Posts

paper in Frontiers

/in /by

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.

DOE Award: Genesis Mission

/in , /by

 I am very excited to share that UC grant proposal, “AI-Enabled Prediction of Coupled Hydrologic and Biogeochemical Processes in Heterogeneous Subsurface Systems,” has been selected for the U.S. Department of Energy’s initiative to accelerate scientific breakthroughs through artificial intelligence. 

DOE Phase 1: The Genesis Mission: Transforming Science and Energy with AI.
Award Amount: $500,000
Project Period: 09/01/2026–05/31/2027
PI: Reza Soltanian, Co-I: Ming Tang
Partner Institutions: New Mexico State University (NMSU), Pacific Northwest National Laboratory (PNNL), and Certerra Subsurface Imaging.

Quoted from UC News: UC selected for federal initiative to use AI to advance scientific discovery. Project will develop new workflows for energy and environmental applications

The University of Cincinnati has been selected to participate in the U.S. Department of Energy’s new national initiative designed to accelerate scientific discovery through artificial intelligence. 

Led by Reza Soltanian, professor of subsurface energy and hydrogeology in UC’s Department of Geosciences, the multidisciplinary project will develop next-generation AI-enabled scientific workflows and digital twins that integrate geological information, advanced geophysical imaging, field observations, physics-based simulations and AI surrogate models to characterize and predict complex subsurface systems.

The UC-led team brings together expertise in hydrogeology, hydrobiogeochemistry, geophysics, artificial intelligence, numerical and surrogate modeling, advanced subsurface imaging and extended reality. The collaboration includes Ming Tang, professor in UC’s School of Architecture and Interior Design and director of the Extended Reality Lab at UC Digital Futures, along with researchers from Pacific Northwest National Laboratory, New Mexico State University and industry partner Certerra Subsurface Imaging.

“The Department of Energy’s selection of this project reflects the strength of UC’s growing artificial intelligence ecosystem,“ Interim Vice President for Research Frank Gerner said.

“Through investments in initiatives such as Digital Futures and the Advanced Research Computing Center, we have created an environment where researchers can combine expertise in AI, data science and domain-specific scholarship to address complex challenges. Professor Soltanian and Professor Tang’s work demonstrate how these capabilities are advancing scientific discovery in ways that can have lasting impact on our energy and environmental future.“

 

paper in Environments Journal

/in , /by

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.

Housing Studio

/in , /by

2026. Housing Studio. 

SAID, DAAP, UC

This studio will focus on a large-scale housing project on one of two linear sites in Cincinnati. The proposal centers on a 100-unit dense housing intervention integrated with shared amenities serving both residents and the surrounding urban community. Rather than creating a singular tower or landmark, the studio will explore low-rise, high-density housing strategies organized as a continuous “housing-scape” — a mat-building or field-condition approach to multiple dwelling units (MDUs).
In this studio, AI is explored not only as a visualization tool, but also as an analytical design agent for evaluating solar exposure, wind, noise, daylighting, and carbon-neutral strategies during the early stages of design. AI is also used to generate conceptual sketch models that support rapid design exploration and iteration.
 
 

Re-storying Fort Ancient

/in /by

Re-storying Fort Ancient: An AI-Augmented Digital Twin Installation for Indigenous Earthwork
PI: Ming Tang, Co-Is: John Hancock, Tianyu Jiang, Samira Sarabandikachyani. $5,000. CDRI Grant, DAAP, UC. 5/23/2026- 8/23/2026

This project proposes the development of an AI-augmented Digital Twin installation for the Fort Ancient Earthworks, a UNESCO World Heritage site in southern Ohio. Using reality capture, spatial computing, and Large Language Models (LLMs), the project will create an interactive web- and mobile-based experience that allows users to explore the site through immersive visualization and natural language conversation.

The project builds upon existing 3D earthwork models previously developed by CERHAS together with earlier XR-Lab spatial computing workflows. This foundation allows the team to focus on AI-driven interaction, interpretation, and public engagement without needing to reconstruct the site from the ground up. The AI system will be developed through a carefully curated Retrieval-Augmented Generation (RAG) workflow using approved scholarly, archival, and Indigenous-informed materials as its knowledge base.

Users will be able to ask questions about the geometry, ceremonial purpose, astronomy, landscape design, and cultural significance of the earthworks while virtually navigating a Digital Twin of the site. The project approaches AI as a tool for interpretation and storytelling that can support more accessible and engaging public experiences with cultural heritage.

At the same time, the project explores broader questions about authorship, representation, historical interpretation, and the role of AI in public humanities and creative practice.