The quasipotential function allows for comprehension and prediction of the escape mechanisms from metastable states in nonlinear dynamical systems. This function acts as a natural extension of the potential function for non-gradient systems and it unveils important properties such as the maximum likelihood transition paths, transition rates and expected exit times of the system. Here, we demonstrate how to discover parsimonious equations for the quasipotential directly from data. Leveraging machine learning, we combine two existing data-driven techniques, namely a neural network and a sparse regression algorithm, specifically designed to symbolically describe multistable energy landscapes. First, we employ a vanilla neural network enhanced with a renormalization and rescaling procedure to achieve an orthogonal decomposition of the vector field. Next, we apply symbolic regression to extract the downhill and circulatory components of the decomposition, ensuring consistency with the underlying dynamics. This symbolic reconstruction involves a simultaneous regression that imposes constraints on both the orthogonality condition and the vector field. We implement and benchmark our approach using an archetypal model with a known exact quasipotential, as well as a nanomechanical resonator system. We further demonstrate its applicability to noisy data and to a four-dimensional system. Our model-unbiased analytical forms of the quasipotential is of interest to a wide range of applications aimed at assessing metastability and energy landscapes, serving to parametrically capture the distinctive fingerprint of the fluctuating dynamics.
Towards a data-scale independent regulariser for robust sparse identification of non-linear dynamics
Department of Mechanical and Aeronautical Engineering, University of Pretoria(机械与航空工程系,普里蒂亚大学);School of Mechanical, Industrial and Aeronautical Engineering, University of the Witwatersrand(机械、工业与航空工程学院,威特沃特斯兰大学)
From STLS to Projection-based Dictionary Selection in Sparse Regression for System Identification
AI Institute in Dynamic Systems, Department of Mechanical Engineering, University of Washington(动态系统人工智能研究所,机械工程系,华盛顿大学);Department of Mechanical Engineering, University of Hawai‘i at Mānoa(机械工程系,夏威夷大学马诺阿分校);Departamento de Matemática e Computação, Faculdade de Ciências e Tecnologia, Universidade Estadual Paulista “Júlio de Mesquita Filho”(数学与计算系,科技学院,保罗斯州立大学“朱利奥·梅斯奎塔·弗洛雷斯”分校)
PySINDy: A Python package for the Sparse Identification of Nonlinear Dynamics from Data
PySINDy是一个Python包,用于从数据中发现控制动力系统模型。特别是,PySINDy提供了将非线性动力学稀疏识别(SINDy)(Brunton et al. 2016)方法应用于模型发现的工具。在这项工作中,我们提供了一个简单的描述的数学基础的SINDy,概述和演示的功能实现的PySINDy(与代码示例),实用的建议,为用户,并列出了潜在的扩展PySINDy。软件可在https://github.com/dynamicslab/pysindy上获得。
Physiology-Informed Sparse Identification of Dynamic Crop Models
Delft Institute of Applied Mathematics, Delft University of Technology(代尔夫特理工大学应用数学研究所);Applied Statistics, Wageningen University and Research(瓦赫宁根大学与研究与应用统计系)