Timur Dogan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Timur Dogan has a total of 97 co-authors. Here are the top co-authors by number of shared publications:
- Patrick Kastner
Georgia Institute of Technology
7 shared publications - Amber Jiayu Su
Cornell University
3 shared publications Christoph Reinhart
3 shared publications- Christoph Reinhart
Massachusetts Institute of Technology
3 shared publications Samitha Samaranayake
School of Civil and Environmental Engineering, Cornell University, Ithaca, NY, USA
3 shared publicationsYang Yang
Cornell University, 252 East Sibley,Environment Systems Lab,Ithaca,NY,USA
3 shared publications
Latest Publications
- Open Access
- 12 March 2026
- Published by Elsevier in SSRN Electronic Journal
A Physics-informed GAN framework for Urban Wind Analysis with Arbitrary Input and Output Channels
Urban wind flow patterns influence pedestrian comfort, safety, and urban ventilation, yet high-fidelity CFD remains too costly for iterative design exploration. We present a cGAN implemented in PyTorch that takes multi-height SDFs of the air domain and a wind-direction channel as input and predicts all three velocity components and pressure at real-time inference speed. Unlike prior approaches, our architecture produces multi-variable flow fields in a single forward pass and accepts arbitrary input and output channel counts, making it straightforward to add new geometry encodings or output quantities. A physics-residual loss based on 2D continuity and momentum conservation stabilizes adversarial training. The model achieves SSIM scores of 0.90–0.98 on unseen cases, with residual errors concentrated only near sharp geometric transitions and wake regions. A systematic ablation across five input configurations shows that multi-height SDFs improve accuracy, whereas an explicit scale channel or building- only SDFs provide no significant benefit. Despite richer inputs and outputs, inference takes approximately 1 s, which is faster than the previous model. The trained generator is exported to ONNX format for direct integration into Rhino/Grasshopper CAD workflows, enabling real- time wind feedback during early-stage massing studies.
- 12 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA Physics-informed GAN framework for Urban Wind Analysis with Arbitrary Input and Output Channels
Urban wind flow patterns influence pedestrian comfort, safety, and urban ventilation, yet high-fidelity CFD remains too costly for iterative design exploration. We present a cGAN implemented in PyTorch that takes multi-height SDFs of the air domain and a wind-direction channel as input and predicts all three velocity components and pressure at real-time inference speed. Unlike prior approaches, our architecture produces multi-variable flow fields in a single forward pass and accepts arbitrary input and output channel counts, making it straightforward to add new geometry encodings or output quantities. A physics-residual loss based on 2D continuity and momentum conservation stabilizes adversarial training. The model achieves SSIM scores of 0.90–0.98 on unseen cases, with residual errors concentrated only near sharp geometric transitions and wake regions. A systematic ablation across five input configurations shows that multi-height SDFs improve accuracy, whereas an explicit scale channel or building- only SDFs provide no significant benefit. Despite richer inputs and outputs, inference takes approximately 1 s, which is faster than the previous model. The trained generator is exported to ONNX format for direct integration into Rhino/Grasshopper CAD workflows, enabling real- time wind feedback during early-stage massing studies.
- 14 February 2026
- Published by Elsevier in Energy and Buildings
- Vol. 357
Voxel Shader – An efficient shadow calculation approach for urban building energy modeling
- 14 February 2026
- Published by Elsevier in Energy and Buildings
- Vol. 357
Voxel Shader – An efficient shadow calculation approach for urban building energy modeling
- 31 July 2025
- Published by Taylor & Francis in LEUKOS
- Vol. 23 (1) , 16-47
Window View Satisfaction Assessment Method: A Comparison of Physical Space, Virtual Reality, and Digital Image
- 31 July 2025
- Published by Taylor & Francis in LEUKOS
- Vol. 23 (1) , 16-47
Window View Satisfaction Assessment Method: A Comparison of Physical Space, Virtual Reality, and Digital Image
- 24 July 2025
- Published by Taylor & Francis in Journal of Building Performance Simulation
- Vol. 19 (2) , 289-316
A bottom-up urban building energy model for evaluating thermal load electrification measures
- 24 July 2025
- Published by Taylor & Francis in Journal of Building Performance Simulation
- Vol. 19 (2) , 289-316
A bottom-up urban building energy model for evaluating thermal load electrification measures
- 12 May 2025
- Published by Taylor & Francis in Journal of Building Performance Simulation
- Vol. 18 (7) , 964-982
Scalable building reconstruction and window detection for urban building energy modelling applications
- 12 May 2025
- Published by Taylor & Francis in Journal of Building Performance Simulation
- Vol. 18 (7) , 964-982
Scalable building reconstruction and window detection for urban building energy modelling applications
- 21 January 2025
- Published by Taylor & Francis
- p. 274-290
Computational Urban Design
Population growth, urbanization and related space constraints will require new construction and densification of urban centers worldwide. Until 2060, the UN forecasts a construction demand equivalent to 250 times the size of New York City. This is a worrisome development since roughly 40% of our energy use and greenhouse gas emissions can be attributed to buildings. Conversely, constructing and renewing urban centers can also be a unique opportunity to mitigate climate change through intelligent design solutions that enhance energy efficiency and renewables, mobility and quality of life. Apart from being resource efficient, next-generation urban habitats must provide indoor and outdoor comfort conditions, including access to daylight, high-quality public spaces and streetscapes, and innovative transportation concepts. Concepts to cope with extreme weather, such as storms and heat waves, must also be considered. This chapter describes a framework for an urban design studio that addresses how architects and urban designers can account for these diverse issues in the design processes. Students learn about emerging building performance and mobility modeling tools. They are challenged to develop visions for the future of our cities, ranging from urban retrofitting and renewal to master planning and designing new neighborhoods.
- 21 January 2025
- Published by Taylor & Francis
- p. 274-290
Computational Urban Design
Population growth, urbanization and related space constraints will require new construction and densification of urban centers worldwide. Until 2060, the UN forecasts a construction demand equivalent to 250 times the size of New York City. This is a worrisome development since roughly 40% of our energy use and greenhouse gas emissions can be attributed to buildings. Conversely, constructing and renewing urban centers can also be a unique opportunity to mitigate climate change through intelligent design solutions that enhance energy efficiency and renewables, mobility and quality of life. Apart from being resource efficient, next-generation urban habitats must provide indoor and outdoor comfort conditions, including access to daylight, high-quality public spaces and streetscapes, and innovative transportation concepts. Concepts to cope with extreme weather, such as storms and heat waves, must also be considered. This chapter describes a framework for an urban design studio that addresses how architects and urban designers can account for these diverse issues in the design processes. Students learn about emerging building performance and mobility modeling tools. They are challenged to develop visions for the future of our cities, ranging from urban retrofitting and renewal to master planning and designing new neighborhoods.
- 31 May 2024
- Published by Elsevier in Energy and Buildings
- Vol. 317
Towards Auto-Calibrated UBEM Using Readily Available, Underutilized Urban Data: A Case Study for Ithaca, NY
- 31 May 2024
- Published by Elsevier in Energy and Buildings
- Vol. 317
Towards Auto-Calibrated UBEM Using Readily Available, Underutilized Urban Data: A Case Study for Ithaca, NY
- 22 February 2023
- Published by SAGE Publications in Environment and Planning B: Urban Analytics and City Science
- Vol. 50 (9) , 2452-2469
A clustering-based approach to quantifying socio-demographic impacts on urban mobility patterns
This paper uses a generalizable clustering approach to investigate the effects of socio-demographic features on aggregate urban mobility patterns, including activity distribution and travel modal split. We use K-means via principal component analysis to identify eight representative traveler clusters from the 2017 U.S. National Household Travel Survey. Based on the cluster centroids and the cluster percentages within a neighborhood, we can estimate a Temporal Mobility Choice Matrix ( TM) that describes the neighborhood-level aggregate mobility choice pattern. The estimation accuracy is assessed in a case study in LA City. It is found that the neighborhood-level temporal mobility patterns are well-replicated, with an average R2 of 65.47%, 53.15%, and 72.04% among all analyzed neighborhoods in the city. However, we find a moderate to low accuracy in estimating the spatial differences in the mobility patterns across neighborhoods. This could be because factors other than socio-demographics, such as physical and built environment factors like terrain, street quality, or amenity densities, are contributing to the spatial differences but have not been considered in this study. Overall, we show that socio-demographic features alone can approximate the average temporal mobility choice patterns of a given population. Our method and result can serve as the baseline and benchmark for future mobility studies that take the socio-demographics of the traveler population into consideration in modeling.
- 22 February 2023
- Published by SAGE Publications in Environment and Planning B: Urban Analytics and City Science
- Vol. 50 (9) , 2452-2469
A clustering-based approach to quantifying socio-demographic impacts on urban mobility patterns
This paper uses a generalizable clustering approach to investigate the effects of socio-demographic features on aggregate urban mobility patterns, including activity distribution and travel modal split. We use K-means via principal component analysis to identify eight representative traveler clusters from the 2017 U.S. National Household Travel Survey. Based on the cluster centroids and the cluster percentages within a neighborhood, we can estimate a Temporal Mobility Choice Matrix ( TM) that describes the neighborhood-level aggregate mobility choice pattern. The estimation accuracy is assessed in a case study in LA City. It is found that the neighborhood-level temporal mobility patterns are well-replicated, with an average R2 of 65.47%, 53.15%, and 72.04% among all analyzed neighborhoods in the city. However, we find a moderate to low accuracy in estimating the spatial differences in the mobility patterns across neighborhoods. This could be because factors other than socio-demographics, such as physical and built environment factors like terrain, street quality, or amenity densities, are contributing to the spatial differences but have not been considered in this study. Overall, we show that socio-demographic features alone can approximate the average temporal mobility choice patterns of a given population. Our method and result can serve as the baseline and benchmark for future mobility studies that take the socio-demographics of the traveler population into consideration in modeling.
- 2 February 2023
- Published by SAGE Publications in Environment and Planning B: Urban Analytics and City Science
- Vol. 50 (9) , 2359-2375
Assessing impacts of the built environment on mobility: A joint choice model of travel mode and duration
This paper introduces a joint choice model for travel mode and duration to quantify the mobility impacts of urban design changes on the built environment. The model is formulated as a Random Forest classifier that predicts the mode-duration probabilities of a given trip. A novel series of predictor features are proposed which measure the urban form, demographics, and service densities on different scales of the transportation network. Through a sensitivity analysis and a proof-of-concept case study, we find that a dense, mixed-use environment with good coverage of a multi-modal mobility network can significantly promote active transportation and public transit use. However, we also find that ultra-dense, centralized developments can lead to increased travel time and increased vehicle use in the urban periphery. Our modeling and analysis method provides a simplified and effective way to assess urban design and planning scenarios from different mobility perspectives and facilitates data-driven, mobility-aware urban design and planning that can help identify better solutions more quickly.
- 2 February 2023
- Published by SAGE Publications in Environment and Planning B: Urban Analytics and City Science
- Vol. 50 (9) , 2359-2375
Assessing impacts of the built environment on mobility: A joint choice model of travel mode and duration
This paper introduces a joint choice model for travel mode and duration to quantify the mobility impacts of urban design changes on the built environment. The model is formulated as a Random Forest classifier that predicts the mode-duration probabilities of a given trip. A novel series of predictor features are proposed which measure the urban form, demographics, and service densities on different scales of the transportation network. Through a sensitivity analysis and a proof-of-concept case study, we find that a dense, mixed-use environment with good coverage of a multi-modal mobility network can significantly promote active transportation and public transit use. However, we also find that ultra-dense, centralized developments can lead to increased travel time and increased vehicle use in the urban periphery. Our modeling and analysis method provides a simplified and effective way to assess urban design and planning scenarios from different mobility perspectives and facilitates data-driven, mobility-aware urban design and planning that can help identify better solutions more quickly.
- 18 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 523-536
How The Urban Microclimate And Outdoor Thermal Comfort Can Affect Intra-City Mobility Patterns: Evidence From New York City
Employing urban planning and design to promote active travel modes, such as walking and biking, are important for decarbonizing urban mobility. This paper proposes a modeling framework that investigates the interdependencies between the built environment and travel behaviors through the lens of urban microclimates. We combine travel data, built environment data, and Universal Thermal Climate Index (UTCI) calculations for New York City and train a predictive model for intra-city mobility patterns. Then, impacts of UTCI features are studied through a sensitivity analysis and a spatial heterogeneity analysis. Results show that impacts of UTCI features can account for up to 4 change in the choice of active travel mode in dense urban areas. Also, impacts of microclimate vary across different travel contexts regarding season, time of day, activity, built environment, and traveler type. Our methodology and findings can inform future decision-making of microclimate-oriented spatial planning and design interventions.
- 18 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 523-536
How The Urban Microclimate And Outdoor Thermal Comfort Can Affect Intra-City Mobility Patterns: Evidence From New York City
Employing urban planning and design to promote active travel modes, such as walking and biking, are important for decarbonizing urban mobility. This paper proposes a modeling framework that investigates the interdependencies between the built environment and travel behaviors through the lens of urban microclimates. We combine travel data, built environment data, and Universal Thermal Climate Index (UTCI) calculations for New York City and train a predictive model for intra-city mobility patterns. Then, impacts of UTCI features are studied through a sensitivity analysis and a spatial heterogeneity analysis. Results show that impacts of UTCI features can account for up to 4 change in the choice of active travel mode in dense urban areas. Also, impacts of microclimate vary across different travel contexts regarding season, time of day, activity, built environment, and traveler type. Our methodology and findings can inform future decision-making of microclimate-oriented spatial planning and design interventions.