HUBSUArizona

Research

Ask hard. Answer harder.

The lab picks the questions that matter and stays with them for years.

Funding

Current and past projects

Current

Collaborative Research: Empowering STEM Education by Creating Benchmarking Models for GenAI Learning Assistants

National Science Foundation · 10/2025 – 09/2028

Role: PI (non-leading institution; Lead PI: Dr. Namgyun Kim at Texas A&M University)

AZTI SPR-804: Potential Revenue Generation Through Arizona Rest Areas

Arizona Department of Transportation · 08/2025 – 10/2026

Role: Co-PI (PI: Dr. Ali Shamshiripour)

Past

Benefits of Smart Electric Panels for SRP Sustainability Goals

Salt River Project · 08/2024 – 07/2026

Role: PI

Towards All-Electric Buildings in the SRP Territory

Salt River Project · 08/2024 – 07/2025

Role: PI

Enhancing Environmental and Energy Equity: Advanced Indoor Heat Stress Sensing for Diverse Populations

SensorLab (UArizona) · 08/2023 – 07/2024

Role: PI

Emergency System for Collaborative and Active Protection and Evacuation (ESCAPE)

Western Alliance to Expand Student Opportunities (WAESO) · 08/2024 – 05/2025

Role: PI

Modeling Distributed Energy Resource Solar Generation Output

Salt River Project · 08/2024 – 07/2025

Role: Co-PI (PI: Dr. Chris Chaeha Lim)

Previous affiliations

Pacific Northwest National Laboratory

ASHRAE Standard 140 Maintenance and Development

U.S. Department of Energy · 02/2022 – 05/2022

EnergyPlus Development

U.S. Department of Energy · 05/2021 – 05/2022

Healthy Buildings

U.S. Department of Energy & General Services Administration · 07/2020 – 05/2022

Quantification of HVAC Energy Savings for Occupancy Sensing in Buildings Through an Innovative Testing Methodology

Advanced Research Projects Agency-Energy (ARPA-E) · 07/2020 – 02/2022

Building Energy Codes Program

U.S. Department of Energy · 07/2020 – 02/2022

Virginia Tech

Human-Aware Environments for Distributed Building Systems Operations

National Science Foundation · 08/2017 – 05/2020

Publications

Papers and proceedings

Every paper the lab has published, each with a citation you can download.

All publications Google Scholar

Intellectual property

Software and data

Software and data released by the lab. Everything here is citable and independently archived — each release carries its own DOI, so it can be referenced without going through the paper that describes it.

All repositories on GitHub

Software

BuildOcc v1.0.0 APACHE-2.0 Updated July 2026

ATUS-grounded LLM occupant agents for building energy simulation

LLM-based occupant agents grounded in American Time Use Survey microdata. Ships a Python agent library, a REST API, and an MCP server — with ATUS-informed activity scheduling across demographic groups, persona generation from EIA RECS appliance data, a memory stream, demand-response signal classification, and validation metrics for both behaviour and energy.

GitHub 10.5281/zenodo.21192895
HEMA Updated April 2026

Multi-Agent Home Energy Management Assistant

A multi-agent assistant for residential energy management.

GitHub SoftwareX
ROSS MIT Updated July 2023

Residential Occupancy Schedule Simulator

Generates representative U.S. residential occupancy schedules derived from smart thermostat data.

GitHub Building and Environment

Datasets & benchmarks

BuildGraph 1.0 CC-BY-NC-4.0 Updated May 2026

A Synthetic Multi-Archetype Building Knowledge Graph Dataset

120 commercial building knowledge graphs in Brick Schema v1.3, as RDF Turtle. Derived from DOE Commercial Prototype Building Models across eight building types and three ASHRAE code vintages, with sensor placement mined from 65 real buildings via Mortar. Ships 75 SPARQL queries with automatic scope detection; BuildGraph buildings reach a 91.5% Query Answerability Rate against that benchmark, versus 35.8% for public real-world Brick models.

GitHub 10.5281/zenodo.20015123
Build2SPARQL 1.0 CC-BY-NC-4.0 Updated May 2026

A Large-Scale Text-to-SPARQL Benchmark for Building Knowledge Graph Querying

6,136 executable SPARQL queries and 30,680 natural-language questions over 201 building knowledge graphs. Queries are validated by graph traversal before the natural-language questions are generated, across six query patterns and five vocabulary registers from ontology jargon to plain English. Includes a 173/28 building train–test split.

10.5281/zenodo.20451474
BATS v1.0 CC-BY-NC-4.0 Updated June 2026

Building AI Testbed Suite — physics-grounded sensor time-series with knowledge graph annotations and auto-gradable QA benchmarks

Eighteen building simulations from three DOE commercial prototypes (small, medium and large office, ASHRAE 90.1-2019) across three climate zones, each in fault-free and faulted variants. Combines Brick v1.3 knowledge graphs, 9.2 million hourly sensor readings across 1,050 streams, and 249 machine-gradable question–answer pairs. Faults are injected as physics parameters rather than post-hoc adjustments, so they propagate through the control system realistically.

10.5281/zenodo.20777376

Acknowledgements

Sponsors and partners

With support from

In partnership with