Paper: AI-Powered Digital Twin

AI-Powered Digital Twin for Sustainable Campus Facility Management

Nikolaenko, Mikhail, Ming Tang, Aayush Kumar, and Sid Thatham. 2026. “AI-Powered Digital Twin for Sustainable Campus Facility Management” Architecture 6, no. 4: 205. https://doi.org/10.3390/architecture6040205

University campus buildings consume significant energy through chilled water (CHW) systems, yet facility and energy managers lack tools that connect sensor data to actionable, spatially grounded decisions without requiring programming expertise. We present BearcatAI, an end-to-end analytics platform developed at the University of Cincinnati (UC) that unifies machine learning demand prediction, a large language model (LLM) conversational interface, and an interactive 3D campus visualization derived from geographic information system (GIS) data. All models were trained and evaluated on 271 days of daily meter data collected across the UC building portfolio (June 2025–February 2026); ten years of monthly CHW records (July 2015–July 2025) provided long-term context only. An ensemble of XGBoost and Random Forest models achieves an in-sample 𝑅2=0.988, mean absolute percentage error (MAPE) =20.4% (inflated by near-zero winter readings), and normalized mean bias error =−0.3% on DAAP (College of Design, Architecture, Art, and Planning), the priority building identified by the UC utility engineering team. Beyond building-specific models, we introduce use-type models that pool buildings by functional category (Academic, Research, Administrative, Housing, Recreation, Medical) without any building-specific identity features. Leave-One-Building-Out (LOBO) cross-validation shows that the Research type model generalizes to unseen research buildings with median 𝑅2=0.911, and the Academic model achieves 𝑅2=0.918 on DAAP without having seen it during training, whereas medical and hospital types do not generalize, demonstrating the feasibility of functional type models as campus-scale benchmarking tools within the study dataset. A natural language interface powered by BearcatGPT, UC’s hosted instance of GPT-4.1, allows utility managers to query anomalies, request forecasts, and generate building charts through conversation. Anomalous buildings are automatically highlighted in a 3D campus model spanning UC Main Campus, Medical Campus, and Digital Futures. The results are limited to a single campus and observation period; user evaluation and a robotic inspection module under development remain future work.

Read more

paper in Computers, Environment and Urban Systems

Osoro, Ogutu B., Jingjing Li, Ming Tang, Xi Chen, Kelly Merrill, Lauren Forbes, Briana L. Simms, Paris Wheeler, Clementine Adeyemi, and Diego F. Cuadros. “Family Specific Spatial Borrowing in Multimodal Urban Reconstruction: A Leave-One-Neighborhood-Out Study of Cincinnati.” Computers, Environment and Urban Systems 132 (2027): 102541. https://doi.org/10.1016/j.compenvurbsys.2026.102541.

Family Specific Spatial Borrowing in Multimodal Urban Reconstruction: A Leave-One-Neighborhood-Out Study of Cincinnati.

Urban spatial models often assume that nearby borrowing improves prediction across target variables, but this assumption is rarely tested across distinct urban feature families within a city. We evaluate this question on a citywide hexagonal grid of Cincinnati, Ohio (2016 cells, 60 features in 14 feature families) using multimodal masked reconstruction. We compare four models spanning linear, local nonlinear, shared-gate graph, and selective-gate graph architectures under full leave-one-neighborhood-out evaluation across 50 neighborhoods, with primary summaries for the 36 neighborhoods having at least 20 cells. Median held-out-neighborhood R2 is the primary comparison metric. Cross-neighborhood transfer is family-specific, and no single borrowing strategy dominates. Ridge performs best for street structure, indicating that some spatially regular families are best reconstructed from local linear combinations. The local nonlinear masked autoencoder (MLP-MAE) holds the highest median for most families with positive transfer, though these differences are not statistically distinguishable from the graph models, indicating that local nonlinear multimodal fusion is often sufficient. Graph-based models help most clearly for topography, while the selective-gate graph model wins many individual neighborhood comparisons for several families despite lower medians, reflecting different error profiles. Graph models also produce more neighborhood-structured representations: contextual embeddings from the selective multimodal spatial autoencoder (SMSA) recover neighborhood structure better than raw principal components or local-only embeddings. Learned gates are stable across folds and provide interpretable diagnostics of context reliance, but not a universal ranking of borrowing regimes. These results show that the appropriate spatial borrowing strategy is target-specific rather than universal. For neighborhood-scale interpolation, imputation, and urban monitoring, one spatial modeling recipe can systematically misrepresent some feature families even within the same city.

Read more

paper in Frontiers

Differentiated memory and scientific cognition in AI research agents

Cuadros DF, Maiga A-A, Thatham S, Ortiz A, Powers-Fletcher M and Tang M (2026) Differentiated memory and scientific cognition in AI research agents. Front. Big Data 9:1916523. doi: 10.3389/fdata.2026.1916523

AI research agents increasingly support ideation, literature search, coding, experimental execution, analysis, and manuscript drafting across the scientific workflow. This progress advances automated discovery, but workflow automation is not scientific cognition. Scientific reasoning is cumulative and path-dependent: it depends on what a researcher has written, read, learned from critique, absorbed through experience, and used as habitual standards for judging novelty, rigor, feasibility, and significance. We propose Mnemo as a framework for modeling scientific cognition in AI research agents. First, scientific cognition may require differentiated memory, organized into distinct spaces for authored work, external reference, critique, experience, and judgment. Second, provenance should be treated not as passive metadata but as memory routing, because source origin helps determine cognitive function in reasoning. Third, new ideas may be better modeled as controlled collisions across memory spaces, filtered by judgment, rejection, and epistemic calibration, than as generic recombination from model priors. Mnemo motivates a research agenda for AI in science centered on routing fidelity, critique use, judgment alignment, rejection quality, and epistemic calibration.

paper in Environments Journal

Toward Sub-Sewershed Spatio-Temporal Wastewater Surveillance: A Critical Review and a Candidate Multimodal Foundation-Model Framework

Cuadros, Diego F., Xi Chen, and Ming Tang. 2026. “Toward Sub-Sewershed Spatio-Temporal Wastewater Surveillance: A Critical Review and a Candidate Multimodal Foundation-Model Framework” Environments 13, no. 7: 382. https://doi.org/10.3390/environments13070382

Wastewater-based epidemiology (WBE) has matured into a population-level surveillance complement with operational precedent in poliovirus environmental surveillance, institutionalised systems for SARS-CoV-2, and expanding evidence across respiratory pathogens, substance-use markers, and antimicrobial-resistance targets at uneven maturity. The unresolved problem is specific: sub-sewershed spatio-temporal inference under sewer-network and observational aggregation. Intra-catchment heterogeneity, hydraulic dynamics, and equity-relevant population differences can all be obscured by aggregate-scale modelling. Current artificial intelligence/machine learning (AI/ML) methods in WBE can be organised into four threads: temporal forecasting, spatial–statistical localisation, sewer-network and hydraulic transport, and cross-site transfer. These methods solve useful parts of the surveillance problem at the scales they target, but they do not yet supply transferable latent sub-sewershed representations under downstream aggregation. This review proposes a candidate multimodal foundation-model framework that treats place and time as jointly learnable entities, integrates a graph backbone over the sewer-network topology, incorporates physics-informed constraints, and embeds equity-conscious downstream validation as a design requirement. The framework is intended to make sub-sewershed hypotheses explicit, testable, uncertainty-bounded, and accountable to environmental-justice-relevant external validation. Whether those hypotheses survive empirical testing remains an open question.

Figure 1. The aggregation problem at the sub-sewershed scale.

Poster in Creativity & Cognition

VR as a Creative Medium for Immersive Storytelling: An Autobiographic Design Exploration

Bozhi Peng, Heekyoung Jung, Ming Tang, and Yoshiko Burke. 2026. VR as a Creative Medium for Immersive Storytelling: An Autobiographic Design Exploration. In Proceedings of the  Creativity & Cognition 2026 conference (C&C ’26,  London. UK. 2026). Association for Computing Machinery, New York, NY, USA, 1363–1370.  https://doi.org/10.1145/3803784.3816833

This project explores virtual reality (VR) as a creative medium for expressing personal memories through space, movement, and interaction, while evoking shared experiences. Using autobiographic and research through design approaches, three VR scenes were developed through iterative prototyping and first-person inquiry to investigate immersive storytelling. Guided by the framework of immersion, presence, and interactivity, the project examines how design decisions shape immersive experience in VR through the alignment of perception, embodied movement, and responsive interaction. The work demonstrates how personal memory can function as a generative resource for experiential storytelling rather than representational narration. It also reflects on the potential and limitations of autobiographic design as a method of creative inquiry in VR and identifies future directions for engaging collective and cultural memory through audience participation.

Besides the proceeding book, the publication is also included in the ACM Digital Library.