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

Reality Capture

Victory City

Metaverse of Simpson’s Victory City Reconstruct & Reimaging of Orville Simpson’s Vision of Urban Futures using AI

Ming Tang. $4500. Supported by SAID Simpson Urban Futures Grant Program. UC. 8. 2026-8. 2027

This project works on the AI-creation of an online Metaverse by reconstructing and reimaging Orville Simpson’s visionary “Victory City.” Using archival materials from the Simpson Collection—including drawings, paintings, and manuscripts—the project will generate digital interpretations of Simpson’s future city through AI-assisted visualization and 3D modeling. The platform will allow users to explore a multiplayer virtual city accessible through web browsers, mobile devices, and VR headsets. In addition to a virtual reconstruction of Victory City, the project will include a digital gallery presenting Simpson’s archival works and a digital installation at the Simpson Center, reintroducing Simpson’s ideas as a contemporary dialogue on sustainable urban futures.

The goal of this project is to translate Simpson’s visionary urban concepts into an interactive 3D digital environment that allows the public to experience and interpret his ideas spatially. Although Simpson’s online archive contains extensive drawings and models, these materials remain largely static. This project transforms them into an immersive platform where users can explore the spatial logic of Victory City. The project emphasis: 

  • AI-assisted visualization: generative AI tools will be used to produce architectural imagery, animations, and 3D models inspired by Simpson’s designs.
  • Construction of a Metaverse environment: a browser-based immersive environment will be developed to represent major elements of Victory City, including the central 102-story tower and the larger metropolitan system described in Simpson’s writings.

By Stephen Luo + AI. Victory City VIZ.

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.