隐含的基于Runge-Kutta的生物动机系统中管理方程的稀疏识别
Mehrdad Anvari1, Hamidreza Marasi2, Hossein Kheiri1
1Department of Applied Mathematics, Faculty of Mathematics, Statistics, and Computer Science, University of Tabriz, Tabriz, 51666-16471, Iran.
一个新的IRK-SINDy框架使用隐性Runge-Kutta方法来从稀缺的,杂的数据中稳定地确定治理方程. 这种数据驱动的方法改善了复杂的物理和生物系统中的模型发现.
科学领域:
- 动态系统理论
- 计算物理
- 生物信息学
背景情况:
- 从数据中发现治理方程对于科学理解至关重要.
- 像SINDy这样的传统方法与杂或有限的数据集作斗争.
- 导数近似的灵敏度阻碍了现有技术的稳定性.
研究的目的:
- 引入一个新的数据驱动框架,IRK-SINDy,用于稳健的方程发现.
- 在数据稀缺和噪音的情况下加强动态系统的识别.
- 提高发现模型的可解释性和通用性.
主要方法:
- 将高阶隐性朗格-库塔方法 (IRK) 与稀疏识别结合起来.
- 使用代方案和深度神经网络进行IRK集成.
- 验证各种基准动态系统的框架.
主要成果:
- 与SINDy和RK4-SINDy相比,IRK-SINDy在数据稀缺和噪声方面表现出更高的稳定性.
- IRK 的 A 稳定性允许更少的步骤大小限制,提高性能.
- 在各种线性,非线性和生物模型中成功识别治理方程.
结论:
- 在数据驱动的科学发现方面取得了重大进展.
- 该框架甚至在具有挑战性的数据条件下提供可靠的方程识别.
- 这种方法在复杂系统中为更准确的建模铺平了道路.
更多相关视频
14:33Optimize Flue Gas Settings to Promote Microalgae Growth in Photobioreactors via Computer Simulations
Published on: October 1, 2013
08:54Creating a Structurally Realistic Finite Element Geometric Model of a Cardiomyocyte to Study the Role of Cellular Architecture in Cardiomyocyte Systems Biology
Published on: April 18, 2018
相关概念视频
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
Linear Approximation in Time Domain
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
Linear Approximation in Frequency Domain
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
Euler Equations of Motion
Transmission-Line Differential Equations
Line Section Model
A circuit representing a line section of length Δx helps in understanding the transmission line parameters. The voltage V(x) and current i(x) are measured...
One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation
On...
