Khuloud Ali
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Khuloud Ali has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Ghayth Tintawi
IMAGINE Studios, Brazil
8 shared publications - Mohamad Khaled Bassma
IMAGINE Studios, Brazil
5 shared publications Mohamad Khaled Bassma
3 shared publicationsGhayth Tintawi
2 shared publications- Aftab Haider
Southwest University of Political Science and Law, China
1 shared publication - Ali Bokhari
Department of Architecture, Faculty of Engineering, Al Baha University, Al Baha, Saudi Arabia, Saudi Arabia
1 shared publication
Latest Publications
- Open Access
- 23 June 2026
- Published by MDPI AG in Preprints.org
Integrating Multi-Objective Optimization, Random Forest Learning, and SHAP-Based Explainability for Climate-Responsive Residential Envelope Design in Gulf Coastal Cities
This study presents an explainable artificial intelligence framework for climate-responsive residential envelope design in Gulf coastal cities by integrating building performance simulation, multi-objective optimization, machine learning, and explainability analysis. While previous studies have largely focused on minimizing energy consumption, limited research has simultaneously considered energy performance, capital cost, and thermal comfort within a unified and interpretable decision-support framework. The objective of this research was to identify dominant envelope design variables and derive practical design recommendations for residential buildings located in Dubai, Doha, and Manama. A two-story detached villa prototype was developed and simulated under representative coastal hot-arid climate conditions. Six envelope and operational design variables, including window-to-wall ratio (WWR), shading depth, cooling setpoint, glazing type, wall construction, and roof construction, were evaluated through a simulation-based optimization framework. A total of 600 design alternatives were generated using NSGA-II optimization and subsequently used to train Random Forest predictive models for energy use intensity (EUI), capital cost, and ASHRAE 55 thermal discomfort hours. SHAP (Shapley Additive Explanations) analysis was then applied to quantify variable importance and extract interpretable design rules. The results demonstrated strong predictive capability, with Random Forest models achieving R² values of 0.933 for EUI, 0.982 for capital cost, and 0.955 for thermal discomfort. SHAP analysis revealed that WWR was the dominant driver of energy performance, accounting for 65.2% of total feature importance, while wall construction exerted the greatest influence on capital cost. Thermal comfort was primarily governed by cooling setpoint, followed by WWR and shading depth. Dependence analysis further identified clear threshold relationships between envelope variables and performance outcomes. The proposed framework transforms optimization datasets into actionable design knowledge and provides interpretable decision support for architects, consultants, and developers seeking cost-effective and climate-responsive residential envelope solutions in Gulf coastal environments.
- 23 June 2026
- Published by MDPI AG in Preprints.org
Open AccessIntegrating Multi-Objective Optimization, Random Forest Learning, and SHAP-Based Explainability for Climate-Responsive Residential Envelope Design in Gulf Coastal Cities
This study presents an explainable artificial intelligence framework for climate-responsive residential envelope design in Gulf coastal cities by integrating building performance simulation, multi-objective optimization, machine learning, and explainability analysis. While previous studies have largely focused on minimizing energy consumption, limited research has simultaneously considered energy performance, capital cost, and thermal comfort within a unified and interpretable decision-support framework. The objective of this research was to identify dominant envelope design variables and derive practical design recommendations for residential buildings located in Dubai, Doha, and Manama. A two-story detached villa prototype was developed and simulated under representative coastal hot-arid climate conditions. Six envelope and operational design variables, including window-to-wall ratio (WWR), shading depth, cooling setpoint, glazing type, wall construction, and roof construction, were evaluated through a simulation-based optimization framework. A total of 600 design alternatives were generated using NSGA-II optimization and subsequently used to train Random Forest predictive models for energy use intensity (EUI), capital cost, and ASHRAE 55 thermal discomfort hours. SHAP (Shapley Additive Explanations) analysis was then applied to quantify variable importance and extract interpretable design rules. The results demonstrated strong predictive capability, with Random Forest models achieving R² values of 0.933 for EUI, 0.982 for capital cost, and 0.955 for thermal discomfort. SHAP analysis revealed that WWR was the dominant driver of energy performance, accounting for 65.2% of total feature importance, while wall construction exerted the greatest influence on capital cost. Thermal comfort was primarily governed by cooling setpoint, followed by WWR and shading depth. Dependence analysis further identified clear threshold relationships between envelope variables and performance outcomes. The proposed framework transforms optimization datasets into actionable design knowledge and provides interpretable decision support for architects, consultants, and developers seeking cost-effective and climate-responsive residential envelope solutions in Gulf coastal environments.
- Open Access
Simulation-Based Evolutionary Optimization of Residential Buildings for Energy and Carbon Reduction Across Warm–Humid and Coastal Hot–Arid Climates
Buildings in warm–humid and hot–arid coastal climates experience continuous cooling demand due to high solar radiation, humidity, and extended cooling seasons. Reducing operational energy use and carbon emissions through improved early-stage design is therefore essential. This study investigates a simulation-based evolutionary optimization framework to evaluate energy-efficient design strategies for residential buildings across representative warm–humid and hot–arid climates. A prototype residential building was modeled in DesignBuilder using EnergyPlus and evaluated across four locations: Singapore, Miami, Rio de Janeiro, and Jeddah. Key variables included the window-to-wall ratio, glazing type, wall and roof constructions, cooling setpoint, and HVAC system configuration. An evolutionary search process based on the NSGA-II algorithm was applied to systematically explore high-performing building configurations using energy use intensity (EUI) and operational carbon indicators. The results indicate a consistent tendency toward boundary values within the defined parameter ranges. The window-to-wall ratios consistently approached the minimum tested value (20%), while the cooling setpoints approached the upper bound (26 °C) within the defined parameter ranges. This behavior highlights the influence of solar gains and operational temperature settings on cooling demand. Low-emissivity glazing and insulated envelope assemblies were frequently associated with improved performance. Miami achieved the lowest EUI among the high-performing configurations (75.08 kWh/m2·yr; 27.55 kgCO2/m2·yr), while other locations showed higher demand due to climatic conditions. These findings emphasize the importance of parameter range selection and demonstrate the effectiveness of simulation-based evolutionary search methods in identifying high-performing configurations within defined constraints.
Open AccessSimulation-Based Evolutionary Optimization of Residential Buildings for Energy and Carbon Reduction Across Warm–Humid and Coastal Hot–Arid Climates
Buildings in warm–humid and hot–arid coastal climates experience continuous cooling demand due to high solar radiation, humidity, and extended cooling seasons. Reducing operational energy use and carbon emissions through improved early-stage design is therefore essential. This study investigates a simulation-based evolutionary optimization framework to evaluate energy-efficient design strategies for residential buildings across representative warm–humid and hot–arid climates. A prototype residential building was modeled in DesignBuilder using EnergyPlus and evaluated across four locations: Singapore, Miami, Rio de Janeiro, and Jeddah. Key variables included the window-to-wall ratio, glazing type, wall and roof constructions, cooling setpoint, and HVAC system configuration. An evolutionary search process based on the NSGA-II algorithm was applied to systematically explore high-performing building configurations using energy use intensity (EUI) and operational carbon indicators. The results indicate a consistent tendency toward boundary values within the defined parameter ranges. The window-to-wall ratios consistently approached the minimum tested value (20%), while the cooling setpoints approached the upper bound (26 °C) within the defined parameter ranges. This behavior highlights the influence of solar gains and operational temperature settings on cooling demand. Low-emissivity glazing and insulated envelope assemblies were frequently associated with improved performance. Miami achieved the lowest EUI among the high-performing configurations (75.08 kWh/m2·yr; 27.55 kgCO2/m2·yr), while other locations showed higher demand due to climatic conditions. These findings emphasize the importance of parameter range selection and demonstrate the effectiveness of simulation-based evolutionary search methods in identifying high-performing configurations within defined constraints.
- Open Access
- 25 May 2026
- Published by MDPI AG in Preprints.org
Material Sufficiency, Energy Use, and Life-Cycle Carbon in Hot-Arid Residential Buildings: A Pareto-Informed Multi-Criteria Evaluation of Envelope Design Strategies
Hot-arid residential buildings experience persistent cooling demand and increasing material intensity, yet most building-performance studies prioritize operational energy while insufficiently integrating life-cycle carbon and material sufficiency into envelope evaluation. This limits the ability to distinguish between performance gains achieved through passive design efficiency and those dependent on increased material input. This study investigates the interaction between material sufficiency, energy use, and life-cycle carbon in residential buildings across three representative hot-arid climates: Riyadh, Abu Dhabi, and Doha. A Pareto-informed multi-criteria evaluation framework was applied using a standardized mid-rise residential prototype to assess predefined envelope design strategies under consistent operational conditions. Dynamic energy simulations were conducted in DesignBuilder/EnergyPlus, while embodied carbon was quantified through a consistent material inventory approach. Baseline energy use intensity (EUI) values reached 64.98, 83.13, and 93.67 kWh/m²·year for Riyadh, Abu Dhabi, and Doha, respectively, reflecting increasing cooling demand from inland dry to humid coastal conditions. Envelope optimization reduced EUI to 47.33–72.40 kWh/m²·year, while embodied carbon ranged from 40,761.2 to 57,146.2 kgCO₂-eq per configuration. Reduced window-to-wall ratio strategies consistently achieved the most balanced performance across all climates, whereas high-glazing configurations increased energy demand, carbon emissions, and material intensity. The study operationalizes a sufficiency-oriented evaluation perspective that supports climate-responsive envelope decision-making by integrating operational and material performance within a unified comparative framework.
- 25 May 2026
- Published by MDPI AG in Preprints.org
Open AccessMaterial Sufficiency, Energy Use, and Life-Cycle Carbon in Hot-Arid Residential Buildings: A Pareto-Informed Multi-Criteria Evaluation of Envelope Design Strategies
Hot-arid residential buildings experience persistent cooling demand and increasing material intensity, yet most building-performance studies prioritize operational energy while insufficiently integrating life-cycle carbon and material sufficiency into envelope evaluation. This limits the ability to distinguish between performance gains achieved through passive design efficiency and those dependent on increased material input. This study investigates the interaction between material sufficiency, energy use, and life-cycle carbon in residential buildings across three representative hot-arid climates: Riyadh, Abu Dhabi, and Doha. A Pareto-informed multi-criteria evaluation framework was applied using a standardized mid-rise residential prototype to assess predefined envelope design strategies under consistent operational conditions. Dynamic energy simulations were conducted in DesignBuilder/EnergyPlus, while embodied carbon was quantified through a consistent material inventory approach. Baseline energy use intensity (EUI) values reached 64.98, 83.13, and 93.67 kWh/m²·year for Riyadh, Abu Dhabi, and Doha, respectively, reflecting increasing cooling demand from inland dry to humid coastal conditions. Envelope optimization reduced EUI to 47.33–72.40 kWh/m²·year, while embodied carbon ranged from 40,761.2 to 57,146.2 kgCO₂-eq per configuration. Reduced window-to-wall ratio strategies consistently achieved the most balanced performance across all climates, whereas high-glazing configurations increased energy demand, carbon emissions, and material intensity. The study operationalizes a sufficiency-oriented evaluation perspective that supports climate-responsive envelope decision-making by integrating operational and material performance within a unified comparative framework.
- Open Access
- 25 May 2026
- Published by MDPI AG in Preprints.org
AI‐Driven Multi‐City Optimization of Glazing and Shading Systems for Building Energy Use and Operational Carbon Reduction Across Global Climate Zones
Buildings account for a major share of global energy demand and operational carbon emissions, underscoring the importance of climate-responsive façade design in sustainable architecture. Façade parameters such as glazing ratio, shading systems, and glazing properties strongly influence thermal performance of buildings; however, most optimization studies remain confined to single climates and rarely provide practical design guidance. This study introduces an AI-assisted optimization framework for evaluating façade performance across four contrasting climate zones: Abu Dhabi (hot-arid), Singapore (hot-humid), Athens (Mediterranean), and Berlin (temperate). A standardized five-story residential prototype was modeled in DesignBuilder using the EnergyPlus simulation engine. Window-to-Wall Ratio, orientation, shading depth, and glazing type were optimized using the Non-Dominated Sorting Genetic Algorithm II to minimize Energy Use Intensity (EUI) and operational CO₂ emissions while maintaining thermal comfort through ASHRAE 55 discomfort-hour constraints. The optimized solutions reduced EUI by approximately 54% in Abu Dhabi, 56% in Singapore, 43% in Athens, and 40% in Berlin relative to baseline conditions. A post-optimization AI-assisted rule-based interpretation layer applied to identify recurring façade parameter patterns among Pareto-optimal solutions revealed a systematic transition from low-glazing, deep-shading solutions in hot climates toward higher glazing ratios with limited shading in temperate environments. These findings indicate that façade optimization is climate-dependent and that AI-assisted workflows can support interpretable, performance-driven architectural decision-making.
- 25 May 2026
- Published by MDPI AG in Preprints.org
Open AccessAI‐Driven Multi‐City Optimization of Glazing and Shading Systems for Building Energy Use and Operational Carbon Reduction Across Global Climate Zones
Buildings account for a major share of global energy demand and operational carbon emissions, underscoring the importance of climate-responsive façade design in sustainable architecture. Façade parameters such as glazing ratio, shading systems, and glazing properties strongly influence thermal performance of buildings; however, most optimization studies remain confined to single climates and rarely provide practical design guidance. This study introduces an AI-assisted optimization framework for evaluating façade performance across four contrasting climate zones: Abu Dhabi (hot-arid), Singapore (hot-humid), Athens (Mediterranean), and Berlin (temperate). A standardized five-story residential prototype was modeled in DesignBuilder using the EnergyPlus simulation engine. Window-to-Wall Ratio, orientation, shading depth, and glazing type were optimized using the Non-Dominated Sorting Genetic Algorithm II to minimize Energy Use Intensity (EUI) and operational CO₂ emissions while maintaining thermal comfort through ASHRAE 55 discomfort-hour constraints. The optimized solutions reduced EUI by approximately 54% in Abu Dhabi, 56% in Singapore, 43% in Athens, and 40% in Berlin relative to baseline conditions. A post-optimization AI-assisted rule-based interpretation layer applied to identify recurring façade parameter patterns among Pareto-optimal solutions revealed a systematic transition from low-glazing, deep-shading solutions in hot climates toward higher glazing ratios with limited shading in temperate environments. These findings indicate that façade optimization is climate-dependent and that AI-assisted workflows can support interpretable, performance-driven architectural decision-making.
- Open Access
- 30 March 2026
- Published by MDPI AG in Preprints.org
Governing Environmental Decisions with Artificial Intelligence: Algorithmic Sustainability for Accountability and Lifecycle Impact, a Policy Review
Artificial intelligence is increasingly incorporated into public environmental decision-making processes, directing the classification of risks, the distribution of resources, and the implementation of regulatory measures. Current policy discussions tend to emphasize predictive performance and ethical principles. Institutional conditions play a lesser role in determining the decision authority of algorithm-generated outputs. This policy review bridges this gap by examining environmental artificial intelligence as part of administrative decision processes rather than as neutral analytical software. Building on recent work on algorithmic sustainability, the review assesses how existing governance instruments engage with lifecycle environmental impacts, organizational responsibility, and procedural legitimacy. The analysis of international frameworks indicates that transparency and risk-based governance are receiving increasing attention, particularly in relation to their effectiveness in addressing environmental concerns and ensuring accountability in AI applications. At the same time, lifecycle environmental impacts remain weakly integrated into decision justification and oversight, which undermines the effectiveness of governance frameworks in addressing the environmental impacts associated with AI technologies. To overcome this limitation, the paper proposes a way of examining how artificial intelligence is integrated into decision processes. The results show that effective governance depends on aligning institutional design with sustainability objectives at the points where algorithmic outputs affect public decisions.
- 30 March 2026
- Published by MDPI AG in Preprints.org
Open AccessGoverning Environmental Decisions with Artificial Intelligence: Algorithmic Sustainability for Accountability and Lifecycle Impact, a Policy Review
Artificial intelligence is increasingly incorporated into public environmental decision-making processes, directing the classification of risks, the distribution of resources, and the implementation of regulatory measures. Current policy discussions tend to emphasize predictive performance and ethical principles. Institutional conditions play a lesser role in determining the decision authority of algorithm-generated outputs. This policy review bridges this gap by examining environmental artificial intelligence as part of administrative decision processes rather than as neutral analytical software. Building on recent work on algorithmic sustainability, the review assesses how existing governance instruments engage with lifecycle environmental impacts, organizational responsibility, and procedural legitimacy. The analysis of international frameworks indicates that transparency and risk-based governance are receiving increasing attention, particularly in relation to their effectiveness in addressing environmental concerns and ensuring accountability in AI applications. At the same time, lifecycle environmental impacts remain weakly integrated into decision justification and oversight, which undermines the effectiveness of governance frameworks in addressing the environmental impacts associated with AI technologies. To overcome this limitation, the paper proposes a way of examining how artificial intelligence is integrated into decision processes. The results show that effective governance depends on aligning institutional design with sustainability objectives at the points where algorithmic outputs affect public decisions.
- Open Access
- 10 March 2026
- Published by MDPI AG in Preprints.org
Algorithmic Sustainability: Governance Conditions for AI-Driven Environmental Decision-Making
Environmental governance is no longer shaped only by expert judgement or statutory procedure. In recent years, algorithmic systems have begun to mediate how data are interpreted, to shape the scoring of risk, and to influence the way policy priorities are established. These systems now affect regulatory analysis. They also inform climate adaptation modelling and guide decisions on land use while supporting sustainability monitoring. Although artificial intelligence (AI) is often presented as a means to improve environmental outcomes, its deployment introduces lifecycle emissions while raising concerns about institutional opacity and exposing risks related to public legitimacy that remain insufficiently embedded in current governance frameworks. This article advances the concept of algorithmic sustainability and treats it as a condition of governance rather than a technical attribute of computational tools. Drawing on a structured qualitative synthesis of interdisciplinary research, the study identifies three conditions required for sustainable AI use in environmental decision systems. One concerns lifecycle carbon integrity. Another addresses institutional accountability. A third focuses on alignment with public value. These conditions are translated into a tiered Environmental AI Impact Assessment model (EAIA) designed to support regulatory oversight while remaining institutionally feasible. By separating computing-related effects from operational consequences and from wider systemic implications, the framework clarifies how algorithmic applications may improve environmental performance while still generating rebound pressures that threaten broader sustainability goals.
- 10 March 2026
- Published by MDPI AG in Preprints.org
Open AccessAlgorithmic Sustainability: Governance Conditions for AI-Driven Environmental Decision-Making
Environmental governance is no longer shaped only by expert judgement or statutory procedure. In recent years, algorithmic systems have begun to mediate how data are interpreted, to shape the scoring of risk, and to influence the way policy priorities are established. These systems now affect regulatory analysis. They also inform climate adaptation modelling and guide decisions on land use while supporting sustainability monitoring. Although artificial intelligence (AI) is often presented as a means to improve environmental outcomes, its deployment introduces lifecycle emissions while raising concerns about institutional opacity and exposing risks related to public legitimacy that remain insufficiently embedded in current governance frameworks. This article advances the concept of algorithmic sustainability and treats it as a condition of governance rather than a technical attribute of computational tools. Drawing on a structured qualitative synthesis of interdisciplinary research, the study identifies three conditions required for sustainable AI use in environmental decision systems. One concerns lifecycle carbon integrity. Another addresses institutional accountability. A third focuses on alignment with public value. These conditions are translated into a tiered Environmental AI Impact Assessment model (EAIA) designed to support regulatory oversight while remaining institutionally feasible. By separating computing-related effects from operational consequences and from wider systemic implications, the framework clarifies how algorithmic applications may improve environmental performance while still generating rebound pressures that threaten broader sustainability goals.
- Top Cited PapersOpen Access
AI-Guided Evolutionary Optimization of Passive Solar Design for Residential Heating Across Distinct Climate Zones
Achieving meaningful reductions in residential heating demand requires design strategies that can respond to climate-specific solar availability and envelope performance. Although passive solar principles are well established, their effectiveness remains highly context-dependent, and simplified prescriptive approaches may not capture interactions across different climates. This study presents an AI-guided evolutionary optimization framework for passive solar residential design, focusing exclusively on the reduction in annual space heating demand under standardized assumptions. A standardized single-story residential prototype is simulated across three climatic contexts: hot–dry (Riyadh), temperate (Barcelona), and cold (Toronto). Dynamic building performance simulations are conducted using EnergyPlus, coupled with DesignBuilder’s built-in Non-Dominated Sorting Genetic Algorithm II (NSGA-II) evolutionary optimization engine. Envelope-related variables, including the window-to-wall ratio, orientation, glazing configuration, and thermal mass, are optimized with a single objective: minimizing the annual heating load under idealized heating conditions. The results demonstrate substantial climate-dependent reductions in heating demand. In Toronto, the annual heating demand is reduced from approximately 16,900 kWh to 9600 kWh (≈43%). In Barcelona, a reduction from approximately 5650 kWh to 1990 kWh (≈65%) is achieved, while in Riyadh, heating demand is reduced from approximately 990 kWh to 39 kWh (>95%). The optimized solutions reveal distinct climate-specific design logic rather than universal passive rules. The results demonstrate that evolutionary optimization can support early-stage envelope design by revealing climate-specific heating strategies under clearly defined and comparable assumptions.
Top Cited PapersOpen AccessAI-Guided Evolutionary Optimization of Passive Solar Design for Residential Heating Across Distinct Climate Zones
Achieving meaningful reductions in residential heating demand requires design strategies that can respond to climate-specific solar availability and envelope performance. Although passive solar principles are well established, their effectiveness remains highly context-dependent, and simplified prescriptive approaches may not capture interactions across different climates. This study presents an AI-guided evolutionary optimization framework for passive solar residential design, focusing exclusively on the reduction in annual space heating demand under standardized assumptions. A standardized single-story residential prototype is simulated across three climatic contexts: hot–dry (Riyadh), temperate (Barcelona), and cold (Toronto). Dynamic building performance simulations are conducted using EnergyPlus, coupled with DesignBuilder’s built-in Non-Dominated Sorting Genetic Algorithm II (NSGA-II) evolutionary optimization engine. Envelope-related variables, including the window-to-wall ratio, orientation, glazing configuration, and thermal mass, are optimized with a single objective: minimizing the annual heating load under idealized heating conditions. The results demonstrate substantial climate-dependent reductions in heating demand. In Toronto, the annual heating demand is reduced from approximately 16,900 kWh to 9600 kWh (≈43%). In Barcelona, a reduction from approximately 5650 kWh to 1990 kWh (≈65%) is achieved, while in Riyadh, heating demand is reduced from approximately 990 kWh to 39 kWh (>95%). The optimized solutions reveal distinct climate-specific design logic rather than universal passive rules. The results demonstrate that evolutionary optimization can support early-stage envelope design by revealing climate-specific heating strategies under clearly defined and comparable assumptions.
- Open Access
- 25 February 2026
- Published by MDPI AG in Preprints.org
AI-Guided Evolutionary Optimization of Passive Solar Design for Residential Heating Across Distinct Climate Zones
Achieving meaningful reductions in residential heating demand requires design strategies that can respond to climate-specific solar availability and envelope performance. Although passive solar principles are well established, their effectiveness remains highly context-dependent, and simplified prescriptive approaches may not capture interactions across different climates. This study presents an AI-guided evolutionary optimization framework for passive solar residential design, focusing exclusively on the reduction in annual space heating demand under standardized assumptions. A standardized single-story residential prototype is simulated across three climatic contexts: hot–dry (Riyadh), temperate (Barcelona), and cold (Toronto). Dynamic building performance simulations are conducted using EnergyPlus, coupled with DesignBuilder’s built-in NSGA-II evolutionary optimization engine. Envelope-related variables, including the window-to-wall ratio, orientation, glazing configuration, and thermal mass, are optimized using a single objective: minimizing the annual heating load under idealized heating conditions. The results demonstrate substantial climate-dependent reductions in heating demand. In Toronto, the annual heating demand is reduced from approximately 16,900 kWh to 9600 kWh (≈43%). In Barcelona, a reduction from approximately 5650 kWh to 1990 kWh (≈65%) is achieved, while in Riyadh, heating demand is reduced from approximately 990 kWh to 39 kWh (>95%). The optimized solutions reveal distinct climate-specific design logic rather than universal passive rules. The results demonstrate that evolutionary optimization can support early-stage envelope design by revealing climate-specific heating strategies under clearly defined and comparable assumptions.
- 25 February 2026
- Published by MDPI AG in Preprints.org
Open AccessAI-Guided Evolutionary Optimization of Passive Solar Design for Residential Heating Across Distinct Climate Zones
Achieving meaningful reductions in residential heating demand requires design strategies that can respond to climate-specific solar availability and envelope performance. Although passive solar principles are well established, their effectiveness remains highly context-dependent, and simplified prescriptive approaches may not capture interactions across different climates. This study presents an AI-guided evolutionary optimization framework for passive solar residential design, focusing exclusively on the reduction in annual space heating demand under standardized assumptions. A standardized single-story residential prototype is simulated across three climatic contexts: hot–dry (Riyadh), temperate (Barcelona), and cold (Toronto). Dynamic building performance simulations are conducted using EnergyPlus, coupled with DesignBuilder’s built-in NSGA-II evolutionary optimization engine. Envelope-related variables, including the window-to-wall ratio, orientation, glazing configuration, and thermal mass, are optimized using a single objective: minimizing the annual heating load under idealized heating conditions. The results demonstrate substantial climate-dependent reductions in heating demand. In Toronto, the annual heating demand is reduced from approximately 16,900 kWh to 9600 kWh (≈43%). In Barcelona, a reduction from approximately 5650 kWh to 1990 kWh (≈65%) is achieved, while in Riyadh, heating demand is reduced from approximately 990 kWh to 39 kWh (>95%). The optimized solutions reveal distinct climate-specific design logic rather than universal passive rules. The results demonstrate that evolutionary optimization can support early-stage envelope design by revealing climate-specific heating strategies under clearly defined and comparable assumptions.
- Open Access
- 25 December 2025
Climate-Resilient Coastal Housing: An Adaptive Architectural Framework for Flood-Responsive Design
Coastal settlements face accelerating climate pressures, including the rise of sea levels, storm surges, and compound pluvial and tidal events. All of those factors can increasingly disrupt the residential built environment. Therefore, despite extensive engineering research, current flood-resilience approaches remain fragmented and rarely translate climate-risk evidence into architectural decision-making. This study introduces an Adaptive Architectural Framework for Flood-Responsive Design (AAF-Flood). This framework addresses the persistent gap between hazard analysis and the operational design logic of coastal housing. The research methodology employs an interpretive mixed-evidence approach combined with recent climate data on sea-level rise and extreme rainfall. The methodology also incorporates records of past storm surges, floods, and intensive rainfall events; examines how building envelopes perform under coastal exposure; reviews evidence on wetlands and vegetated buffers; and includes an institutional assessment. The development of this framework is guided by a structured four-stage workflow that includes diagnosis, translation, integration, and evolution. The AAF-Flood operates across five resilience dimensions and three representative housing typologies. The paper also reviews four documented case studies and interprets the data in relation to future conditions represented by RCP 4.5 and RCP 8.5 climate pathways. The framework also integrates spatial configuration, material durability, ecological interfaces, and governance feasibility within a single architectural methodology. Findings indicate that early incorporation of adaptive morphology, ground-floor designs that can safely flood when necessary, and application of finishes and structural components designed for high-salinity environments significantly enhance long-term habitability and reduce disruption during both moderate and extreme flood events. The paper contributes a method for converting climate projections into architectural guidance applicable at both building and community scales. This guidance supports the design of new housing and the adaptation of existing structures. Ultimately, the AAF-Flood provides actionable direction for architects, planners, and policymakers confronting rapidly evolving coastal risk.
- 25 December 2025
Open AccessClimate-Resilient Coastal Housing: An Adaptive Architectural Framework for Flood-Responsive Design
Coastal settlements face accelerating climate pressures, including the rise of sea levels, storm surges, and compound pluvial and tidal events. All of those factors can increasingly disrupt the residential built environment. Therefore, despite extensive engineering research, current flood-resilience approaches remain fragmented and rarely translate climate-risk evidence into architectural decision-making. This study introduces an Adaptive Architectural Framework for Flood-Responsive Design (AAF-Flood). This framework addresses the persistent gap between hazard analysis and the operational design logic of coastal housing. The research methodology employs an interpretive mixed-evidence approach combined with recent climate data on sea-level rise and extreme rainfall. The methodology also incorporates records of past storm surges, floods, and intensive rainfall events; examines how building envelopes perform under coastal exposure; reviews evidence on wetlands and vegetated buffers; and includes an institutional assessment. The development of this framework is guided by a structured four-stage workflow that includes diagnosis, translation, integration, and evolution. The AAF-Flood operates across five resilience dimensions and three representative housing typologies. The paper also reviews four documented case studies and interprets the data in relation to future conditions represented by RCP 4.5 and RCP 8.5 climate pathways. The framework also integrates spatial configuration, material durability, ecological interfaces, and governance feasibility within a single architectural methodology. Findings indicate that early incorporation of adaptive morphology, ground-floor designs that can safely flood when necessary, and application of finishes and structural components designed for high-salinity environments significantly enhance long-term habitability and reduce disruption during both moderate and extreme flood events. The paper contributes a method for converting climate projections into architectural guidance applicable at both building and community scales. This guidance supports the design of new housing and the adaptation of existing structures. Ultimately, the AAF-Flood provides actionable direction for architects, planners, and policymakers confronting rapidly evolving coastal risk.