Inferring Parameters in a Complex Land Surface Model by Combining Data Assimilation and Machine Learning

Journal of Advances in Modeling Earth Systems, vol. 17

Abstract

Abstract Complex Land Surface Models (LSMs) rely on a plethora of parameters. These parameters and the associated process formulations are often poorly constrained, which hampers reliable predictions of ecosystem dynamics and climate feedbacks. Robust and uncertainty‐aware parameter estimation with observations is complicated by, for example, the high dimensionality of the model parameter space and the computational cost of LSM simulations. Herein, we adapt a novel Bayesian data assimilation (DA) and machine learning framework termed “calibrate, emulate, sample” (CES) to infer parameters in a widely‐used LSM coupled with a demographic vegetation model (CLM‐FATES). First, an iterative ensemble Kalman smoother provides an initial estimate of the posterior distribution (“calibrate”). Subsequently, a machine‐learning‐based emulator is trained on the resulting model‐observation mismatches to predict outcomes for unseen parameter combinations (“emulate”). Finally, this emulator replaces CLM‐FATES simulations in an adaptive Markov Chain Monte Carlo approach enabling computationally feasible posterior sampling with enhanced uncertainty quantification (“sample”). We test our implementation with synthetic and real observations representing a boreal forest site in southern Finland. We estimate a total of six plant‐functional‐type‐specific photosynthetic parameters by assimilating evapotranspiration (ET) and gross primary production (GPP) flux data. CES provided the best estimates of the synthetic truth parameters when compared to data‐blind emulator sampling designs while all approaches reduced model‐observation errors compared to a default parameter simulation (GPP: % to %, ET: % to %). Although errors were also consistently reduced with real data, comparing the emulator designs was less conclusive, which we mainly attribute to equifinality, structural uncertainty within CLM‐FATES, and/or unknown errors in the data that are not accounted for.

Authors 8

1. Lasse Torben Keetz corresponding

   University of Oslo

   Affiliation as printed

   Department of Geosciences University of Oslo Oslo Norway

   Natural History Museum University of Oslo Oslo Norway

2. Kristoffer Aalstad

   University of Oslo

   Affiliation as printed

   Department of Geosciences University of Oslo Oslo Norway

3. Rosie A. Fisher

   CICERO Center for International Climate Research

   Affiliation as printed

   CICERO Center for International Climate Research Oslo Norway

4. Christian Poppe Terán Aachen Faculty of Georesources and Materials Engineering Rheinisch‐Westfälische Technische Hochschule (RWTH) Aachen Germany

   Forschungszentrum Jülich · RWTH Aachen University

   Affiliation as printed

   Faculty of Georesources and Materials Engineering Rheinisch‐Westfälische Technische Hochschule (RWTH) Aachen Germany

   Institute of Bio‐ and Geosciences: Agrosphere (IBG‐3) Research Centre Jülich Jülich Germany

5. Bibi S. Naz

   Forschungszentrum Jülich

   Affiliation as printed

   Institute of Bio‐ and Geosciences: Agrosphere (IBG‐3) Research Centre Jülich Jülich Germany

6. Norbert Pirk

   University of Oslo

   Affiliation as printed

   Department of Geosciences University of Oslo Oslo Norway

7. Yeliz A. Yılmaz

   University of Oslo

   Affiliation as printed

   Department of Geosciences University of Oslo Oslo Norway

8. Olav Skarpaas

   University of Oslo

   Affiliation as printed

   Natural History Museum University of Oslo Oslo Norway