Machine learning enables scalable optimisation of agroecosystem management

Reducing greenhouse gas emissions from agriculture while maintaining crop yield and soil health requires an improved management of thousands of fields. However, running traditional process-based crop models for this many fields is both time-consuming and computationally intensive, making it impractical on a large scale. Meshach Ojo Aderele's PhD tackled this bottleneck head-on. He developed a machine learning surrogate of the process-based modelling framework LandscapeDNDC called Machine Learning LandscapeDNDC (mLDNDC) to predict nitrous oxide emissions, nitrate leaching, crop yield and changes in soil organic carbon. mLDNDC enabled an optimisation approach to be taken across fields covering 90% of Danish croplands. This approach found optimal management options that reduced nitrous oxide emissions and nitrate leaching while improving crop yields and soil organic carbon stock in over 60% of fields. This research advances the development of machine learning methods for implementing sustainable agricultural management on a national scale. It gives policymakers and farm advisors a tool with which to test strategies in practice rather than just in theory.

The PhD study was completed at the Center for Landscape Research in Sustainable Agricultural Futures (Land-CRAFT), Department of Agroecology, Faculty of Technical Sciences, Aarhus University.

This summary was prepared by the PhD student.

Time: October 23, 2026. 1PM
Place: Room 230, Building 1171, Ole Worms Allé 3, 8000 Aarhus
Title of PhD thesis: Integrating Machine Learning into Process-Based Modelling to Identify GHG Mitigation Potentials of Cropping Systems in Denmark
Contact information: Meshach O. Aderele, e-mail: meshach.aderele@agro.au.dk, tel.: +45 50387058
Members of the assessment committee:
Professor Masahiro Ryo, Leibniz Centre for Agricultural Landscape Research (ZALF), Germany
Research Director Catherine Hénault, Department of Environment and Agronomy, French National Institute for Agriculture, France
Senior researcher Fiona Hay, Department of Agroecology, Aarhus University, Denmark
Main Supervisor: Professor Dr. Klaus Butterbach-Bahl, Department of Agroecology, Center for Landscape Research in Sustainable Agricultural Futures (Land-CRAFT), Aarhus University, Denmark.
Co-supervisor: Dr. Jaber Rahimi, Institute of Meteorology and Climate Research, Atmospheric Environmental Research (IMK-IFU), Karlsruhe Institute of Technology (KIT), Garmisch-Partenkirchen, Germany.
Language: The PhD dissertation will be defended in English

The defence is public.
The PhD thesis is available for reading at the Graduate School of Technical Sciences/GSTS, Ny Munkegade 120, building 1521, 8000 Aarhus C.