Integrating AI/ML Capabilities for Geohazards and Urban Management Applications

The primary objective of this project is to augment the capabilities of Ellip-powered Exploitation platforms, specifically Geohazards Exploitation Platform (GEP) and Urban Thematic Exploitation Platform (U-TEP), by seamlessly integrating an AI/ML processing framework. This comprehensive framework will encompass the entire machine learning pipeline, including data discovery, access to training data, model development and deployment.

GEP and U-TEP are both platforms that are designed to support the exploitation of satellite Earth Observation (EO) data in their respective thematic areas, geohazards and urban management, catering to diverse user communities such as researchers, policymakers, and planners:

• GEP is designed to support the exploitation of satellite Earth Observations for geohazards, focusing on mapping hazard-prone land surfaces and monitoring terrain deformation. With more than 25 services for monitoring terrain motion and critical infrastructures, GEP has over 2950 registered users, with 350+ actively creating new content.
• U-TEP aims to provide end-to-end and ready-to-use solutions for a broad spectrum of users to extract unique information and indicators required for urban management and sustainability. It focuses on bridging the gap between the mass data streams and archives of various satellite missions and the information needs of users involved in urban and environmental science, planning, and policy.

Both platforms offer various services, including data access, processing, analytics, and visualization, while providing tools and resources for customized applications. They leverage cloud-based infrastructure to handle large volumes of EO data efficiently and offer seamless access to their services.

A critical aspect of this project will be the integration of MLOps processes into both GEP and U-TEP platforms’ service offerings. MLOps, which combines machine learning, DevOps, and data engineering practices, will facilitate seamless deployment, monitoring, and management of AI/ML models, ensuring the smooth operation of AI-driven applications on the platforms.

To achieve the project’s goals, the focus will be on addressing key questions related to necessary services, interface requirements, component interactions, support for various geospatial data types, and algorithm independence. Several approaches will be considered to tackle these challenges, such as managing training data, implementing “move-the-algorithm-to-the-data” principles, emphasizing transparency and accountability, and enabling testing and deployment of ML algorithms on fully-scaled infrastructures.

Upon successful completion, the project will result in the enhancement of both GEP and Urban TEP platforms and their service offerings. The addition of AI/ML capabilities will empower service providers to develop and deploy AI/ML models, ultimately improving their services and delivering added value to their customers. This enhancement will greatly benefit the GEP and Urban TEP platforms by expanding their capabilities and enabling new AI-driven applications for geohazards and urban management.