AI, fungi and raw enthusiasm

University of Idaho Coeur d’Alene computer science student Leif Huender proves that real-world discovery isn’t reserved for seasoned scholars.

Huender’s undergraduate research reveals how airborne fungal diseases spread through weather patterns while pioneering the innovative use of artificial intelligence in outbreak prediction.

Our research is the first to apply extended LSTM models to Valley Fever prediction. This opens new doors for public health planning and disease prevention. Leif Huender, computer science undergraduate researcher

As wildfires intensify worldwide, researchers are exploring the behaviors and health effects of fires in new ways. Huender — a first-generation college student who is concurrently enrolled at U of I Coeur d’Alene and North Idaho College — is part of a team developing AI-driven methods to predict disease outbreaks from wildfire smoke using long short-term memory (LSTM) models.

LSTM models are a type of artificial intelligence that can remember important information over time and forget irrelevant details, making them good at predicting what comes next in sequences, like in text or weather patterns.

“Using LSTM models, we’ve made a big step forward in predicting future outcomes,” Huender said. “These models are exceptional at recognizing complex patterns over time, even with limited data.”

Predicting Valley Fever

Valley Fever, a fungal disease common in the arid regions of California and Arizona, has long been linked to weather patterns, but predicting outbreaks has remained a challenge.

Huender’s undergraduate research explores alternative ways to forecast Valley Fever outbreaks using a new approach with AI.

With an INBRE fellowship working with Center for Intelligent Industrial Robotics Associate Director and Vandal alumna Mary Everett, Huender developed AI methods predicting agricultural outcomes in microclimates with limited weather data. He presented this work at the International Society of Precision Agriculture in July 2024.

“I realized the same techniques we used to predict crop yields could be applied to forecasting disease outbreaks,” Huender said. “Both problems involve analyzing complex environmental data to make real-world predictions. The LSTM models that worked for agriculture proved equally valuable for forecasting Valley Fever outbreaks based on climate conditions.”

In Fall 2025, Huender expanded this research, analyzing two decades of meteorological data from 48 California counties. He fine-tuned hundreds of AI models to make predictions that significantly outperformed traditional statistical methods that are unable to detect complex patterns and connections in data. The result is better predictions for complicated, time-based problems.

“Not only did we improve predictive accuracy by 38%, but we also pioneered the use of this AI architecture in epidemiological research,” Huender said. “To my knowledge, our research is the first to apply extended LSTM models to Valley Fever prediction. This opens new doors for public health planning and disease prevention.”

This Valley Fever research was recently accepted for publication by the Journal of Biomedical Informatics – a milestone that Huender calls validating.

“Learning about machine learning techniques in class is one thing, but applying it to solve real problems and have that work recognized by the scientific community is another,” Huender said. “Being published and presenting at an international conference as an undergraduate confirms that meaningful contributions to science can come from anywhere.”

Huender’s work is part of a growing profile of Valley Fever research happening at U of I. Leda Kobziar, professor of wildland fire science and pioneer in a new field of study called pyroaerobiology, studies how smoke transports microbes and particles, including the fungal spores that cause Valley Fever. Kobziar was instrumental in connecting the computer science team with dataset resources and collaborators to look at environmental data, Everett said.

“Dr. Kobziar’s research is really what started this project, and collaborating across disciplines is what made Leif’s work possible,” she said. “The computer science results can’t be interpreted without a domain expert, so this partnership is crucial to understanding the problem and coming to accurate results that we can make sense of as a team.”

Changing the game

Huender’s research opportunities were game-changing on a personal level, too. After dropping out of high school for academic and personal reasons, he worked construction for several years before applying to North Idaho College in 2021. There, he was selected for the Bridges to Baccalaureate program, which identifies students with research potential and connects them with mentors.

Through the program, he met John Shovic, computer science professor and director of the Coeur d’Alene-based Center for Intelligent Industrial Robotics, who immediately saw Huender’s potential.

“My enthusiasm must have been obvious because he had me start lab work weeks before my official start date,” Huender said.

Shovic said Huender’s journey highlights what’s possible when students seize the opportunities before them.

“What stood out to me about Leif was his raw enthusiasm for the project,” Shovic said. “He came in so full of ideas that it was hard to keep up with him, and his success in undergraduate research and publications shows the impact of passion combined with opportunity.”

Active discovery

Huender isn’t slowing down. His U of I Coeur d’Alene team is working on a third research publication that builds a comprehensive dataset for Valley Fever research, the first of its kind.

“This dataset is specifically designed for complex machine-learning modeling,” Huender said. “Releasing it alongside our next publication will give researchers access to high-quality data for their own investigations. This could significantly accelerate progress in understanding and predicting this disease.”

For Huender, undergraduate research transformed his education from passive learning to active discovery. His experience at U of I Coeur d’Alene exposed him to new machine learning techniques, faculty mentorship and the process of scientific publication.

“The experience helped me understand the daily reality of research work: the challenges, the iterations, the collaborative nature of science,” Huender said. “These insights can't be gained in a traditional classroom setting. Most importantly, it helped me discover my passion for applying computational methods to solve complex real-world problems.”

He is no stranger to solving actual problems. Huender and fellow U of I Coeur d’Alene student Andrea Knauff co-founded Disseminate, a nonprofit dedicated to providing rural students with the connective technology, educational resources and community support that Huender lacked as a young student to grow and thrive academically.

Huender and Knauff provide new and refurbished computers, build community networks to provide reliable, affordable internet to disadvantaged students, and distribute learning resources via USB drives to students without internet connectivity. Through Disseminate, one rural North Idaho family  received of a high-power computer that Huender rescued, refurbished and loaded with textbooks, e-books and video lessons for the family to use without internet.

“While my research might inspire some students, Disseminate creates immediate, tangible impact by opening digital doorways to knowledge,” Huender said. “We’re guaranteeing that curiosity isn’t limited by geography or economic circumstances — something that I believe is fundamental to educational equity.”

Article and photos by Megan Snodgrass, U of I Coeur d’Alene.

Published in April 2025.