Spatiotemporal Trajectory Evolution Optimization: A Heuristic Optimization Method Based on Spatiotemporal Data Analytics

With the development of information technology and the Internet of Things, spatiotemporal data is experiencing explosive growth in fields such as transportation, environment, energy, and public safety. How to utilize spatiotemporal data analysis methods to solve optimization problems has become an important direction in current data science and artificial intelligence research. This paper proposes a novel Spatiotemporal Trajectory Evolution Optimization (STTEO) algorithm, which treats candidate solutions as trajectories evolving in a continuous spatial-temporal domain. It achieves a balance between global search capability and local search accuracy through a spatiotemporal potential field mechanism, a trajectory prediction mechanism, and an adaptive perturbation mechanism. This method fully reflects the characteristics of spatiotemporal data analysis, including spatial neighborhood correlation, temporal dynamic evolution, and historical trajectory dependence. The algorithm's mathematical formulas systematically describe the update process of candidate solutions, potential field calculation, and adaptive perturbation mechanism, laying the foundation for further theoretical analysis and applications.