Dong-Wook Sohn
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Dong-Wook Sohn has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Weihao Hao
The Lab of Architectural & Urban Space Design, Department of Architecture and Architectural Engineering, Yonsei University Seoul Campus, Seoul 03722, Republic of Korea
3 shared publications - Hyungkyoo Kim
Department of Urban Design and Planning, Hongik University, Seoul 04066, Republic of Korea
2 shared publications - Jongho Lee
BIM Center, Construction Industry Promotion Department, Korea Institute of Civil Engineering and Building Technology (KICT), Goyang 10223, Republic of Korea
2 shared publications - Chorong Park
Department of Architecture & Architectural Engineering, Yonsei University, Seoul 03722, Republic of Korea
1 shared publication - Chorong Park
Korea Institute of Civil Engineering and Building Technology (KICT), 283 Goyang-daero, Ilsanseo-gu, Goyang 10223, Republic of Korea
1 shared publication - Da Wan
School of Architecture, Tianjin Chengjian University, Tianjin 300074, China
1 shared publication
Latest Publications
- Open Access
Spatial Assessment of Fire-Casualty Vulnerability in Industrial Complexes: Comparing AHP-Derived Weights with SHAP-Based Feature Importance
Fires in industrial complexes cause property damage and casualties, but the spatial conditions under which fires result in casualties are rarely assessed. This study proposes a two-stage framework that combines expert-based Analytic Hierarchy Process (AHP)–geographic information system (GIS) assessment with machine-learning feature-importance analysis of observed fires. Seven spatial indicators—four vulnerability indicators (building density, aged-building share, fire-engine access, and hazardous-facility proximity) and three reverse-coded mitigation indicators (fire-station response time, firefighting water-supply coverage, and evacuation-facility accessibility)—were defined with largely common scoring rules. In Stage 1, weights from an AHP survey of 62 experts were applied in GIS to map fire-casualty vulnerability on a 250 m grid in the Myeongji Noksan National Industrial Complex, Busan, Republic of Korea. In Stage 2, scores for the same indicators were assigned to 5417 factory fires recorded in Busan’s 41 industrial complexes during 2019–2023 (32.9% with casualties); four classifiers were trained to predict casualty occurrence, and Shapley additive explanations (SHAP) were computed for XGBoost, which achieved the highest recall (0.621). The map identified a localized high-vulnerability zone in the south-central part of the complex, where hazardous-facility proximity was concentrated, although recorded casualty fires were not clearly concentrated in these cells. SHAP ranked aged-building share and building density highest, whereas experts emphasized fire-engine access and response time. Comparing the two perspectives shows where expert emphasis and data-driven importance diverge and offers an exploratory basis for spatial prioritization and for re-examining indicator weights.
Open AccessSpatial Assessment of Fire-Casualty Vulnerability in Industrial Complexes: Comparing AHP-Derived Weights with SHAP-Based Feature Importance
Fires in industrial complexes cause property damage and casualties, but the spatial conditions under which fires result in casualties are rarely assessed. This study proposes a two-stage framework that combines expert-based Analytic Hierarchy Process (AHP)–geographic information system (GIS) assessment with machine-learning feature-importance analysis of observed fires. Seven spatial indicators—four vulnerability indicators (building density, aged-building share, fire-engine access, and hazardous-facility proximity) and three reverse-coded mitigation indicators (fire-station response time, firefighting water-supply coverage, and evacuation-facility accessibility)—were defined with largely common scoring rules. In Stage 1, weights from an AHP survey of 62 experts were applied in GIS to map fire-casualty vulnerability on a 250 m grid in the Myeongji Noksan National Industrial Complex, Busan, Republic of Korea. In Stage 2, scores for the same indicators were assigned to 5417 factory fires recorded in Busan’s 41 industrial complexes during 2019–2023 (32.9% with casualties); four classifiers were trained to predict casualty occurrence, and Shapley additive explanations (SHAP) were computed for XGBoost, which achieved the highest recall (0.621). The map identified a localized high-vulnerability zone in the south-central part of the complex, where hazardous-facility proximity was concentrated, although recorded casualty fires were not clearly concentrated in these cells. SHAP ranked aged-building share and building density highest, whereas experts emphasized fire-engine access and response time. Comparing the two perspectives shows where expert emphasis and data-driven importance diverge and offers an exploratory basis for spatial prioritization and for re-examining indicator weights.
- Open Access
Integration of Photovoltaic Shading Device and Vertical Farming on School Buildings to Improving Indoor Daylight, Thermal Comfort and Energy Performance in Three Different Cities in China
This study explores the integration of photovoltaic (PV) shading devices and vertical farming (VF) in school buildings to optimize indoor daylight, thermal comfort, and energy performance across three different climate regions in China: Beijing, Shanghai, and Shenzhen. With rapid urbanization and increasing energy consumption in educational buildings, this research investigates the impact of innovative facade design on both energy efficiency and occupant comfort. Through parametric simulations and multi-objective optimization, various PV and VF facade prototypes were evaluated to determine the best configurations for reducing energy consumption while enhancing thermal and visual comfort. This study optimized facade systems integrating photovoltaic and vertical farming for school buildings in Shenzhen, Beijing, and Shanghai. Key findings include: In Shenzhen, Model B’s UDI increased by 5.1% and Model C by 19.02%, with glare areas reduced by 5.4% and 21.40% and stable thermal comfort (PMV 0.52–0.59) throughout the year. In Beijing, Model B’s UDI decreased by 0.2%, while Model C increased by 6.55%. Glare areas reduced by 2.92% and 14.35%, with improved winter comfort (PMV −0.35 to −0.1). In Shanghai, Model C’s UDI increased by 6.7%, but summer thermal discomfort was notable (PMV up to 1.2). The study finds that PV shading systems combined with vertical farming can provide significant energy savings, reduce greenhouse gas emissions, and offer organic vegetable production within school environments. The findings suggest that integrating these systems into the building envelope can optimize the energy performance of school buildings while improving the comfort and well-being of students and staff.
Open AccessIntegration of Photovoltaic Shading Device and Vertical Farming on School Buildings to Improving Indoor Daylight, Thermal Comfort and Energy Performance in Three Different Cities in China
This study explores the integration of photovoltaic (PV) shading devices and vertical farming (VF) in school buildings to optimize indoor daylight, thermal comfort, and energy performance across three different climate regions in China: Beijing, Shanghai, and Shenzhen. With rapid urbanization and increasing energy consumption in educational buildings, this research investigates the impact of innovative facade design on both energy efficiency and occupant comfort. Through parametric simulations and multi-objective optimization, various PV and VF facade prototypes were evaluated to determine the best configurations for reducing energy consumption while enhancing thermal and visual comfort. This study optimized facade systems integrating photovoltaic and vertical farming for school buildings in Shenzhen, Beijing, and Shanghai. Key findings include: In Shenzhen, Model B’s UDI increased by 5.1% and Model C by 19.02%, with glare areas reduced by 5.4% and 21.40% and stable thermal comfort (PMV 0.52–0.59) throughout the year. In Beijing, Model B’s UDI decreased by 0.2%, while Model C increased by 6.55%. Glare areas reduced by 2.92% and 14.35%, with improved winter comfort (PMV −0.35 to −0.1). In Shanghai, Model C’s UDI increased by 6.7%, but summer thermal discomfort was notable (PMV up to 1.2). The study finds that PV shading systems combined with vertical farming can provide significant energy savings, reduce greenhouse gas emissions, and offer organic vegetable production within school environments. The findings suggest that integrating these systems into the building envelope can optimize the energy performance of school buildings while improving the comfort and well-being of students and staff.
- Open Access
- 18 January 2024
- Published by Oxford University Press (OUP) in International Journal of Low-Carbon Technologies
- Vol. 19, 2309-2327
Research on thermal comfort and energy efficiency in office buildings with high window-to-wall ratios: a case study in Qingdao
High window-to-wall ratios (WWRs) are commonly used in office buildings, yet their effects on thermal comfort and energy consumption are not fully understood. This study uses TRNSYS software to analyze the thermal environment of buildings with varying WWRs (0%–100%) in Qingdao. The findings show that as WWRs increase, the average monthly maximum temperatures (Tmax) rise between 1.33°C and 5.62°C. Middle floors (F2–F3) are consistently warmer than the ground (F1) and top floors (F4). In summer, higher WWRs (>60%) significantly reduce the prevalence of extremely high temperatures (>37°C) by 0.64% to 11.29%. High WWRs also improve nocturnal heat dissipation, increasing the percentage of temperatures within the thermal comfort range and reducing heating loads by 0.62% to 1.08%. Implementing shading facilities during summer further enhances thermal comfort and energy efficiency in buildings with high WWRs.
- 18 January 2024
- Published by Oxford University Press (OUP) in International Journal of Low-Carbon Technologies
- Vol. 19, 2309-2327
Open AccessResearch on thermal comfort and energy efficiency in office buildings with high window-to-wall ratios: a case study in Qingdao
High window-to-wall ratios (WWRs) are commonly used in office buildings, yet their effects on thermal comfort and energy consumption are not fully understood. This study uses TRNSYS software to analyze the thermal environment of buildings with varying WWRs (0%–100%) in Qingdao. The findings show that as WWRs increase, the average monthly maximum temperatures (Tmax) rise between 1.33°C and 5.62°C. Middle floors (F2–F3) are consistently warmer than the ground (F1) and top floors (F4). In summer, higher WWRs (>60%) significantly reduce the prevalence of extremely high temperatures (>37°C) by 0.64% to 11.29%. High WWRs also improve nocturnal heat dissipation, increasing the percentage of temperatures within the thermal comfort range and reducing heating loads by 0.62% to 1.08%. Implementing shading facilities during summer further enhances thermal comfort and energy efficiency in buildings with high WWRs.
- Open Access
- 30 October 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (21) , 11866
Development of a Data-Based Machine Learning Model for Classifying and Predicting Property Damage Caused by Fire
Large fires in factories cause severe human casualties and property damage. Thus, preparing more economical and efficient management strategies for fire prevention can significantly improve fire safety. This study deals with property damage grade prediction by fire based on simplified building information. This paper’s primary objective is to propose and verify a framework for predicting the scale of property damage caused by fire using machine learning (ML). Korean public datasets are collected and preprocessed, and ML algorithms are trained with only 15 input data using building register and fire scenario information. Four models (artificial neural network (ANN), decision tree (DT), k-nearest neighbor (KNN), and random forest (RF)) are used for ML. The RF model is the most suitable for this study, with recall and precision of 74.2% and 73.8%, respectively. Structure, floor, causes, and total floor area are the critical factors that govern the fire size. This study proposes a novel approach by utilizing ML models to accurately and rapidly predict the size of fire damage based on basic building information. By analyzing domestic fire incident data and creating fire scenarios, a similar ML model can be developed.
- 30 October 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (21) , 11866
Open AccessDevelopment of a Data-Based Machine Learning Model for Classifying and Predicting Property Damage Caused by Fire
Large fires in factories cause severe human casualties and property damage. Thus, preparing more economical and efficient management strategies for fire prevention can significantly improve fire safety. This study deals with property damage grade prediction by fire based on simplified building information. This paper’s primary objective is to propose and verify a framework for predicting the scale of property damage caused by fire using machine learning (ML). Korean public datasets are collected and preprocessed, and ML algorithms are trained with only 15 input data using building register and fire scenario information. Four models (artificial neural network (ANN), decision tree (DT), k-nearest neighbor (KNN), and random forest (RF)) are used for ML. The RF model is the most suitable for this study, with recall and precision of 74.2% and 73.8%, respectively. Structure, floor, causes, and total floor area are the critical factors that govern the fire size. This study proposes a novel approach by utilizing ML models to accurately and rapidly predict the size of fire damage based on basic building information. By analyzing domestic fire incident data and creating fire scenarios, a similar ML model can be developed.
- Open Access
Development and Research Regarding Stormwater Runoff Management: Bibliometric Analysis from 2001 to 2021
As a result of climate change and urbanization, human activities are placing increasing pressure on nature, including with regard to urban stormwater runoff; consequently, various concepts related to urban stormwater runoff management have been proposed to tackle this problem in multiple countries. In this study, the latest research and techniques related to stormwater runoff management are reviewed in detail. A bibliometric analysis of proposed stormwater runoff management concepts developed from 2001 to 2021 was conducted based on a screening of 1771 studies obtained from the Web of Science (WoS). Bibliometric analysis is a research method that can be used to quantitatively analyze academic literature. Visualization of the data obtained from the literature using CiteSpace software and subsequent analysis of patent data through S-curve prediction were performed. The United States, China, and Australia were the top three countries from which publications on this issue were sourced. Each country tends to study its own most relevant issues and has a particularly clear understanding of its own research landscape. The development of stormwater runoff management concepts was analyzed using reference emergence analysis. This was followed by keyword clustering and keyword emergence analysis to identify current research hotspots, trends, technological developments, and limitations. The limitations and emerging trends related to current stormwater runoff management concepts are discussed thoroughly, and suggestions for future studies are provided.
Open AccessDevelopment and Research Regarding Stormwater Runoff Management: Bibliometric Analysis from 2001 to 2021
As a result of climate change and urbanization, human activities are placing increasing pressure on nature, including with regard to urban stormwater runoff; consequently, various concepts related to urban stormwater runoff management have been proposed to tackle this problem in multiple countries. In this study, the latest research and techniques related to stormwater runoff management are reviewed in detail. A bibliometric analysis of proposed stormwater runoff management concepts developed from 2001 to 2021 was conducted based on a screening of 1771 studies obtained from the Web of Science (WoS). Bibliometric analysis is a research method that can be used to quantitatively analyze academic literature. Visualization of the data obtained from the literature using CiteSpace software and subsequent analysis of patent data through S-curve prediction were performed. The United States, China, and Australia were the top three countries from which publications on this issue were sourced. Each country tends to study its own most relevant issues and has a particularly clear understanding of its own research landscape. The development of stormwater runoff management concepts was analyzed using reference emergence analysis. This was followed by keyword clustering and keyword emergence analysis to identify current research hotspots, trends, technological developments, and limitations. The limitations and emerging trends related to current stormwater runoff management concepts are discussed thoroughly, and suggestions for future studies are provided.
- Open Access
- 25 June 2020
- Published by Taylor & Francis in Journal of Asian Architecture and Building Engineering
- Vol. 19 (6) , 731-741
The urban built environment and the mobility of people with visual impairments: analysing the travel behaviours based on mobile phone data
The purpose of this study is to examine the relationship between urban built environment factors and the travel behaviours of visually impaired people. Using mobile phone data containing information on the movements of people with visual impairment, the association between their traffic volume and the built environment factors of land uses, public transit, and pedestrian facilities for visually impaired people were analysed. The results indicated that some of the urban built environment factors were significantly associated with the travel of people with visual impairments. The model results showed that the associations between their traffic volume and the factors of pedestrian infrastructure for visually impaired people were much higher than the association with all other factors considered in the analysis. Commercial, civic, and cultural uses were also significantly related to their traffic volume. Proximity to the subway was positively associated with an increase in the traffic volume of people with visual impairments. The current study contributes to the ongoing discussion on the mobility of people with disabilities by taking afirst step towards constructing amethod whereby mobile phone data can be utilised to examine the relationship between the built environment and the travel patterns of visually impaired people.
- 25 June 2020
- Published by Taylor & Francis in Journal of Asian Architecture and Building Engineering
- Vol. 19 (6) , 731-741
Open AccessThe urban built environment and the mobility of people with visual impairments: analysing the travel behaviours based on mobile phone data
The purpose of this study is to examine the relationship between urban built environment factors and the travel behaviours of visually impaired people. Using mobile phone data containing information on the movements of people with visual impairment, the association between their traffic volume and the built environment factors of land uses, public transit, and pedestrian facilities for visually impaired people were analysed. The results indicated that some of the urban built environment factors were significantly associated with the travel of people with visual impairments. The model results showed that the associations between their traffic volume and the factors of pedestrian infrastructure for visually impaired people were much higher than the association with all other factors considered in the analysis. Commercial, civic, and cultural uses were also significantly related to their traffic volume. Proximity to the subway was positively associated with an increase in the traffic volume of people with visual impairments. The current study contributes to the ongoing discussion on the mobility of people with disabilities by taking afirst step towards constructing amethod whereby mobile phone data can be utilised to examine the relationship between the built environment and the travel patterns of visually impaired people.
- 15 December 2019
- Published by Taylor & Francis in Local Environment
- Vol. 25 (1) , 69-82
Minority neighbourhoods and availability of green amenities: empirical findings from Seoul, South Korea
Availability of green amenities in cities often raises environmental justice issues. This study empirically examines Seoul, South Korea, where minority populations, such as foreigners, the poor, the old, the young, and the disabled, are generally increasing but the land area of parks and green spaces is gradually decreasing. Using ordinary least squares (OLS) and generalised least squares (GLS) regression models, this study finds that foreign population is mostly negatively associated with green amenities. The old and the young are positively associated with the green amenities in general but negatively with small and children’s parks. Neighbourhood parks do not seem to be associated with concentrations of any minority populations. Findings of this study argue for securing more lands for green amenities in cities and provide lessons to local planning practice.
- 15 December 2019
- Published by Taylor & Francis in Local Environment
- Vol. 25 (1) , 69-82
Minority neighbourhoods and availability of green amenities: empirical findings from Seoul, South Korea
Availability of green amenities in cities often raises environmental justice issues. This study empirically examines Seoul, South Korea, where minority populations, such as foreigners, the poor, the old, the young, and the disabled, are generally increasing but the land area of parks and green spaces is gradually decreasing. Using ordinary least squares (OLS) and generalised least squares (GLS) regression models, this study finds that foreign population is mostly negatively associated with green amenities. The old and the young are positively associated with the green amenities in general but negatively with small and children’s parks. Neighbourhood parks do not seem to be associated with concentrations of any minority populations. Findings of this study argue for securing more lands for green amenities in cities and provide lessons to local planning practice.