This paper presents the Open-Source Intelligence Disaster Event Tracker (ODET), a modular platform that provides customizable endpoints and agents for each processing step. ODET enables the implementation of AI-enhanced algorithms to respond to various complex disaster scenarios. To evaluate ODET, we conducted two case studies using unmodified AI models to demonstrate its base performance and potential applications. Through our case studies on Hurricane Harvey and the 2023 Turkey earthquake, we show how complex tasks can be quickly broken down with ODET while achieving a score of up to 89% using the AlignScore metric. ODET enables compliance with Berkeley protocol requirements by ensuring data privacy and using privacy-preserving processing methods. Our results demonstrate that ODET is a robust platform for the long-term monitoring and analysis of dynamic environments and can improve the efficiency and accuracy of situational awareness reports in disaster management.
Rapid classification of social media content during humanitarian crises is essential for effective disaster relief; however, traditional approaches require extensive annotated training data, which are often unavailable during new disasters. This paper presents a training-free, multimodal classification framework that leverages zero-shot vision-language models to analyze disaster-related social media content without task-specific training. The framework employs a two-stage prompt-engineered pipeline using the locally deployable Mistral-Small-3.1-24B-Instruct model, performing binary informativeness detection followed by multiclass categorization into eight humanitarian categories through structured JSON output generation. Evaluation on the CrisisMMD dataset of 18,082 multimodal samples from seven natural disasters demonstrated binary F1 scores above 0.84 for both text and image informativeness detection and weighted F1 scores of 0.61 (text) and 0.72 (image) for humanitarian categorization. The framework generalizes consistently across all disaster types with minimal performance variance (standard deviation below 0.031) and operates entirely on local infrastructure without cloud dependencies, requiring only moderate GPU resources. By eliminating training data requirements, this approach enables immediate deployment during new disasters, demonstrating that zero-shot multimodal classification achieves practically relevant performance for real-time crisis response.
Microgrid systems encounter various challenges, including critical issues such as load scheduling and the generation of large amounts of data that need to be monitored to stabilize the system during operation. It is essential to ensure the real-time collection and protection of data throughout the process. In this context, infrastructure such as cloud computing and data security plays a crucial role in addressing these challenges. Data generated from a microgrid includes different attributes such as meteorological information, energy production data, and distributed energy resources data, which help monitor the balance between supply and demand. This data also plays a crucial role in energy forecasting, predictive maintenance, and analyzing the critical performance of grid-connected or standalone microgrid systems. The paper discusses the significance of the data collected from distributed energy resources and provides a critical analysis of current solutions and future perspectives on data sharing in microgrids and their challenges.