Research Quick Takes

Jun 12, 2025

Research Prize: Metamaterials

PhD student Xiangbei Liu received third prize in the 2025 Neukom Outstanding Graduate Research Awards. Her research with Yan Li’s Group uses machine learning to efficiently design metamaterials with zero Poisson's ratio that maintain their shape in the transverse direction when stretched or compressed, making them ideal for soft robotics and biomedical devices.

Jun 05, 2025

Improving Healthcare Access

Professor Vikrant Vaze is a co-author of "A novel outreach approach for identification of familial hypercholesterolemia: Interview-based formative evaluation to improve healthcare access and quality" published in PEC Innovation. "This was a collaborative effort with folks from DH and Geisel, as well as Family Heart Foundation. The study is aimed at designing and evaluating direct outreach and referral to specialty care for patients with an elevated risk of FH identified through a machine learning model and expert review of the electronic record in a rural US health system. It's an excellent human-centered design thinking exercise and it yielded a great deal of success," said Vaze.

May 22, 2025

Cyber Defense x2

Professor Peter Chin's Learning, Intelligence + Singal Processing (LISP) lab had two papers accepted at the Reinforcement Learning Conference (RLC): "Hierarchical Multi-agent Reinforcement Learning for Cyber Network Defense" and "Quantitative Resilience Modeling for Autonomous Cyber Defense." Said Chin, "Both papers are part of the outcome of the four-year DARPA research project called CASTLE: Cyber Agents for Security Testing and Learning Environments that LISP lab has been working on to develop game-theoretic reinforcement learning agents that can outsmart potential cyber adversaries in an enterprise-level network."

May 22, 2025

Most Read of All Time

Professor Vikrant Vaze is a co-author of “Operational Research: methods and applications” which recently became the most read article of all time in the Journal of the Operational Research Society—the oldest journal in the field of operations research. "This is arguably the first prominent article to provide a comprehensive overview of the state-of-the-art in operations research [OR], from both a methodological and from an applications standpoint. It is meant to serve as the first point of reference for OR academics, researchers, students and practitioners alike," said Vaze.

May 01, 2025

Understanding AI Behavior

PhD students Clement Nyanhongo '17 Th'18 and Bruno Miranda Henrique, and Professor Gene Santos co-authored "Reward Distance Comparisons Under Transition Sparsity" published in Transactions on Machine Learning Research. "Traditional reward comparison methods rely on behavioral simulations, which can be costly and pose safety risks. Our method is specifically designed to operate in more realistic and practical settings, recognizing real-world constraints, and outperforms existing approaches across a range of domains," says Santos.

Apr 24, 2025

Tissue Engineering on Display

The Hixon Lab had a strong showing at the Society for Biomaterials 50th Annual Meeting & Exposition in Chicago earlier this month. PhD student Amritha Anup Th'23, MS-MD student Jewelia Durant, Jack Flaggert '26, Daniel Kang '25, Kristine Suritis '25, and Kate Wasacz '25all presented posters showcasing their work, and Emma Kerimo '25 was invited to deliver an oral presentation.

Apr 24, 2025

Machine Learning + Human Expertise

Professors Vikrant Vaze and Peter Chin are co-authors of "Implementation of a Machine Learning Model and Direct-to-Patient Outreach Program for Targeted Screening for Familial Hypercholesterolemia" published in Journal of Clinical Lipidology. "Machine learning by itself may not make a big difference," says Vaze. "The difference is what you do with the results. Ultimately, the combination of expert knowledge and careful operationalizing of machine learning can make a major practical impact."

Apr 17, 2025

Poster Session Award Winner

PhD student Prabhat Hegde was one of four to be recognized at the Guarini Graduate Student Poster Session for the clarity, accessibility, and engagement of his presentation titled, "Considering Retreat Can Lead to More Robust Adaptation Strategies in Nourishment-Dependent Coastal Communities." Each winner received a $200 prize.

Mar 27, 2025

Numerical Modeling Workshop

Professor Hélène Seroussi—along with Earth Sciences Professor Mathieu Morlighem, and Academic Cluster Initiative Program Coordinator Amy Flockton—organized and hosted the Ice-sheet and Sea-level System Model (ISSM) Workshop at Thayer. "The workshop was attended by about 60 participants and sponsored by Dartmouth's Changing Polar Regions Academic cluster and NASA's Earth Surface and Interior Program," said Seroussi.

Mar 20, 2025

Novel Piezo-Composites

PhD students Huan Zhao, Ya Tang, and Xiangbei Liu, undergraduate students Andrew Kim and Jace Henry, and Professor Yan Li co-authored "High-temperature piezoelectric composites with enhanced structural integrity" published in Ceramics International. "This article reports a novel piezoelectric composite that can increase the temperature limit to 500°C while maintaining good structural integrity and mechanical performance. This innovative piezo-composite opens new possibilities for sensing, energy harvesting, and actuation in high-temperature environments," said Li.

PhD candidates in the medical physics program

Mar 13, 2025

NEAAPM Symposium Winners

Jacob Sunnerberg and Conner Ubert, PhD candidates in the Medical Physics Education Program, respectively won first and second place at the New England chapter of the American Association of Medical Physicists Early Career Symposium. They were one of eight Dartmouth students and researchers to compete in the Early Investigator Competition.

Feb 27, 2025

Early Detection of Internal Bleeding

PhD student Navid Rashedi (pictured), Professor Ethan Murphy, Alexandra Hamlin '16 Th'17 Th'19, research associate Victor Borza, and Professors Jonathan Elliott, Ryan Halter, and Vikrant Vaze are co-authors of: "Detection of occult hemorrhage using multivariate non-invasive technologies" published in Physiological Measurement. "This work investigated machine learning to combine multiple technologies—electrical impedance and near infrared spectroscopy—to better detect internal bleeds in a porcine study. Internal bleeds are often not detectable until it's too late. This approach appears to detect them earlier and more accurately," said Murphy.