Constrained hybrid modelling to predict microbial dynamics and organic matter turnover in soil systems

Paul Collart, Juergen Gall, Andrea Schnepf, Holger Pagel, Lars Doorenbos
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:21241-21256, 2026.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-collart26a, title = {Constrained hybrid modelling to predict microbial dynamics and organic matter turnover in soil systems}, author = {Collart, Paul and Gall, Juergen and Schnepf, Andrea and Pagel, Holger and Doorenbos, Lars}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {21241--21256}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/collart26a/collart26a.pdf}, url = {https://proceedings.mlr.press/v306/collart26a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Constrained hybrid modelling to predict microbial dynamics and organic matter turnover in soil systems %A Paul Collart %A Juergen Gall %A Andrea Schnepf %A Holger Pagel %A Lars Doorenbos %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-collart26a %I PMLR %P 21241--21256 %U https://proceedings.mlr.press/v306/collart26a.html %V 306 %X 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.
APA
Collart, P., Gall, J., Schnepf, A., Pagel, H. & Doorenbos, L.. (2026). Constrained hybrid modelling to predict microbial dynamics and organic matter turnover in soil systems. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:21241-21256 Available from https://proceedings.mlr.press/v306/collart26a.html.

Related Material