Deep Learning-based Analysis of Basins of Attraction

Abstract

This research addresses the challenge of characterizing the complexity and unpredictability of basins within various dynamical systems. The main focus is on demonstrating the efficiency of convolutional neural networks (CNNs) in this field. Conventional methods become computationally demanding when analyzing multiple basins of attraction across different parameters of dynamical systems. Our research presents an innovative approach that employs CNN architectures for this purpose, showcasing their superior performance in comparison to conventional methods. We conduct a comparative analysis of various CNN models, highlighting the effectiveness of our proposed characterization method while acknowledging the validity of prior approaches. The findings not only showcase the potential of CNNs but also emphasize their significance in advancing the exploration of diverse behaviors within dynamical systems.

References in corpus (8)

• Attractor Reconstruction by Machine Learning
• Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model
• Basin entropy: a new tool to analyze uncertainty in dynamical systems
• Effortless estimation of basins of attraction
• A test for fractal boundaries based on the basin entropy
• The saddle-straddle method to test for Wada basins
• Using the basin entropy to explore bifurcations
• Characterization of Fractal Basins Using Deep Convolutional Neural Networks