We are excited to announce an upcoming FLUXNET-ECN Seminar/Workshop, a community event co-sponsored by the FLUXNET Early Career Network, AmeriFlux Management Project (AMP), and members of the FLUXNET communities. The workshop focuses on Knowledge-Guided Machine Learning (KGML) for Estimating Carbon Fluxes using Eddy Covariance Data: Seminar and Tutorial. Our invited speaker is Dr. Licheng Liu at the University of Minnesota.

This seminar will explore methods to open the ‘black box’ of machine learning by integrating scientific knowledge from mechanism-based models into advanced machine learning frameworks, known as Knowledge-Guided Machine Learning (KGML). The focus will be on utilizing eddy covariance data for accurate, efficient, and interpretable simulations of carbon cycles.

Tutorials will be provided based on the Nature Communications paper led by Dr. Liu (https://www.nature.com/articles/s41467-023-43860-5), along with its associated code. Participants are encouraged to review the paper and try the ‘five_steps_training’ code before the seminar.

Short Bio:
Dr. Licheng Liu is a senior research scientist leading the KGML division in the AI-CLIMATE Institute at the University of Minnesota. Dr. Liu’s research centers on enhancing our understanding of greenhouse gas (GHG) sources and sinks in agricultural and natural ecosystems, to explain their roles in climate change and provide actionable insights for mitigation strategies, by integrating advanced analytical tools such as process-based models and KGML, multi-source data from modern sensing techniques, and AI-accelerated optimization algorithms in decision making (https://bbe.umn.edu/people/licheng-liu).

Register for this webinar: https://lbnl.zoom.us/meeting/register/tJAldOugqj4uHNTMDM0L0Hll4E0fRVaEZrJQ