Learning Biological Dynamics From Spatio-Temporal Data by Gaussian Processes

Lifeng Han, Changhan He, Huy Dinh, John Fricks, Yang Kuang

Research output: Contribution to journalArticlepeer-review

Abstract

Model discovery methods offer a promising way to understand biology from data. We propose a method to learn biological dynamics from spatio-temporal data by Gaussian processes. This approach is essentially “equation free” and hence avoids model derivation, which is often difficult due to high complexity of biological processes. By exploiting the local nature of biological processes, dynamics can be learned with data sparse in time. When the length scales (hyperparameters) of the squared exponential covariance function are tuned, they reveal key insights of the underlying process. The squared exponential covariance function also simplifies propagation of uncertainty in multi-step forecasting. After evaluating the performance of the method on synthetic data, we demonstrate a case study on real image data of E. coli colony.

Original languageEnglish (US)
Article number69
JournalBulletin of mathematical biology
Volume84
Issue number7
DOIs
StatePublished - Jul 2022

Keywords

  • Forecasting
  • Gaussian processes
  • Spatio-temporal data

ASJC Scopus subject areas

  • General Neuroscience
  • Immunology
  • General Mathematics
  • General Biochemistry, Genetics and Molecular Biology
  • General Environmental Science
  • Pharmacology
  • General Agricultural and Biological Sciences
  • Computational Theory and Mathematics

Fingerprint

Dive into the research topics of 'Learning Biological Dynamics From Spatio-Temporal Data by Gaussian Processes'. Together they form a unique fingerprint.

Cite this