Predicting the Unpredictable: AI Improves Earthquake Forecasting
A new neural network approach leveraging spatial data and advanced statistical modeling enhances the accuracy of weekly earthquake probability forecasts.
A new neural network approach leveraging spatial data and advanced statistical modeling enhances the accuracy of weekly earthquake probability forecasts.
![The Visibility Graph algorithm was applied to a time series generated by a Geometric Brownian Motion-initialized at 100 and characterized by a mean of [latex]0.05[/latex] and variance of [latex]0.5[/latex]-using the “time series to visibility graphs” Python package, demonstrating its capacity to analyze stochastic processes.](https://arxiv.org/html/2605.21192v1/Images/visibility_graph.png)
A new approach leverages the geometric relationships within financial time series data to improve prediction accuracy.

A new framework combines the power of generative AI with statistical modeling to deliver more accurate and robust financial risk predictions.

A new simulation framework reveals that artificial intelligence agents often struggle to self-regulate within complex marketplaces, necessitating targeted training for stable and fair outcomes.
New research introduces a graph neural network that leverages the principles of chaos theory to generate more reliable prediction intervals for stock prices, moving beyond simple forecasts.
A new artificial intelligence system leverages the power of language models to autonomously generate accurate forecasts for multiple infectious diseases.

A new approach leveraging artificial intelligence reconstructs the complex web of relationships between companies in the semiconductor industry, offering a dynamic view of supply chains and geopolitical influence.

A new review explores the evolution of machine learning models used to forecast the dynamic movements of athletes, focusing on advancements in trajectory prediction.

A new framework combines the power of time series models and large language models to deliver more accurate and explainable predictions.
Securing increasingly autonomous AI systems demands a shift in thinking, and this paper proposes a powerful parallel to the decades of experience in operating system protection.