Abstract
Abstract. Accurate model representation of land–atmosphere carbon fluxes is essential for climate projections. However, the exact responses of carbon cycle processes to climatic drivers often remain uncertain. Presently, knowledge derived from experiments, complemented by a steadily evolving body of mechanistic theory, provides the main basis for developing such models. The strongly increasing availability of measurements may facilitate new ways of identifying suitable model structures using machine learning. Here, we explore the potential of gene expression programming (GEP) to derive relevant model formulations based solely on the signals present in data by automatically applying various mathematical transformations to potential predictors and repeatedly evolving the resulting model structures. In contrast to most other machine learning regression techniques, the GEP approach generates readable models that allow for prediction and possibly for interpretation. Our study is based on two cases: artificially generated data and real observations. Simulations based on artificial data show that GEP is successful in identifying prescribed functions, with the prediction capacity of the models comparable to four state-of-the-art machine learning methods (random forests, support vector machines, artificial neural networks, and kernel ridge regressions). Based on real observations we explore the responses of the different components of terrestrial respiration at an oak forest in south-eastern England. We find that the GEP-retrieved models are often better in prediction than some established respiration models. Based on their structures, we find previously unconsidered exponential dependencies of respiration on seasonal ecosystem carbon assimilation and water dynamics. We noticed that the GEP models are only partly portable across respiration components, the identification of a general terrestrial respiration model possibly prevented by equifinality issues. Overall, GEP is a promising tool for uncovering new model structures for terrestrial ecology in the data-rich era, complementing more traditional modelling approaches.
Highlights
IntroductionI. Ilie et al.: Reverse engineering model structures for soil and ecosystem respiration: the potential of gene expression programming (GEP) quantitative description of the terrestrial carbon cycle (Bonan, 2008; Heimann and Reichstein, 2008; Luo et al, 2015)
One prerequisite to understand and anticipate the global consequences of anthropogenic climate change is an accuratePublished by Copernicus Publications on behalf of the European Geosciences Union.I
To investigate the capacity of gene expression programming (GEP) to reconstruct a simple model used in the ecology field as well, we introduced as well an artificial test for the “Q10” model that is used in the field for simulating the response of ecosystem respiration to change in air temperature of 10 ◦C at a reference temperature of 15 ◦C
Summary
I. Ilie et al.: Reverse engineering model structures for soil and ecosystem respiration: the potential of GEP quantitative description of the terrestrial carbon cycle (Bonan, 2008; Heimann and Reichstein, 2008; Luo et al, 2015). Peng et al, 2014), often referred to as “terrestrial ecosystem respiration” (Reco), varies across the scientific literature and existing global models. This is partly because Reco does not originate from a single process but is the sum of fluxes from different autotrophic and heterotrophic respiration processes that operate across different temporal and spatial scales and compartments (e.g. soil depths). In the rest of the paper we use the term “model” as an equivalent of “response functions”, i.e. some analytic description of how environmental drivers influence ecosystem fluxes
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
