Hong Kong — December 24, 2025
In a landmark development for seismic research and artificial intelligence, a team of researchers led by Boris Kriuk at the Hong Kong University of Science and Technology has released “Poseidon”, the world’s largest open-source earthquake dataset, marking the first phase of an ambitious project to develop next-generation earthquake prediction technology.
The dataset, named after the Greek god of earthquakes, contains over 2.8 million seismic events spanning 35 years of global earthquake activity from 1990 to 2024. The advanced collection includes detailed measurements of magnitude, depth, geographic coordinates, energy release calculations, and dozens of quality metrics for each recorded event.
“This is not just another dataset sample release,” Kriuk stated during the announcement. “Poseidon represents the foundation upon which we will build truly adaptive earthquake prediction systems. The seismic research community has long needed a unified, accessible resource of this scale, and we are making it freely available to researchers worldwide.”
The release marks the beginning of a two-phase initiative from Kriuk’s Particle AI research group. The second phase, expected in the coming months, will introduce an open-source artificial intelligence model featuring what the team describes as a “novel dynamic physics-informed architecture.” The approach aims to combine traditional physics-based seismic modeling with cutting-edge adaptive learning techniques, revolutionizing how scientists approach earthquake forecasting.
Boris Kriuk has established himself as one of the world’s leading pioneers in the field of dynamic adaptation, a paradigm that emphasizes creating AI systems capable of modifying their internal structures and decision-making processes in real-time as conditions change. His research portfolio demonstrates a consistent commitment to moving beyond static, rigid computational models toward autonomous systems that can adjust their logic in response to evolving data distributions and environmental contexts.
In November 2025, Kriuk published inspiring work on morphing tree structures in gradient boosting algorithms, demonstrating how traditionally fixed decision tree architectures could be redesigned to dynamically reshape themselves during the learning process. Earlier in January, he and his collaborators introduced the concept of epigenetic memory in evolutionary algorithms, drawing inspiration from biological systems where organisms retain and transmit adaptive responses across generations without altering their underlying genetic code.
“The earthquake prediction problem is fundamentally a dynamic adaptation challenge,” Kriuk explained. “Seismic patterns are not static. Fault systems evolve, stress accumulates and releases in complex patterns, and the relationships between precursor signals and actual events shift over time. Any AI system that hopes to make meaningful predictions must be capable of adapting its understanding as the Earth itself changes.”
The team brings significant experience in applying advanced computational methods to large-scale environmental challenges. Earlier this year, Kriuk’s group completed the largest open-source study conducted on the Arctic zone, developing AI-powered algorithmic analysis to process vast quantities of climate and environmental data from the polar region. That project demonstrated the team’s capability to handle massive datasets while extracting meaningful patterns relevant to global scientific challenges.
The Poseidon dataset has been specifically structured to support a wide range of machine learning applications, including earthquake prediction modeling, aftershock sequence analysis, magnitude-frequency studies, tsunami early warning system development, and seismic hazard mapping. The inclusion of pre-computed energy values using the Gutenberg-Richter relation and spatial grid features for heatmap generation reflects the team’s intention to lower barriers for researchers entering the field.
Industry observers note that the open-source nature of both the dataset and the forthcoming AI model represents a significant departure from the proprietary approaches that have characterized much of the recent AI development landscape. By making these resources freely available, Kriuk and his team are positioning their work as a public good rather than a commercial product.
As the world grapples with increasing seismic risks in densely populated regions, the potential for AI-assisted earthquake prediction has never been more urgent. With the Poseidon dataset now available and a physics-informed adaptive AI model on the horizon, Boris Kriuk and his team may be laying the groundwork for a new era in humanity’s ability to anticipate and prepare for one of nature’s most destructive forces.
