GHGs going down

A team of researchers led by the University of Minnesota has significantly improved the performance of numerical predictions for agricultural nitrous oxide emissions. The first-of-its-kind knowledge-guided machine learning (ML) model is said to be 1 000 times faster than current systems and could significantly reduce greenhouse gas (GHG) emissions from agriculture.

The research was recently published in Geoscientific Model Development, a not-for-profit international scientific journal focused on numerical models of the earth. Researchers involved were from the University of Minnesota, the University of Illinois at Urbana-Champaign, Lawrence Berkeley National Laboratory, and the University of Pittsburgh.

Nitrous oxide is not as well-known as other GHGs like carbon dioxide and methane, but in reality, it is about 300 times more powerful than carbon dioxide in trapping heat in the atmosphere.

Human-induced nitrous oxide emissions (mainly from agricultural synthetic fertiliser and cattle manure) have grown by at least 30% over the past four decades. “There’s a pressing need to shut off the valve as quickly as possible, but you can’t manage what you can’t measure,” says Licheng Liu, the lead author of the study and research scientist from the University of Minnesota’s Digital Agriculture Group in the Department of Bioproducts and Biosystems Engineering.

Estimating nitrous oxide emitted from cropland is an extremely difficult task because the related biogeochemical reactions involve complex interactions with soil, climate, crop, and human management practises – all of which are hard to quantify. Although scientists have come up with different ways to estimate nitrous oxide emission from cropland, most existing solutions are either too inaccurate (when using complex computational models with physical, chemical, and biological rules), or too expensive (when deploying sophisticated instruments in the field).

In this new study, researchers developed a first-of-its-kind knowledge-guided ML model for agroecosystems, called KGML-ag. Machine learning is a type of artificial intelligence that allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so. Previous ML models have been criticised, however, for being a “black-box” where scientists can’t explain what happens between inputs and outputs. Now, scientists have developed a new generation of methods that integrates scientific knowledge into ML to unpack the “black-box”.

KGML-ag was constructed using a special procedure that incorporates the knowledge learned from an advanced agroecosystem computational model, called ecosys, to design and train a ML model. In small, real-world observations, the KGML-ag turns out to be much more accurate than both ecosys and pure ML models, as well as 1 000 times faster than previous computational models.

“This is the first-of-its-kind journey with ups and downs because there’s almost no literature to tell us how to develop a knowledge-guided machine learning model that can handle the many interactive processes in the soil, and we’re so glad things worked out,” says Liu.

One unique feature of KGML-ag is that it goes beyond most ML methods by explicitly representing many less obvious variables related to nitrous oxide production and emission. It also captures the complex causal relationship among inputs, outputs, and other complex intermediate variables.

“Knowing these intermediate variables, such as soil water content, oxygen level, and soil nitrate content, are (sic) very important because they inform drivers of nitrous oxide emissions, and give us possibilities to reduce nitrous oxide,” says corresponding author Zhenong Jin, a University of Minnesota assistant professor in the Department of Bioproducts and Biosystems Engineering who also leads the Digital Agriculture Group.

The development of the KGML-ag was inspired in part by pioneering research on knowledge-guided ML in environmental systems led by Vipin Kumar, a University of Minnesota Regents Professor in the Department of Computer Science and Engineering. This research includes studies for lake temperature and streamflow predictions.

“This is another success story of computer scientists working closely with experts in agriculture and the environment to better protect our earth,” Kumar points out. “This new effort will further enhance existing knowledge-based machine learning activities that the University of Minnesota is currently leading nationally.”