Early Stages Of Building Design Research Articles

Application of multimodal learning in daylight provision and view quality assessment of residential building layouts

Optimizing the layout of residential buildings based on daylight performance and view quality is crucial to visual comfort and well-being of building occupants. Machine Learning (ML) methods offer valuable support for performance-based decision-making process at the early-stage building design. In this study, a novel workflow is introduced to integrate ML models into the architectural design process. With the designer’s input floor layout designs, the presented multimodal ML model predicts daylight provision and view quality, which are then translated into practical visual representations by a post-processing step. This approach allows input designs to be evaluated by the ML model, leading to enhanced design decisions while preserving the designer’s autonomy. Results for the best-performing model, implementing ResNet50 and a fully connected network, led to a Mean Square Error (MSE) of 0.0440 and 0.0478, and an R2 score of 0.7411 and 0.7815 for the daylight and view metrics, respectively. The results of the daylight and view predictive models are further interpreted according to different apartment categories and at various resolutions. These results indicate that the method could be viable for predicting daylight provision and view quality in early design tools, providing designers with faster feedback that supports informed decision-making during design iterations. Ultimately, the challenges of the study and further improvements are discussed.

Evolving multi-objective optimization framework for early-stage building design: Improving energy efficiency, daylighting, view quality, and thermal comfort

Evolving multi-objective optimization framework for early-stage building design: Improving energy efficiency, daylighting, view quality, and thermal comfort

Advancing building energy efficiency: A deep learning approach to early-stage prediction of residential electric consumption

Enhancing building energy efficiency underscores the critical need for innovative predictive models to mitigate environmental issues from high energy consumption, especially in residential areas with air-conditioning and heating ventilation systems. This study introduces the use of Long Short-Term Memory (LSTM) networks for early prediction of residential electric consumption, representing a significant innovation in the field. Unlike traditional Deep Neural Network (DNN) and Artificial Neural Network (ANN) models, Long Short-Term Memory networks efficiently process time-series data, predicting future energy usage with unmatched accuracy. The Long Short-Term Memory model exhibited superior training efficiency, requiring only 2.69 s for over 500 test cases, outperforming Deep Neural Network and Artificial Neural Network models, which took 5.26 and 3.88 s, respectively. Its predictive accuracy, evidenced by an R-squared value of 0.97, surpasses the 0.95 and 0.92 of Deep Neural Network and Artificial Neural Network models, respectively. This breakthrough enables accurate predictions of annual energy usage before construction starts and aids in identifying energy efficiency improvements early in the design process. Applying Long Short-Term Memory networks in this context marks a substantial advancement in predictive modeling for building energy consumption, equipping architects and engineers with a vital tool for designing energy-efficient buildings from the beginning. The innovation and quantitatively proven effectiveness of the Long Short-Term Memory model highlight its potential to revolutionize early-stage building design strategies, filling a crucial gap in the existing literature.

A predictive model for daylight performance based on multimodal generative adversarial networks at the early design stage

In the early building design stage, machine learning-based surrogate models demonstrate significant advantages in rapidly evaluating design performance compared to conventional simulation software. However, due to network limitations, current models struggle to incorporate comprehensive building information, leading to undesired generalizability in adapting to design variations. This study proposes a multimodal Generative Adversarial Network (GAN)-based surrogate model, representing building features with combined multimodal data of images and vectors. Geometric features on the plan and façade are translated into grayscale maps, indicating the potential for daylight reception from each viewpoint, while material properties and weather features are extracted as vectors, such as reflectance, transmittance, sun position and sky conditions. To satisfy the demands of multimodal inputs, the multimodal feature fusion block, the vector-based feature encoding block, and the feature reinforcement block are introduced. These components aim to promote the deep integration of information from different modalities, balance the influences of features across different dimensional scales, and ensure the integrity of the information. The model's validity was verified on the RPLAN database, predicting illumination distribution at the whole-building hierarchy instead of the single-room hierarchy. The results indicate that the multimodal GAN has a Mean Squared Error of 8.129, a Mean Absolute Percentage Error of 0.135, and a Structural Similarity Index of 0.907 on the test set. Meanwhile, this approach saved 73.03% of computing time compared to simulation methods. Boasting strengths in generalizability, speed, and accuracy, the model provides effective support for daylight organization in the early stage of building design, without being confined by variable design scenarios.

Predicting whole-life carbon emissions for buildings using different machine learning algorithms: A case study on typical residential properties in Cornwall, UK

Whole-life carbon emissions (WLCE) studies are critical in assessing the environmental impact of buildings and promoting sustainable design practices. However, existing methods for estimating WLCE are time-consuming and data-intensive, limiting their usefulness in the early building design stages. In response to this, this research introduces a novel approach by harnessing various machine learning algorithms to predict WLCE and WLCE intensity (normalised by floor area) for buildings. To evaluate the suitability of machine learning algorithms, we conducted an experiment involving ten algorithms to build the prediction models. These models were trained using data from 150 typical residential properties in Cornwall, UK, along with 28 features obtained from a comprehensive survey, including floor area, heating type, and occupant characteristics. The ten algorithms include Multiple Linear Regression, and non-linear algorithms such as Decision Tree, Random Forest. Performance evaluation metrics, such as coefficient of determination (R2), mean absolute error (MAE), means squared error (MSE), root-mean-square error (RMSE), and elapsed time, were employed. Our research contributes to the field by showcasing the effectiveness of machine learning models in predicting building WLCE. We reveal that all the tested machine learning algorithms have the capability to predict WLCE and WLCE intensity, non-linear models outperform linear ones, and the Random Forest (RF) model demonstrates superior performance in terms of accuracy, stability, and efficiency. This research encourages the integration of life cycle studies into the early design stage, even within tight building design schedules, offering practical guidance to architects and designers. Furthermore, these results also benefit a wide range of stakeholders, not only the architects but also the engineers, policymakers, and life cycle assessment (LCA) researchers, contributing to the advancement of data-driven sustainability approaches within the building sector.

The GHG Emission Timeline – Integrating sustainability assessment into the early building design stage

To address the challenges of integrating sustainability assessment such as life cycle assessment (LCA) in the early building design stage, we propose a new concept: The Greenhouse gas (GHG) Emission Timeline. The concept is derived from researching robustness assessment methods and personal experiences from teaching. Rather than aggregating environmental aspects into a single number, with the Timeline we want to highlight the temporality of GHG emissions in the context of ongoing transformation processes. Similarly to the previously proposed Material Pyramid for comparing the CO2 footprint of different materials, the Timeline is a pedagogical tool to visualize quantities, dynamics, and uncertainties aiming to provide a common ground for discussing sustainability in the early building design stage. The Timeline is compiled in a few simple steps with readily available resources. Hence, it does not need prior expert knowledge. The concept, as well as the first application examples of the Timeline from an architectural design studio at ETH Zurich are presented and discussed. By using GHG emission calculations for the compilation of a historic timeline, students created new lenses that addressed sustainability from a holistic viewpoint beyond GHG emissions.

Environmental product declaration (EPD) usage in early building design stages: Review of effects on the environmental life cycle of a multi-residential building

The building sector has seen recent growth in the number of published environmental product declarations (EPDs). EPDs share environmental data of construction materials, which can help building practitioners prioritize products with lower environmental impacts. However, EPDs rely on varying assumptions within their life cycle assessment (LCA). This study aimed to evaluate the use of EPDs as a data source instead of a generic data source and its effect on the life cycle impacts of a multi-residential building. This study focused on 19 North American EPDs of structural wood products. The impact assessment results found in the EPDs were compared to the Ecoinvent V3.8 database. The findings of the present study suggest that EPDs can generally be used without distinction compared to the data in the Ecoinvent V3.8 database. However, a few data were found to be outliers. In addition, EPDs of structural wood products only disclosed its manufacturing stage. Other life cycle stages, such as transport of the construction product, can have a significant impact on the building’s LCA. Therefore, using EPDs to assess building impacts is recommended over their direct comparison for practitioners to make more comprehensive decisions towards embodied impacts of buildings.

Calculation of embodied GHG emissions in early building design stages using BIM and NLP-based semantic model healing

To reach the goals of limiting global warming, the embodied greenhouse gas (GHG) emissions of new buildings need to be quantified and optimized in the very early design stages, during which design decisions significantly influence the success of projects in achieving their performance goals. Semantically rich building information models (BIM) enable to perform an automated quantity take-off of the relevant elements for calculating a whole building life cycle assessment (LCA). However, imprecise type and property information often found in today’s BIM practice hinders a seamless processing for downstream applications. At the same time, the early design stages are characterized by high uncertainty due to the lack of information and knowledge, making a holistic and consistent LCA for supporting design decisions and optimizing performance challenging. In assessing this often vague information, it is essential to consider different levels of element and material information for matching BIM to LCA data. For example, the structural properties of concrete are not yet defined in early design stages and should instead be considered as a range of material options due to different compressive strength classes.This paper presents a novel methodology for automatically matching the coarse information available in BIM models of the early design stages to the respective entries in LCA databases as a basis for a fully automated calculation process of the embodied GHG emissions of new buildings. This approach solves the existing gap in the automation process of manually enriching BIM models and adding information of LCA data and missing layers of vague models. In more detail, the proposed method is based on Natural Language Processing (NLP), using different strategies to increase performance in matching elements and materials from a BIM model to a knowledge database to enrich environmental indicators of commonly used elements’ materials. The knowledge database contains all missing information for LCAs and has different levels of information for a range of several potential design options of elements and materials, including their dependencies. Accordingly, this paper investigates multiple NLP techniques and evaluates the performance of state-of-the-art deep learning models such as GermaNet, SpaCy, or BERT. Following this, the most performant NLP approach is used to provide an automatic workflow for matching Industry Foundation Classes (IFC) elements to the knowledge database, facilitating a seamless LCA in the early stages of design. For five different case studies, the performances of the proposed matching method are analyzed. Finally, one case study is selected to compare the embodied emissions results to those of the conventional process.

An interactive assessment framework for residential space layouts using pix2pix predictive model at the early-stage building design

PurposeIn this study, a novel framework based on deep learning models is presented to assess energy and environmental performance of a given building space layout, facilitating the decision-making process at the early-stage design.Design/methodology/approachA methodology using an image-based deep learning model called pix2pix is proposed to predict the overall daylight, energy and ventilation performance of a given residential building space layout. The proposed methodology is then evaluated by being applied to 300 sample apartment units in Tehran, Iran. Four pix2pix models were trained to predict illuminance, spatial daylight autonomy (sDA), primary energy intensity and ventilation maps. The simulation results were considered ground truth.FindingsThe results showed an average structural similarity index measure (SSIM) of 0.86 and 0.81 for the predicted illuminance and sDA maps, respectively, and an average score of 88% for the predicted primary energy intensity and ventilation representative maps, each of which is outputted within three seconds.Originality/valueThe proposed framework in this study helps upskilling the design professionals involved with the architecture, engineering and construction (AEC) industry through engaging artificial intelligence in human–computer interactions. The specific novelties of this research are: first, evaluating indoor environmental metrics (daylight and ventilation) alongside the energy performance of space layouts using pix2pix model, second, widening the assessment scope to a group of spaces forming an apartment layout at five different floors and third, incorporating the impact of building context on the intended objectives.

BIM Based Normative Calculations for Early Stages of Building Design

This paper describes research developed in automatic of normative calculations using BIM technologies for the purpose of supporting design decisions based in engineering data, such systems are an important design assessment parameter when performing design decisions, and influence in the performance of the building in early stages of design. Our research concentrates in developing computational technologies to allow computer software to implement normative calculation to support designer’s capabilities to perform design decisions, this is done in the domain of ventilation systems engineering. We describe here new methodologies for embedding engineering domain heuristics normative calculations and the associated geometric operations in contemporary Computer Aided Design (CAD) software; this is done to achieve close to real time engineering feedback, therefore, facilitating engineering base decision making during early concept architectural design workflows. This research has been developed in the context of laboratory buildings, since for these there is several well-established normative calculations regarding both design best practices and systems engineering particularly in Heating Ventilation and Air Conditioning (HVAC), particularly in ventilation.

Beginning at the End: Visualizing User Experiences in the Early Stages of Building Design

Beginning at the End: Visualizing User Experiences in the Early Stages of Building Design

Opportunities and Limitations of Building Energy Performance Simulation Tools in the Early Stages of Building Design in the UK

This research investigates the use of Building Energy Performance Simulation (BEPS) tools in the early stages of building design in UK architectural practices with a particular focus on the barriers and opportunities to their effective application and further uptake. Two primary methods of investigation were undertaken; the first was a wide survey among UK architects and architectural practices, where the responses of 418 participants were electronically gathered and analysed. A deeper understanding of the issues was developed through an analysis of the process of low-energy building design using semi-structured interviews with six representatives of well-established architectural practices in the UK. The findings reveal that while there is an increasing understanding of the importance of BEPS involvement at the early design stages, there was limited evidence of actual early implementation of BEPS tools other than a few well known but specialised tools such as Passive House Planning Package (PHPP) which were used mainly for domestic energy performance evaluation. However, many practices surveyed showed interest in achieving higher standards than the “basic” regulatory backstops, which has resulted in Passive House and BREEAM seeing increasing use in domestic and non-domestic projects respectively. Although there has been a significant increase in the development and availability of tools and methodologies for assessing building energy performance our study shows that the focus for future research needs to be shifted from the “tool development” to looking at methods of implementing and using such tools in practice at the early design stages.

Coupled EnergyPlus and CFD analysis of PCM for thermal management of buildings

Building energy simulation (BES) tools are key instruments for sizing the PCM based system in the built environment and analyzing its effect on thermal comfort and energy demand. Due to complex solidification and melting phenomena of PCM, BES tools have limitations in predicting its performance with buildings. Computational fluid dynamics (CFD) tools are also used to model the PCM, but those models are not integrated with the building simulation models. This study aims to develop a co-simulation framework between BES tool (EnergyPlus) and CFD tool (Ansys Fluent) to model the PCM integrated built environment and compare its prediction accuracy with the most popular BES tool, i.e., EnergyPlus. Three experimental case scenarios 1) Active use of PCM, 2) Passive use of PCM during natural convection and 3) Passive use of PCM during forced convection have been modeled for prediction accuracy assessment. A common accuracy index (Root Mean Square Error) is used along with temporal temperature variation for the comparison. The results highlight that the proposed co-simulation has better prediction accuracy than the BES tool for active use of PCM and passive use of PCM under forced convection. For modeling the passive use of PCM during natural convection, BES tool is recommended. Since in the extreme climatic conditions, PCM with active use and forced convection are effective compared to the passive use of PCM, this study would be useful in modeling the built environment with PCM at early building design stages for extreme climatic conditions.

Optimum window position in the building façade for high day-light performance: Empirical study in hot and dry climate

Abstract:Day-lighting studies in buildings play a major role in indoor environmental investigation and can be conducted at the early stages of building design. Window position significantly affects day-lighting performance. This paper assessed the impacts of the window position on the visual comfort through two main factors; daylight factor and light uniformity in the hot and dry climate zone. In this study different window positions have been examined to achieve optimal visual comfort, using a dynamic simulation through Vi-suit plugin for Blender 3D software that controls the external application Radiance software. The results revealed that the window position at sill start from 1.4 m of a room characterized by (4.30 m × 3.00 m × 3.00 m) is the best compromising solution that complies with the daylight factor and light uniformity standards in the indoor environment. The findings of this study provide a more detailed and comprehensive analysis of the window design for architects/designers in the early building design stages in the hot and dry climate region.

Evaluating thermal performance of double-skin facade using response factor

Modern office buildings frequently adopted Double-skin façades (DSFs) to save energy use for heating and cooling. The operable layers of a DSFs are designed to control the heat and airflow in its flow domain. The dynamic thermal properties of the operable layers should be well understood for the successful design of a DSFs. The objective of this study was to provide easy and reliable calculation method for cooling or heating load of a DSFs under dynamic weather conditions. The heat transfer in the operable layers was expressed by using the response factor which was got from field monitored data as a transfer function of incident solar radiation and exterior surface temperature at the inner glass of a DSFs. The proposed model was validated by the energy simulations with TRNSYS and field monitoring conducted during 35 days in summer, 6 August to 9 September 2012. From the results, it was found that the response factor is a very useful index to predict the thermal performance of a DSFs. The exterior surface temperature of the DSFs predicted by the response factor was fitted well with the field monitored data in both blind rolling and rolling off conditions. The mean bias error (MBE) and root mean square error (RMSE) of the predicted temperature were within 1.5% and 2.1%, respectively. The models can be helpful to evaluate the thermal performance of DSFs at the early building design stage.

Surveying the environmental life-cycle performance assessments: Practice and context at early building design stages

The international greenhouse gas agreements call for mitigations in the building industry. Thus, the number of scientific publications about life-cycle performance assessment (LCPA) follows an exponential trend since the 2000s. However, previous surveys highlighted that the use of these methods is still not a common practice. Hence, it is of primary importance to understand the gap between the research intensity, and its low-benefits on the practice. To that end, a set of questions has been compiled and spread as an online survey targeting architects and engineers at the European scale. Thanks to 500 answers, three major obstacles have been highlighted. First, there is a clear lack of demand from real estate developers in a context where there is no lifecycle performance regulation yet. Second, the high cost of the use of LCPA methods disqualifies their use at early design, where the financial risk is at its highest level. Last, there are collaboration issues between architects and engineers, decreasing the LCPA benefits. In addition to previous surveys focusing on the scientific issues of the LCA methodology only, these results provide a unique user-centred knowledge for LCPA software and method developers.

Assessing environmental performance in early building design stage: An integrated parametric design and machine learning method

Decisions made at early design stage have major impacts on buildings’ life-cycle environmental performance. However, when only a few parameters are determined in early design stages, the detailed design decisions may still vary significantly. This may cause same early design to have quite different environmental impacts. Moreover, default settings for unknown detailed design parameters clearly cannot cover all possible variations in impact, and Monte Carlo analysis is sometimes not applicable as parameters’ probability distributions are usually unknown. Thus, uncertainties about detailed design make it difficult for existing environmental assessment methods to support early design decisions.Thus, this study developed a quantitative method using parametric design technology and machine learning algorithms for assessing buildings’ environmental performance in early decision stages, considering uncertainty associated with detailed design decisions. The parametric design technology creates design scenarios dataset, then associated environmental performances are assessed using environmental assessment databases and building performance simulations. Based on the generated samples, a machine learning algorithm integrating fuzzy C-means clustering and extreme learning machine extracts the case-specific knowledge regarding designed buildings’ early design associated with environmental uncertainty. Proposed method is an alternative but more generally applicable method to previous approaches to assess building's environmental uncertainty in early design stages.

Integrating building information modeling and life cycle assessment in the early and detailed building design stages

In the early building design stage, there are numerous uncertainties due to the lack of information on materials and processes. Designers therefore cannot quantify the environmental impacts of buildings in order to evaluate the environmental performance of their designs early on. In this paper, life cycle assessment (LCA) and building information modeling (BIM) are carried out in the early and detailed building design stages. The method is applied to a residential building in Québec, Canada. The BIM is conducted with Revit, and the LCA with openLCA. To prepare the Revit outputs as the appropriate inputs of the LCA model, a functional database was developed. It includes all building assemblies, layers and possible materials commonly found in residential buildings in Québec. The ecoinvent database was used to source of life cycle inventory (LCI) data for each material. To manage information uncertainty in the early design stage, a probability function was assigned to each material. At the detailed design stage, all material types and quantities were specified in BIM file, which was used in the LCA study. The environmental impacts of the building stages and assemblies were calculated to determine the best building assembly options from an environmental perspective—a process that could guide building designers in the environmental assessments of their designs, making it possible to select more sustainable materials for each assembly and thus reduce the environmental impacts of the building.

Early predicting cooling loads for energy-efficient design in office buildings by machine learning

Energy-efficient building design has become imperative for energy conservation, emissions reduction, and life quality enhancement of occupant. Physics-based whole building energy simulation is widely used to access building energy performance, which requires large amount of information to specify values of input parameters and includes underlying assumptions. This study proposed an alternative model based on machine learning (ML) to predict cooling loads of buildings with few common parameters in the design phase. The ML models were developed and evaluated using a dataset of 243 buildings. Predicted cooling loads from these models were compared to those from the physics-based whole building energy simulation. The proposed model exhibits good agreement with the physics-based whole building energy simulation. The analytical results present that the ML models obtained the correlation coefficient (R) of 0.98–0.99, the mean absolute percentage error (MAPE) of 6.17–12.93% which shows the high agreement between observed and predicted values of cooling loads in building. Notably, the ensemble bagging artificial neural networks yielded the highest R of 0.99, the lowest root-mean-square error (RMSE) of 158.77 kW, the lowest MAE of 112.07 kW, and the lowest MAPE of 6.17% among all models in this study. This research contributes to (i) the state of the knowledge by examining various ML models that can predict cooling loads in the early building design stage; and (ii) the state of practice by providing an alternative tool in the design process through better understanding of relationships between building cooling loads and building characteristics for enhancing energy efficiency in buildings.

Target Air Change Rate Map for Naturally Ventilated Buildings in the Early Stage of Building Design

Target Air Change Rate Map for Naturally Ventilated Buildings in the Early Stage of Building Design