Guang Lin to Lead Purdue’s Role in National Scientific Machine Learning Initiative
03-05-2026
When researchers set out to answer some of science’s toughest questions, the data can be overwhelming. A new national effort aims to change that by weaving artificial intelligence directly into the fabric of scientific discovery - and Purdue Mathematics is playing a key role.
Purdue University has joined the Learning Accelerated Domain Sciences (LEADS) Institute, a multi-institution collaboration funded by the U.S. Department of Energy. Supported through the Scientific Discovery through Advanced Computing (SciDAC) program, the five-year initiative is designed to transform how researchers apply artificial intelligence to complex scientific challenges.
The LEADS Institute is led by Pacific Northwest National Laboratory and brings together 14 partners, including nine universities and five national laboratories. Researchers across disciplines - including energy systems, materials science and computational chemistry - will collaborate to embed scientific machine learning, or SciML, into domain-specific research problems.
SciML integrates artificial intelligence with large-scale scientific computing. By learning patterns from data and combining them with established physical models, SciML can accelerate simulations, improve predictions and uncover relationships that may be difficult to detect using traditional computational approaches alone. The approach is particularly valuable for problems that involve complex, multiscale systems and massive data sets.
At Purdue, the project includes funding support for Guang Lin, the Moses Cobb Stevens Professor of Mathematical Sciences and Mechanical Engineering. Lin’s research group will focus on developing scalable algorithms and software tools that can be adapted to a range of scientific applications.
“We’re developing a suite of scalable algorithms and software tools designed to create custom scientific machine learning solutions capable of addressing a wide range of challenges,” Lin said.
By building flexible tools that can be tailored to specific research needs, the team aims to make advanced machine learning methods more accessible and reliable for scientists working in high-performance computing environments.
Through Purdue’s participation in the LEADS Institute, faculty and collaborators in mathematical sciences will contribute foundational methods that strengthen the connection between mathematics, computation and real-world scientific discovery — helping ensure that artificial intelligence is not just an add-on, but an integrated and trusted partner in the scientific process.
About the Mathematics Department at Purdue University
The Department of Mathematics is one of seven departments making up Purdue's College of Science. The Department has an international reputation as an outstanding center for mathematical research and education. Over 70 professors are actively involved in research in many areas of mathematics, including visiting scholars and through a vibrant graduate program. The Department offers Bachelor of Science, Master of Science and Doctor of Philosophy degrees. The department is located in the Math Building at 150 N. University Street in West Lafayette, Indiana. Learn more at math.purdue.edu.
Written by: Alisha Willett, Communications Specialist, amwillet@purdue.edu
Contributors: Guang Lin, guanglin@purdue.edu