Francis successfully defended on Thursday, July 16, 2026

Francis successfully defended his dissertation on Thursday, July 16, 2026. Francis's dedicated contributions have made him an important member of the iHARP and UMBC communities. This achievement is a true testament to his scholarly rigor and hard work.

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

_____________________________

Dissertation Title: Accurate Clustering of High-Dimensional Multivariate Spatiotemporal Data

Committee

• Dr. Jianwu Wang, Chair/Advisor, UMBC
• Dr. Vandana P. Janeja, Co-Advisor, UMBC
• Dr. James Foulds, UMBC
• Dr. Yiqun Xie,  University of Maryland, College Park.
• Dr. Aneesh Subramanian, University of Colorado Boulder

Abstract

The rapid growth of multidimensional multivariate spatiotemporal data from Earth observation systems, sensor networks, climate reanalysis products, and large- scale monitoring platforms has created unprecedented opportunities for understanding complex natural and human-driven processes. These datasets simultaneously vary across space, time, and multiple variables, enabling the discovery of hidden patterns, climate regimes, anomalies, and evolving system behaviors. However, clustering such data remains challenging due to high dimensionality, nonlinear interactions, spatial autocorrelation, long-range temporal dependencies, noise, missing values, nonstationarity, and multiscale structures. Traditional clustering approaches
primarily rely on distance-based or correlation-based similarities and often fail to capture the complex spatial, temporal, and causal mechanisms underlying these systems.

To address these challenges, this dissertation develops three novel deep clustering frameworks for multivariate spatiotemporal data. First, Hybrid Ensemble Deep Graph Temporal Clustering (HEDGTC) integrates homogeneous and heterogeneous ensemble clustering with a dual-consensus strategy and a Deep Graph Attention Autoencoder to improve clustering robustness, stability, and accuracy. By combining object co-occurrence consensus and non-negative matrix factorization consensus, HEDGTC effectively reduces noise and misclassification while preserving temporal and relational structures. 

Building on the foundation established by HEDGTC, we introduce the Bi-directional Temporal Graph Attention Transformer (B-TGAT), an end-to-end deep clustering framework for multivariate spatiotemporal data. The proposed architecture combines a ConvLSTM-based U-Net autoencoder for learning rich spatiotemporal representations, graph attention mechanisms for modeling spatial relationships, and a bi-directional transformer for capturing long-range temporal dependencies in both forward and backward directions. This integrated design enables B-TGAT to effectively learn complex spatial and temporal patterns from climate data. By jointly modeling local spatial interactions and long-term temporal dynamics, B-TGAT un- covers meaningful climate regimes, large-scale teleconnections, abrupt climate transitions, and extreme weather events. The learned latent representations improve cluster compactness, stability, and separation, leading to more accurate, robust, and interpretable clustering of multivariate spatiotemporal climate datasets. This unified framework provides a powerful solution for discovering hidden climate patterns that are difficult to identify using conventional clustering approaches. 

Recognizing that correlation-based representations alone may not reveal the true drivers of system evolution, this dissertation further proposes Causal Adversarial Subspace Clustering (CASC), a causality-aided deep clustering framework that transforms spatiotemporal regime discovery from a correlation-driven process into a causal-temporal learning paradigm. CASC integrates a U-Net-inspired adversarial autoencoder, stacked FAConvLSTM layers, graph attention-based self-expressive learning, and two novel objectives: Causal Subspace Preservation (CSP) Loss and Dynamic Temporal Subspace Evolution (DTSE) Loss. These mechanisms enable the model to discover clusters that are not only geometrically compact but also causally meaningful and temporally coherent. A Subspace-Aware Energy-Based TemporalDiscriminator further enhances clustering stability, interpretability, and robustness by evaluating latent representations according to cluster-specific subspace structures.
Extensive experiments on multiple real-world climate and environmental datasets demonstrate  that the proposed frameworks consistently outperform state-of-the-art traditional and deep clustering approaches across clustering quality, robustness, stability, and interpretability metrics. Collectively, the proposed methods establish a unified framework for learning hierarchical spatial, temporal, and causal representations from complex spatiotemporal data. The resulting models provide powerful tools for climate regime discovery, environmental monitoring, anomaly detection, and scientific understanding of dynamic Earth systems, while advancing the state of the art in deep unsupervised spatiotemporal clustering.

The Summer Undergraduate Research Festival (SURF) 2026 abstracts are due on Wednesday, July 22, 2026.  Please direct your student researchers to the SURF website at surf.umbc.edu for information on submitting their abstracts.  All students applying for oral Lightning Round talks must be available to attend two mandatory practices.

UMBC will host an IEEE Baltimore Technical and Professional Development Colloquium on Nov. 7, 2026 on Creativity in an Era of AI. Abstract submissions are due by August 31 for presentations, posters, and demonstrations in one of four tracks:

 • AI Applications in Biology and the (Bio)medical Field
 • AI Software Systems: Design, Engineering, and Deployment
 • AI Meeting Physical Reality
 • AI and the Future of Work: Skills, Talent, and Workforce Transformation

Get more information and register here.

Looking for housing or a roommate near UMBC? 🏠

SphereHub helps students connect with housing opportunities, sublets, available rooms, and potential roommates in one trusted place—completely free for students.

Whether you are searching for a place to live or have a room or sublet to share, SphereHub makes it easier to connect with the UMBC community.

Visit: https://www.sphere-hub.com

Scan. Match. Move in.

All interviews have been conducted; candidates who did not hear from us will be considered for other open positions.

The Graduate Student Association is seeking graduate student representatives to serve on the Grants Review Panel (GRP) for the 2026–2027 academic year.

The GRP is responsible for reviewing Professional Development grant and Research grant applications, helping ensure a fair, transparent, and timely allocation of GSA funding.

We are looking for:

• 2 representatives from CAHSS

• 2 representatives from CNMS

• 2 representatives from COEIT

📅 Position Start Date: July 27, 2026

Applications will be reviewed on a rolling basis, and interviews will begin immediately. Positions will be filled on a first-qualified, first-served basis, so we encourage interested students to apply as soon as possible.

This is a great opportunity to:

• Gain leadership and service experience

• Contribute to graduate student funding decisions

• Work closely with the GSA to support your graduate student community

• Earn a stipend for your time.

If you're interested in serving on the Grants Review Panel, submit your application today!

We look forward to welcoming our new GRP members!

The Graduate Student Association (GSA), in collaboration with SABSC, is currently working to revamp the Professional Development and Research Grant processes to make them more efficient, transparent, and user-friendly for graduate students.

We're excited to introduce several improvements, including:

• A simpler, more intuitive application form

• Clearer and easier-to-understand grant cycles and timelines

• The ability to apply up to 180 days before your travel, allowing approved funding to be used more effectively for planning and booking

To implement these updates, grant applications will be temporarily paused during the month of August while the new system is put into place.

What this means for you:

Students who submitted applications during the current cycle (through July 15th and, as a one-time exception, through July 24th) will receive their decisions during the first week of August, following the normal review timeline.

No new grant applications will be accepted during August, and there will be no September decision cycle, as we transition to the new process.

Applications will reopen on September 1 using the updated system.

We appreciate your patience as we make these improvements. Our goal is to create a grant process that is easier to navigate, more predictable, and better supports graduate students in planning their professional development and research activities.

Stay tuned for additional announcements with the new application form, updated guidelines, and grant cycle information. We can't wait to share these improvements with you!

Questions? Email gsagrants@umbc.edu

As employees in the University System of MD, this webinar is available to all UMBC employees; they also welcome spouses and partners!

USM MetLife will be hosting a webinar on Tuesday, 8/4/26, to provide employees with insights into insurance.

Many believe estate planning is only for the wealthy, but that’s a common misconception. Everybody can benefit from estate planning. 

In this workshop, find out why and learn about: 

· Setting and prioritizing your goals

· Today’s estate tax landscape and what it means for you

· How to avoid the ten common mistakes people make with their estates

Date and details below:

Estate Planning

• August 4, 2026 11:00 AM – 12:00 PM EDT

Click here to register for the session

Login instructions will be sent upon registry.

Questions? Reach out to hrbenefits@umbc.edu

Discover pianos, digital pianos and orchestral instruments offered at significant discounts from new retail pricing.

Most are less than one year old, have 5-10-year service contracts. No-interest financing and delivery is available.

Join us Jul 30–Aug 1, 2026 at University of Maryland, Baltimore County!

Learn more here: https://www.rockleyfamilyfoundation.org/umbc/

Check out the May/June edition of our monthly newsletter for updates on students, faculty, and alumni! 

April 2026 Newsletter

Affected Service: DocuSign

Time of Status Update: 12:30 PM | July 16, 2026

Original Message: Service Alert: DocuSign Temporarily Unavailable

Update: Please be advised that issues impacting DocuSign have been resolved. DocuSign is functioning as normal. 

If you need assistance, please contact the Technology Support Center at UMBC Help or 410-455-3838.

Thank you for your patience and understanding.