Smart Cities &
Urban Energy Systems
Artificial intelligence, digital twins, remote sensing, and advanced analytics are driving the next generation of smart cities and urban energy systems. By combining these technologies, this research project enables intelligent planning, optimized building performance, and more sustainable urban environments.
Explore our research and innovative applications across smart cities and urban energy systems.
Applied AI and Digital Twins
Project 1:
Powering Digital Twins: Development of an NVIDIA™ Omniverse Bi-Directional Connector for Near Real-Time Building Energy Simulation and Optimization
Student: Deepak Balakrishnan
T20133US001: Bi-Directional Integration of NVIDIA™ Omniverse and EnergyPlus™ for Real-Time Performance Simulation and Predictive Maintenance (Ravi Srinivasan, Deepak Balakrishnan, and Chimay Anumba)
Seamless, interactive building energy decision-making platform for conducting building energy scenario analysis and performance optimization and prediction through high-fidelity digital twin visualization and physics-based simulation.
Project 2:
Unified Digital Twins
Student: Deepak Balakrishnan
T20163US001: Unified Digital Twins (UDT) System with a Bi-Directional Connector and Associated Methods (Ravi Srinivasan, Deepak Balakrishnan, and Chimay Anumba)
A Unified Digital Twin (UDT) represents a comprehensive “System of Systems” architecture that seamlessly integrates multiple, distinct digital twins across various scales, including Cities, Campuses, Buildings, and Datacenters, as well as different domains. This integration facilitates a cohesive visualization and management interface.
Project 3:
Built Environment Reasoning from Remote Sensing Imagery Using Large Vision–Language Models
Student(s): Shenhao Wang, Dongdong Wang, Deepak Balakrishnan
This work investigates the use of large language models (LLMs) for tasks in smart cities. The core idea is to leverage remote sensing imagery to characterize the built environment, including design suggestions, constructability assessment, landuse patterns, and risk identification. We examine remote sensing imagery at multiple spatial scales as inputs for multimodal language modeling and evaluate their effects on built-environment-related reasoning. In addition, we compare state-of-the-art LLMs, including InternVL and Qwen, in terms of accuracy and reliability when generating built environment recommendations. The results demonstrate the potential of integrating remote sensing imagery with large language models to assist smart cities and decision-making. (https://arxiv.org/abs/2605.08404)
AI-Enabled Planning, Design, and Construction
Project 1:
Automated Building Code Check
Ravi Shankar Srinivasan, Nawari O Nawari
The present disclosure describes system and methods for determination of building code performance. One such method comprises transforming a building code regulation into a computable record that defines a building design and/or engineering rule for the building code regulation; performing design model validation, wherein design model validation comprises entering building permit application file information and checking the building permit application file information against relevant codes and regulations, using a taxonomy or neural natural language processing techniques or artificial Intelligence; performing exchange model code checking; performing code conformance checking, wherein the code conformance checking comprises receiving a request from the exchange models and passing the building permit application file information to code checking modules; performing verification reporting based.
Patents: Systems and methods for automated building code conformance, Building code check plug-in
Smart Design
Project 1:
Acoustics-Based HVAC System Prognosis
Research Support & Team:
National Science Foundation
PIs: Ravi Srinivasan, Nirjon Shahriar (UNC-Chapel Hill)
Students: Zeyu Wang, Mohammed Islam, Tamzeed Islam
Acoustics-based HVAC Maintenance
Centralized HVAC systems are the primary means to control the indoor climate and maintain occupants’ comfort in over 88% of the commercial buildings in the USA. Due to the lack of an effective, low-cost, and continuous assessment and prognosis mechanism for detecting underperforming HVAC units, it is extremely difficult to determine whether a repair, retrofit, or permanent retirement of an HVAC system is warranted. For a systematic prognosis and lifecycle management of centralized HVAC systems, what we need is a robust, inexpensive, and easily deployable system, so that impending failures can be detected early. Such a system will save money, and help us breathe healthily.
We developed a Smart Audio SEnsing-based Maintenance (SASEM) system; SASEM has a single unifying intellectual focus, i.e., enabling predictive maintenance of building equipment by autonomously monitoring and analyzing their acoustic emissions. Using audio signatures to predict equipment failure requires more than simply connecting a microphone to a digital signal processor; it requires the development of novel hardware and software that are low cost, low maintenance, easy to deploy and take into consideration the variations in noises produced by different equipment, acoustically hostile building environments, false positives and negatives during classification, and privacy issues. We developed effective machine learning-based classifiers to identify acoustic characteristics of building equipment. Refer to our recent publications for more information.
Urban Energy & Environmental Systems + Urban Heat Island
Project 1:
Cool Surfaces – South Africa
Student: Deepak Balakrishnan
In line with South African National Energy Development Institute’s (SANEDI) goal to reduce the carbon footprint of South Africa, utilizing the Reconstruction and Development Programme (RDP) housing project, particularly the “KLAPMUTS ERF 342 Semi-Detached Subsidy House,” this project will have three principal and overarching objectives:
Objective #1: To perform energy analysis to identify energy efficiency opportunities. The focus is on building envelopes.
List of Energy Efficiency Measures:
Objective #2: To perform environmental impact study which will include impacts to human health and ecosystem services. The project will utilize an integrated, cradle-to-cradle, environmental accounting software.
Objective #3: To disseminate the knowledge via a publicly accessible website.
Presented at the Powering South Africa with Cleaner & Smarter Energy Conference & Exhibition. 27-28 May 2015, Johannesburg, S. Africa. SA Conference Final [PDF, 4.19MB]
Project 2:
Cool Surfaces – Indonesia
PIs: Beta Paramita, Ravi Srinivasan
Students: Xinxin Yan
Residential buildings in tropical climates commonly experience persistent thermal discomfort due to the combined effects of high ambient temperature and elevated relative humidity. While solar reflective coatings have been widely investigated as a passive cooling strategy, most existing research has focused primarily on reducing indoor air temperature, with limited attention to relative humidity and its influence on thermal perception. In hot–humid climates, however, high humidity restricts evaporative heat loss from the body surfaces, intensifying heat stress and making it essential to evaluate both temperature and humidity when assessing the cooling performance.
To address this gap, this study integrates measurements of air temperature and relative humidity to assess the indoor environmental performance of solar-reflective coated houses under the RAFLESIA® (Rumah Reflektif Surya Indonesia) project in Indonesia. Field monitoring was onducted in three cities representing two tropical Köppen climate types (Af and Am). Indoor conditions were evaluated using Heat Index (HI) to quantify combined heat–humidity stress, Predicted Mean Vote (PMV) and Predicted Percentage of Dissatisfied (PPD) to assess thermal comfort. Results show that the coating not only reduces daytime heat accumulation but also enhances nighttime heat release, with the strongest cooling effects occurring during morning hours. By adopting an integrated comfort-based evaluation, this study provides a more comprehensive understanding of reflective coatings and highlights their potential for improving thermal comfort in tropical housing.
Project 3:
City of GNV (Gainesville)
Principal Investigator: Ravi Srinivasan
Students: Baalaganapathy Manohar, Rahul Aggarwal, Akshay Padwal, Nikhil Asok Kumar, and Vahid Daneshmand. Collaborators: Saranya Gunasingh, Scott Schuetter, Doug Ahl (SeventhWave)
Cities are facing unprecedented growth with an increase in population and urbanization. The United Nations estimates that the global population will increase to 9.3 billion by 2050, which is an increase of 30% compared to the population in 2011. As development in dense urban areas continues, the scientific community must continue to observe, analyze, and interpret the effects of dense urbanization, including climate change impacts on urban sustainability, particularly buildings.
The challenge is to test the feasibility of implementing green building technologies on a city-wide scale for energy policy decision-making. In this report, we discuss a novel physics-based approach to Urban Energy Modeling (UEM) using the City of Gainesville, Florida, USA as a case study. This city is the fourth largest city in Florida with a population of over 125,000. Our physics-based UEM approach can be used to virtually test the feasibility of implementing green building technologies on a city-wide scale for energy policy decision-making. Such a dynamic tool can be used by utility providers to accurately predict the demand of these communities in the future and mitigate risk.
Learn more:
https://built-ecologist.com/2018/10/19/uf-city-of-gainesville-research-awards-showcase-urban-energy-modeling-for-smart-city-informatics/