algorithmic transparency in Space applications
XAI techniques and tools for (not only) space
Benchmarking of XAI systems
Dataset-centric explanations
Explaining bias and fairness of XAI systems
Resource utilization and resource frugality of on-board XAI methods
Robustness and faithfulness of explanations
XAI for time series analysis approaches
XAI methods for estimating AI models’ confidence