Articles | Volume 15, issue 7
https://doi.org/10.5194/gmd-15-2839-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-15-2839-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Development and technical paper
| 
07 Apr 2022
Development and technical paper |
| 07 Apr 2022
| 07 Apr 2022
KGML-ag: a modeling framework of knowledge-guided machine learning to simulate agroecosystems: a case study of estimating N2O emission using data from mesocosm experiments
Licheng Liu
Department of Bioproducts and Biosystems Engineering, University of Minnesota, Saint Paul, MN 55108, USA
Shaoming Xu
Department of Computer Science and Engineering, University of Minnesota, Minneapolis, MN 55455, USA
Jinyun Tang
Climate and Ecosystem Sciences Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA
Kaiyu Guan
Agroecosystem Sustainability Center, Institute for Sustainability, Energy, and Environment, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
Department of Natural Resources and Environmental Sciences, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
Timothy J. Griffis
Department of Soil, Water, and Climate, University of Minnesota, Saint Paul, MN 55108, USA
Matthew D. Erickson
Department of Soil, Water, and Climate, University of Minnesota, Saint Paul, MN 55108, USA
Alexander L. Frie
Department of Soil, Water, and Climate, University of Minnesota, Saint Paul, MN 55108, USA
Xiaowei Jia
Department of Computer Science, University of Pittsburgh, Pittsburgh, PA 15260, USA
Taegon Kim
Department of Bioproducts and Biosystems Engineering, University of Minnesota, Saint Paul, MN 55108, USA
Department of Smart Farm, Jeonbuk National University, Jeonju, Jeollabuk-do, 54896, Republic of Korea
Lee T. Miller
Department of Soil, Water, and Climate, University of Minnesota, Saint Paul, MN 55108, USA
Bin Peng
Agroecosystem Sustainability Center, Institute for Sustainability, Energy, and Environment, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
Department of Natural Resources and Environmental Sciences, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
Shaowei Wu
School of Physics and Astronomy, University of Minnesota, Minneapolis, MN 55455, USA
Yufeng Yang
Department of Bioproducts and Biosystems Engineering, University of Minnesota, Saint Paul, MN 55108, USA
Wang Zhou
Agroecosystem Sustainability Center, Institute for Sustainability, Energy, and Environment, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
Department of Natural Resources and Environmental Sciences, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
Vipin Kumar
Department of Computer Science and Engineering, University of Minnesota, Minneapolis, MN 55455, USA
Zhenong Jin
CORRESPONDING AUTHOR
Department of Bioproducts and Biosystems Engineering, University of Minnesota, Saint Paul, MN 55108, USA
Data sets
Code and data for "KGML-ag: A Modeling Framework of Knowledge-Guided Machine Learning to Simulate Agroecosystems: A Case Study of Estimating N2O Emission using Data from Mesocosm Experiments " Licheng Liu and Zhenong Jin https://doi.org/10.5281/zenodo.5504533
Short summary
By incorporating the domain knowledge into a machine learning model, KGML-ag overcomes the well-known limitations of process-based models due to insufficient representations and constraints, and unlocks the “black box” of machine learning models. Therefore, KGML-ag can outperform existing approaches on capturing the hot moment and complex dynamics of N2O flux. This study will be a critical reference for the new generation of modeling paradigm for biogeochemistry and other geoscience processes.
By incorporating the domain knowledge into a machine learning model, KGML-ag overcomes the...
