Two PhD positions were available in the Department of Computer Science and Engineering at Michigan State University, under the supervision of Dr. Pang-Ning Tan and Dr. Jiayu Zhou.

The positions were part of a Macrosystems Biology National Science Foundation funded interdisciplinary project — A macrosystems ecology framework for continental-scale prediction and understanding of lakes. The overarching goal of this research was to understand and predict nutrient patterns for continental US lakes using advanced machine learning approaches.

Project Scope

This NSF-funded project brought together machine learning, data mining, and macrosystems ecology to tackle large-scale environmental prediction problems. PhD students joining this effort would have contributed to developing novel computational methods for understanding complex ecological systems at a continental scale.

Doctoral research at the intersection of machine learning and macrosystems ecology offers a unique opportunity to develop scalable computational methods for understanding complex environmental systems. Students engaged in such interdisciplinary work learn to design algorithms that can process vast ecological datasets, uncover latent patterns in environmental observations, and build predictive models that operate across continental scales. The research often involves close collaboration with domain scientists, allowing computer science trainees to ground their algorithmic innovations in real-world scientific questions. This kind of training prepares graduates for careers at the boundary of data science and environmental research, where expertise in both machine learning and scientific inquiry is increasingly valued.

Graduate students working on machine learning for ecological applications gain hands-on experience with multi-task learning, sparse modeling, and temporal analysis techniques that are directly applicable to large-scale environmental data. These methodological skills translate well beyond ecology into biomedical informatics, healthcare analytics, and other data-intensive scientific domains. The collaborative nature of such projects, typically funded by interdisciplinary grants, fosters a research environment where students learn to communicate across disciplinary boundaries, present their work at both computer science and domain-specific conferences, and publish in journals spanning multiple fields. This breadth of training equips researchers to tackle some of the most pressing challenges in data-driven science.