Constrained hybrid modelling to predict microbial dynamics and organic matter turnover in soil systems
For soil scientists and climate modelers, this provides a novel way to integrate genomic data into process-based models to improve predictions of carbon cycling, though the evaluation is limited to synthetic and small real datasets.
This work introduces a hybrid modeling framework that uses neural networks to predict biokinetic parameters of a process-based soil organic matter turnover model from metagenome-inferred functional traits, integrating ecological constraints. The method outperforms baselines on synthetic and real data, effectively learning dynamics of unmeasurable components even with small training datasets.
Soil microorganisms control organic matter cycling and largely determine how soil systems can cope with and mitigate climate change and environmental threats. Representing microbial dynamics in process-based soil models is therefore critical to predict carbon cycling in soils, albeit highly challenging to inform from data. One promising approach to improve their parametrisation is the integration of genomic data, yet modelling the complex and unknown relationship between genomes and the processes the microbes are driving is an unsolved problem. In this work, we present the first hybrid modeling framework for deriving biokinetic parameter values of a process-based soil organic matter turnover model from metagenome-inferred functional traits based on DNA sequencing data. Our model predicts biokinetic parameters of the process-based model from genomic trait data with a neural network and integrates constraints from ecological theory and literature to ensure realistic behavior, even of non-observed state variables. We evaluate our method on synthetic genomic trait datasets of varying complexity and on real data, showing that our approach improves performance over multiple baselines and learns the dynamics of unmeasurable components of the process-based model effectively, even for small training datasets.