A Data-Driven Approach to Partitioning Net Ecosystem Exchange Using a Deep State Space Model

Abstract

Describing ecosystem carbon fluxes is essential for deepening the understanding of the Earth system. However, partitioning net ecosystem exchange (NEE), i.e. the sum of ecosystem respiration (R eco ) and gross primary production (GPP), into these summands is ill-posed since there can be infinitely many mathematically-valid solutions. We propose a novel data-driven approach to NEE partitioning using a deep state space model which combines the interpretability and uncertainty analysis of state space models with the ability of recurrent neural networks to learn the complex functions governing the data. We validate our proposed approach on the FLUXNET dataset. We suggest using both the past and the future of R eco 's predictors for training along with the nighttime NEE (NEE night ) to learn a dynamical model of R eco . We evaluate our nighttime R eco forecasts by comparing them to the ground truth NEE night and obtain the best accuracy with respect to other partitioning methods. The learned nighttime R eco model is then used to forecast the daytime R eco conditioning on the future observations of different predictors, i.e., global radiation, air temperature, precipitation, vapor pressure deficit, and daytime NEE (NEE day ). Subtracted from the NEE day , these estimates yield the GPP, finalizing the partitioning. Our purely data-driven daytime R eco forecasts are in line with the recent empirical partitioning studies reporting lower daytime R eco than the Reichstein method, which can be attributed to the Kok effect, i.e., the plant respiration being higher at night. We conclude that our approach is a good alternative for data-driven NEE partitioning and complements other partitioning methods. INDEX TERMSDeep state space models, net ecosystem exchange, NEE partitioning, time series forecasting

Causal hybrid modeling with double machine learning—applications in carbon flux modeling

“…Common approaches implement functional relationships based on physiology and estimate the fluxes using data-driven models [86][87][88][89][90]. Several hybrid-modeling approaches have recently been proposed modeling both fluxes with NNs [37,67,91].…”

Partitioning of Net Ecosystem Exchange Using Dynamic Mode Decomposition and Time Delay Embedding

“…The two CO 2 fluxes Reco and GPP are derived from NEE by applying partitioning methods. Recently deep learning-based methods have been proposed for modeling Reco dynamics [4,5] using EC measurement of night-time NEE when photosynthesis, and therefore GPP, is assumed to be 0. These approaches provide data-driven equation-free estimates of Reco with the flexibility to include other meteorological and biological drivers affecting Reco during the daytime to achieve the NEE partitioning task.…”

“…Recently, the capabilities of deep neural networks in learning complex and nonlinear dynamical models have been used for modeling Reco dynamics (Tramontana et al, 2020;Trifunov et al, 2021). These approaches provide data-driven equation-free estimates of Reco with the flexibility to include other meteorological and biological drivers affecting Reco.…”