Lecture Title: The Exasperating elusivity of anomaly detection

Lecture Title: Big data analytics for natural disaster management

Abstract

Natural Disaster Management (NDM, e.g., for wildfires, floods) can be greatly improved by automating precise semantic 3D mapping and disaster evolution prediction to achieve NDM goals in near-real-time. To this end, many heterogeneous extreme data sources must be analyzed and fused: smart drone and in-situ sensors, remote sensing data, topographical data, meteorological data/predictions and geosocial media data (text, image and videos). The lecture focus is on the extreme nature of the data, due to their varying resolution and quality, very large volume and update rate, different spatiotemporal resolutions and acquisition frequencies, real-time needs and multilingualism. Extreme data analytics can help developing an integrated, ground-breaking NDM platform, focusing on real-time semantic extraction from multiple heterogeneous data modalities and sources, on-the-fly construction of a meaningful semantically annotated 3D disaster area map, prediction of disaster evolution and improved communication between service providers and end-users, through automated process triggering and response recommendations. Semantic analysis computations will be distributed across the edge-to-cloud continuum, in a federated manner, to minimize latency. Extreme data analytics will be performed in a trustworthy and transparent way, by greatly advancing state-of-the-art AI and XAI approaches. The constantly updated 3D map and the disaster evolution predictions will form the basis for an advanced, interactive, Extended Reality (XR) interface, where the current situation will be visualized and different response strategies will be dynamically evaluated through simulation by NDM personnel. An innovative, scalable and efficient implementation platform will provide precise NDM support, based on extreme data analytics.

Title: Applications and Challenges of AI in Microscopy and Life Science Research

Abstract

AI has transformed many important areas within life science research, offering significant potential for understanding complex biological systems. One of the key areas where AI is making a notable impact is in microscopy-based investigations. AI models have shown impressive abilities in decoding genetic structures, speeding up drug discovery, and analyzing detailed subcellular activities and molecular interactions. By using advanced computational methods across various imaging techniques, these models can provide deeper insights into biological processes that are essential for understanding disease pathways, ultimately improving our knowledge of human biology and leading to the development of effective, targeted treatments. Specifically, vision-based deep learning models, such as U-Nets and graph-based models, have been successfully applied to analyze high-resolution microscopy data. These models enable the automated analysis of subcellular structures, which is crucial for understanding cellular mechanisms and disease development. However, despite many AI advancements, significant challenges remain, such as the need for large, high-quality labeled datasets. This lecture will address the main challenges limiting current AI methods, including data inconsistency and insufficient annotation in biological datasets. We will discuss strategies to overcome these barriers. Additionally, we will highlight recent advancements in AI-driven analysis of subcellular structures, with a focus on mitochondria. Lastly, we will explore new opportunities for AI researchers in this rapidly growing field, emphasizing the potential for innovations that could revolutionize microscopy-based life science research and therapeutic discovery.