Akila successfully defended on Monday, March 9, 2026

Throughout her time with us, Akila's dedicated contributions have made her an invaluable member of both the iHARP and UMBC communities. This significant achievement is a true testament to her scholarly rigor, hard work, and immense talent.

Congratulations, Akila, on this incredible milestone! We have been honored to witness your growth and look forward to your future successes. The entire iHARP community wishes you the very best as you embark on your next great adventure!

• Dr. Jianwu Wang, Chair/Advisor (UMBC)
• Dr. Vandana Janeja, Co-Chair (UMBC)
• Dr. Houbing Song (UMBC)
• Dr. James Foulds  (UMBC)
• Dr. Donald K Perovich (Dartmouth College)
• Dr. Nicole Schlegel (NOAA)

Rapid and accelerating Arctic climate change poses significant challenges for artificial intelligence (AI) systems, primarily due to severe data scarcity, inherent nonlinearities, and complex spatiotemporal interactions within the ocean–ice–atmosphere system. Conventional deep learning approaches rely heavily on large data volumes and often lack physical consistency. Consequently, purely data-driven models may produce physically implausible predictions and offer limited interpretability, thereby reducing their utility for scientific discovery and decision-making. To enable reliable and trustworthy sea ice prediction, physics-embedded learning architectures are required to leverage domain-specific priors that encode known physical laws, constraints, and causal mechanisms.

This dissertation presents a physics-integrated deep learning framework for modeling and analyzing the time-series evolution of Arctic sea ice. The proposed framework systematically combines physical knowledge with data-driven learning to enhance predictive performance, interpretability, and scientific validity. Specifically, this work introduces three complementary strategies for embedding physical constraints and governing principles directly into the learning process, each addressing a distinct scientific challenge in Arctic climate research.

First, a physics-informed deep learning model is developed for sea ice thickness prediction by explicitly incorporating thermodynamic constraints and governing energy-balance laws into the loss function. This approach ensures that model predictions respect known physical relationships while remaining flexible enough to learn from sparse observational data. Second, the dissertation introduces physics-encoded neural network architectures that embed established physical relationships directly into the model structure. These architectures enable the inference of latent physical parameters from noisy, incomplete proxy data, facilitating physically meaningful representation learning. Third, knowledge-guided temporal causal models are formulated to quantify the causal impact of sea ice variability on coupled oceanic and atmospheric processes. By incorporating time-varying treatments, causal structural constraints, and physics-based priors, these models provide interpretable estimates of causal effects that are consistent with established physical mechanisms rather than spurious correlations.

Across all evaluation settings, the results demonstrate that physics-integrated models consistently outperform conventional deep learning baselines. Overall, this work highlights the critical role of physics-integrated machine learning in advancing predictive capability, causal understanding, and trustworthiness in climate and Earth system modeling.

Thursday, March 12, 4:30-6:30 PM
The Commons, Skylight Room (3rd floor)

Are you pursuing a degree in science but are unsure about your career path? Want to learn what industries hire students with a degree in science and the skills that are sought by employers?

Attend the third annual CNMS Career Connection Social Event!

This is also a great opportunity to connect with potential recruiters hiring for their intern and full-time positions.

Registration Requested: Please RSVP on Handshake

Who should attend: Undergraduate and graduate students pursuing a degree in a science-related discipline. All majors/years welcomed!

Here's what you need to know:

• You will have the opportunity to connect and practice your networking skills with amazing UMBC alumni and employer recruiters in a relaxed, no-pressure setting.

• The format will be structured for "speed networking," so you'll know exactly when and who to approach. You will move around the room with a small group of your peers.

• The alumni and employers will represent various science-related industries. They are eager to get to know you!

• Food will be provided.

Through this, you will have a chance to ask questions to all alumni and employers in attendance and share your interests and ideas with them as well.

The Association of International Education Administrators (AIEA) has awarded UMBC’s Global Learning Lab one of two Innovative Excellence in Internationalization Awards. This award honors creative, replicable, and innovative initiatives that are critical to internationalization and require strong leadership to achieve. The AIEA commends the Global Learning Lab for reflecting UMBC’s commitment to justice, equity, diversity, and inclusion by fostering inclusive, cost-effective models that integrate global perspectives into the curriculum. 

The lab’s primary mission is to support faculty development in increasing student access to global learning opportunities. Through a cohort-based model, the lab brings faculty together for a series of workshops to develop best practices for integrating applied global learning into the curriculum. The initiative was originally launched as a pilot program by the Center for Global Engagement (CGE) and the College of Arts, Humanities, and Social Sciences (CAHSS) Dean’s Office in support of CAHSS faculty. In fall 2025, the lab was opened to all faculty with support from the Office of the Provost. Faculty who participate in this initiative produce concrete deliverables, such as course maps, faculty-led study abroad programs, and Collaborative Online International Learning (COIL) projects.

 “To date, 48 faculty members have participated across 27 unique departments ranging from biological sciences to visual arts to chemical, biochemical, and environmental engineering,” according to Provost Provost and Senior Vice President for Academic Affairs, Manfred van Dulmen‘s February campus newsletter. “Projects continue to positively impact the student experience and have included nine mapping initiatives, 12 COIL projects, and 27 study abroad programs.”

Developing an intercultural curriculum

To receive the Excellence in Internationalization Award, the Global Learning Lab had to be grounded in the principles of comprehensive internationalization—an inclusive process that impacts teaching, research, and service. It also had to align with at least two of UNESCO’s 17 Sustainable Development Goals, reflect the underlying principles of justice, equity, diversity, and inclusion in higher education, and serve as a replicable model for other institutions.

Cheryl North, clinical associate professor of education, and Takashi Yamashita, director and professor of sociology, anthropology, and public health (SAPH), are alumni of the inaugural cohort. They were both in the process of designing international university and community partnerships, in Germany and Japan, respectively, before the Global Learning Lab was launched. The lab provided technical and collegial support that bridged the gap between idea and implementation.

North, along with faculty at the University of Kassel in Germany, had established the foundations for a virtual classroom exchange for their education students, but had experienced technical and scheduling conflicts. “After participating in the Global Learning Lab, we learned to structure the collaboration effectively,” said North. “When we implemented these insights, UMBC students were able to share completed lessons and reflections, while the German students shared their process in the early stages of planning and implementation. Despite the scheduling differences, the exchange was successful, meaningful, and professionally enriching for everyone involved.”

The lab’s funding, technical training, and networking opportunities provided essential support that helped Yamashita develop the Global Health and Aging in Japan faculty-led study abroad program, which will launch in summer 2026. 

“Developing a study abroad program can often feel like an isolated effort for a single faculty member,” says Yamashita. “Having a dedicated technical support team from CGE, along with a community of UMBC colleagues to share unique ideas, made the process much more engaging. These interactions kept me inspired and motivated to bring this program to UMBC students.”

Campus-wide internationalization

UMBC faculty and staff at the AIEA award. (Image courtesy of CGE)

“The impact of the Global Learning Lab has been profound,” wrote Ana Oskoz, vice provost for faculty affairs, in her recommendation letter. “It is a shining example of innovative internationalization that prioritizes inclusivity, equity, and academic excellence.”

Faculty interested in participating in the Global Learning Lab are encouraged to follow the Faculty Affairs page on MyUMBC for notifications regarding future offerings.