Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Physics Informed Modeling of Ecosystem Respiration via Dynamic Mode Decomposition with Control Input

Maha Shadaydeh, Joachim Denzler, Mirco Migliavacca

Abstract

Ecosystem respiration (Reco) represents a major component of the global carbon cycle, and accurate characterization of its dynamics is essential for a comprehensive understanding of ecosystem-climate interactions and the impacts of climate extremes on the ecosystem. This paper presents a novel data-driven and physics-aware method for estimating Reco dynamics using the dynamic mode decomposition with control input (DMDc) technique, an emerging tool for analyzing nonlinear dynamical systems. The proposed model represents Reco as a state space model with an autonomous component and an exogenous control input. The control input can be any ecosystem driver(s), such as air temperature, soil temperature, or soil water content. This unique modeling approach allows controlled intervention to study the effects of different inputs on the system. Experimental results using Fluxnet2015 data show that the prediction accuracy of Reco dynamics achieved with DMDc is comparable to state-of-the-art methods, making it a promising tool for analyzing the dynamic behavior of different vegetation ecosystems on multi-temporal scales in response to different climatic drivers.

Physics Informed Modeling of Ecosystem Respiration via Dynamic Mode Decomposition with Control Input

Abstract

Ecosystem respiration (Reco) represents a major component of the global carbon cycle, and accurate characterization of its dynamics is essential for a comprehensive understanding of ecosystem-climate interactions and the impacts of climate extremes on the ecosystem. This paper presents a novel data-driven and physics-aware method for estimating Reco dynamics using the dynamic mode decomposition with control input (DMDc) technique, an emerging tool for analyzing nonlinear dynamical systems. The proposed model represents Reco as a state space model with an autonomous component and an exogenous control input. The control input can be any ecosystem driver(s), such as air temperature, soil temperature, or soil water content. This unique modeling approach allows controlled intervention to study the effects of different inputs on the system. Experimental results using Fluxnet2015 data show that the prediction accuracy of Reco dynamics achieved with DMDc is comparable to state-of-the-art methods, making it a promising tool for analyzing the dynamic behavior of different vegetation ecosystems on multi-temporal scales in response to different climatic drivers.
Paper Structure (8 sections, 4 equations, 1 figure, 2 tables)

This paper contains 8 sections, 4 equations, 1 figure, 2 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. Dynamic Mode Decomposition with Control (DMDc)
  4. Modeling the dynamics of Reco using DMDc
  5. Time delay embedding (TDE) for characterization of Reco dynamics
  6. Experimental Results and Discussion
  7. Conclusions
  8. Acknowledgment

Figures (1)

  • Figure 1: Singular values of the Hankel matrices H of NEEnight and the control input Tair in different Fluxnet sites and vegetation types. The spread of the singular values is an indicator of the predictability of the system. The number of distinct singular values is the number of dominant dynamic modes in the ecosystem. We can observe four to six dominant modes depending on the vegetation type and location.