Special Session on EO-AI for Humanitarian Emergency Response: from risk prediction to recovery operations

Earth observation (EO) is key in providing relevant information to observe surface objects and phenomena with intended spatial and temporal details from complementary sensing modalities (optical, microwave, and thermal). Coupled with recent advances in artificial intelligence (AI) especially deep learning for computer vision applications in image processing have paved the realization of novel information extraction pipelines and fusion of multi-sensor imagery. By leveraging the availability of computational resources, it is also common to see regional, continental and global scale information layers extracted from earth observation imagery. Even though there are promising developments in AI models for image processing, there are technical and operational limitations demanding further research including but not limited to intensive demand for properly annotated training and validation datasets, generalization across space and time (given there is obvious spatial heterogeneity on objects and phenomena across geography and different time and season), computational resource and ease of use. Therefore, in this session, we welcome submissions that try to address EO-AI research themes including deep learning as well as symbolic expert-based or hybrid AI in analyzing EO data and derivatives related to:

1. EO-AI algorithmic developments in label-efficient training strategies like self-supervised learning, unsu- pervised learning including generative models, few-shot learning, learning from noisy and or incomplete labels
2. Adapting language and foundation models for EO-based operational tasks in disaster management and humanitarian response like visual question answering, object detection and localization tasks
3. Spatio-temporal transfer learning strategies like domain adaptation, meta-learning and any other novel transfer learning strategies enhancing transferability of EO-AI models across geography and time
4. Application of EO-AI models in various application cases including flood mapping, building detection and change monitoring, building damage assessment, settlement and population mapping, burned area mapping
5. Multi-modal hazard prediction and mapping like drought, earthquake, disease outbreak, flood inun- dation and return periods that are relevant for the early warning system
6. Systematic evaluation of regional, continental and global scale open source EO-based information layers like population and settlement layer products, open building datasets
7. Datasets studies tailored for training and validation of EO-AI models.
8. Multi-indicator developments relevant for hazard-related integrated assessments.

Organisers

Prof. Dr. Stefan Lang: Paris Lodron University of Salzburg, Department of Geoinformatics

stefan.lang (at) plus.ac.at

Getachew Workineh Gella: Paris Lodron University of Salzburg, Department of Geoinformatics

getachewworkineh.gella (at) plus.ac.at