MSU Ph.D. Student Uses AI to Help Farmers Boost Crop Yields

Artificial intelligence has made its way into Montana’s agriculture fields, thanks to a doctoral student from Montana State University’s Gianforte School of Computing. Giorgio Morales, a Ph.D. candidate originally from Peru, is utilizing AI to help farmers improve crop yields while reducing the need for fertilizers. Morales is applying AI to analyze the variables that affect farming, providing farmers with data-driven insights that can enhance profitability and precision in the field.

Precision Agriculture and AI

While to the untrained eye, one field of winter wheat might look similar to another, Morales’ data reveals a different story. Using AI, he can detect significant changes in soil conditions and other variables within 10 meters. By analyzing thousands of data points, Morales aims to help farmers optimize their resource usage—specifically water, fertilizer, and seed—on a highly localized scale.

Morales is focused on creating AI methods that analyze how various factors—such as soil nutrients, nitrates, humidity, and precipitation—combine to impact crop yield. This work is part of a broader approach known as precision agriculture, where cutting-edge technologies are integrated into farming systems to enhance efficiency and output.

"We can collect data from the soil, and also we can use aerial and satellite images to monitor the fields. All of that data can be combined to understand the behavior of the fields themselves," Morales explained. The detailed insights provided by AI enable farmers to make better-informed decisions throughout the growing season, predicting what will happen during the harvest and minimizing guesswork.

The Role of Neural Symbolic Regression

At the core of Morales’ research is a technique called neural symbolic regression, a subset of AI that transforms large datasets into adaptable mathematical functions. This process allows AI models to adapt equations that can predict various outcomes, from crop yield to resource needs.

"In the history of scientific discovery, it took a lot of trial and error to obtain mathematical laws that explain certain phenomena, but they were limited to very specific situations," said Morales. "But if we have data and observations about the world, is there a way to simply train a model using artificial intelligence to tell us this is the equation that explains the phenomenon that you're observing?"

Morales’ goal is to apply these models to a range of industries beyond farming, making his work adaptable to various sectors where data-driven decision-making is crucial.

AI Across Montana State University

Montana State University is actively involved in several AI and machine learning projects. John Sheppard, Distinguished Professor of Computer Science and Morales’ Ph.D. advisor, highlighted MSU's work in areas beyond agriculture. For example, MSU researchers are working with the U.S. Navy to develop risk-based predictive maintenance for aircrafts and using AI to assess wildfire risks using a program called, SMART FireS, which optimizes the location & extent of the fires, in collaboration with the University of Montana.

Recognizing Morales’ Contributions

During his time at Montana State, Morales has authored 11 papers and co-authored three others. His recent peer-reviewed paper was presented at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases in Vilnius, Lithuania, marking another milestone in his academic career.

"The fact that different communities and groups are recognizing Giorgio’s contributions is a clear indication of the quality and potential impact of his research," said Sheppard. "There is no doubt that to succeed in the AI space requires working hard, and Giorgio does that. There is no doubt that he has the inspiration to motivate and drive that hard work."