Artificial intelligence, or AI, the groundbreaking technology that mimics human intelligence is dominating news cycles lately, and it holds the potential to save lives through improved weather prediction.
Haonan Chen, assistant professor of Electrical and Computer Engineering at Colorado State University, is at the center of AI research. He recently received the National Science Foundation CAREER award – NSF’s most prestigious honor for early-career faculty – to harness the strength of AI to transform radar remote sensing and weather forecasting.
“AI is a powerful tool for untangling meteorological phenomena,” said Chen.
AI meets radar data
Chen’s project builds on the ECE department’s decades-long legacy in radars and remote sensing. With proven success in leveraging AI to predict the initiation of fast-evolving storms, the $646,000 award will help him take his research to the next level.
Chen is developing a suite of AI models that draw on data from radar observations of clouds and precipitation to improve the accuracy of short- and long-term weather predictions.
Like human intelligence, these models can think critically to solve problems, make decisions, and increase productivity. They are smart enough to learn the internal dynamics of a storm and how it is changing in four dimensions – and the resulting insights enable faster, more accurate detection, classification, and estimation of future weather events.
Chen’s methodologies could one day generate forecasts that offer the public unparalleled specificity, such as a storm’s precise street location, its start and end times, and precipitation amounts.
Chen’s proposed approach is also highly adaptable, meaning it could be applied to radar networks all over the world to improve forecasting. “Adaptability is important because what might work here in Colorado algorithm-wise may not work in Texas,” said Chen.
Engaging future generations
As part of the CAREER award, Chen will launch a new outreach program with high schools in Northern Colorado to enhance STEM education and broaden participation in AI and meteorology fields. With a focus on historically underserved populations, he has developed instructional kits and field trips designed to introduce students to weather observations and AI applications.
