Expanding Data Integration and Backend Capabilities

Development during this phase focused on strengthening the data infrastructure and backend capabilities that support the Virtual Situation Room. A key milestone was implementing Azure PostgreSQL migration and integration into the core pipeline, allowing processed data and generated outputs to be stored and accessed more reliably across the system. In parallel, work began on building the backend application using Django, laying the foundation for a more robust application layer that connects the data pipelines, analytical services, and frontend interface.

ReliefWeb Integration

To expand the system’s information coverage, ReliefWeb was successfully integrated into the data ingestion agent, providing access to a broader and more consistent stream of crisis-related information. As a well-established humanitarian information platform, ReliefWeb offers structured and regularly updated reports from a wide range of trusted organisations, making it a valuable addition to the ingestion pipeline.

The integration enables the system to systematically retrieve and incorporate relevant reports into its processing workflow, increasing both the volume and diversity of available data. This reduces reliance on existing sources such as HDX HAPI and GDELT and improves the robustness of the overall data ingestion agent.

Application Features

On the application side, we designed an interactive chatbot feature that allows users to conversationally explore insights generated from the reports. Instead of navigating only through static outputs, analysts can now ask targeted questions and quickly surface relevant findings derived from the generated reports. The chatbot is designed to only answer queries relevant to the current reports selected by the user, preventing any misuse of the model, as well as preventing hallucination by augmenting its answers with reliable information.

We also extended the frontend analytical tools by adding geospatial overlays to the dashboard map, enabling analysts to visualize areas of impact directly within the interface. These overlays are sourced from Copernicus, and contextualize the data geographically, making it easier to identify patterns, affected regions, and emerging hotspots during crisis monitoring.

Copernicus Area-of-Interest overlays with crisis density highlights on the Regions Panel below

Finally, we contributed to testing the system on an additional humanitarian scenario through the Sudan crisis analysis pipeline, which was prepared for an internal demonstration within the International Federation of Red Cross and Red Crescent Societies. This work helped validate that the pipeline could be adapted to different crisis contexts while maintaining consistent analytical outputs.

Comments

Post a Comment

Popular posts from this blog

Project Consolidation and Interesting Finds

Image
Over the past few weeks, the team has been focused on integrating and consolidating the various components of the Virtual Situation Room into a single, streamlined workflow. Integration Highlights Language Verification Agent Integration – We fully incorporated the agent into the main workflow, ensuring that content verification and AI-generated outputs maintain high quality across the system. Frontend-Backend Connection – The dashboard frontend is now fully integrated with backend services, allowing seamless display of processed data and AI-generated reports. Unified Pipeline Development – The team is consolidating modular agents and data components into a single pipeline, ensuring smooth operation from data ingestion, through processing, to final report generation and dashboard visualization. Preparing for Client Handover As the project approaches client delivery, the team was focused on making the system as user-friendly and reliable as possible: Single-Click Wor...
Read more

Finishing Touches and Deployment

Image
With the project deadline approaching, the team applied the finishing touches to the Virtual Situation Room, as well as ensuring robustness throughout the entire system. While some members were working on deploying the app onto Azure, the following features were being finalized: Resilience testing for the agent orchestration pipeline Admin panel for role-based access to key endpoints "What's New" feature that enables report comparisons Resilience Testing Resilience testing is implemented within the agent orchestration pipeline to ensure consistent and stable report generation under varying conditions. Given the inherent non-determinism of LLM-based systems, these tests focus on validating robustness rather than exact output matching. The resilience testing framework introduces controlled variations in input data, including formatting differences and reordered context. The pipeline is expected to produce semantically consistent reports despite these changes, ensuring that...
Read more