
Thomas WortmannUniversity of Stuttgart · Institute for Computational Design and Construction
Thomas Wortmann
PhD (Architecture and Sustainable Design) MSc (Design and Computation) MArch
About
81
Publications
123,117
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,218
Citations
Introduction
I am an architect with extensive experience in computational design, performance simulation and optimization. I have developed Opossum, a machine-learning-based optimization tool for Grasshopper, a parametric modelling platform. I recently completed my PhD. My thesis tests the performance of different optimization methods on problems from structure, energy and daylighting and aims to better integrate optimization into design processes via a novel, interactive visualization method.
Additional affiliations
September 2018 - August 2020
January 2014 - August 2018
Publications
Publications (81)
The integration of robots in the construction industry is an important requirement for urgently needed improvements in productivity and sustainability. This integration calls for new perspectives on human-robot collaboration (HRC) to retain skilled staff, including a new and diverse work-force, support skills and decision-making while considering c...
The Architecture, Engineering, and Construction (AEC) industry
faces increasing demand for customized products and is undergoing
transformation through Industry 4.0, necessitating adaptable
production systems. Digital twins—virtual counterparts of physical
systems—enable real-time synchronization, monitoring, and
optimization of construction proces...
In the realm of Industry 4.0, significant changes have unfolded across various sectors, notably in construction, driven by the adoption of digitisation and automation. This transformation demands a reassessment of traditional practices within the Architectural, Engineering, and Construction (AEC) industry. In response, the concept of Co-Design has...
Automating robotic assembly in architectural construction is challenging due to material uncertainties and the buildup of tolerance experienced in assembling many parts. Implementing AI technologies, including various machine learning algorithms in robotic assembly, has demonstrated significant potential for robots to respond to this uncertainty. T...
The paper explores integrating cyber-physical systems in construction, targeting workforce shortages, productivity issues, and environmental concerns. It highlights the shift towards human-robot collaboration (HRC) to enhance productivity and safety. However, HRC implementation in prefabrication and construction encounters challenges like low produ...
This study explores the potential impact of geometric configurations on the growth and mechanical properties of 3D-printed Mycelium-Based Composites (MBCs). Through a combination of digital exploration, physical experimentation, and data analysis, the study examines how geometrical parametric manipulation may affect MBCs growth and mechanical prope...
The densification of urban spaces globally has contributed to a need for design tools supporting the planning of more sustainable, efficient, and liveable cities. Urban Design Optimisation (UDO) responds to this challenge by providing a means to explore many design solutions for a district, evaluate multiple objectives, and make informed selections...
In architectural design optimization, fitness landscapes are used to visualize design space parameters in relation to one or more objective functions for which they are being optimized. In our design study with domain experts, we developed a visual analytics framework for exploring and analyzing fitness landscapes spanning data, projection, and vis...
It is widely recognized that the sustainability of the built environment is one of the key strategies to tackle global crises such as climate change, resource depletion, and human health. An environmentally driven approach to architectural design and urban planning through simulations has been around for many decades. However, architects and planne...
Several assessment methodologies have been proposed to measure the environmental impact of buildings. However, these methodologies require processing data which is often not available or requires a high integration effort. In this paper, we propose an ontology to describe the use and reuse of prefabricated components in buildings. This ontology des...
This project showcases a use case away from most other research in the field of generative AI in architecture. We present a workflow to generate new, three-dimensional spatial configurations of buildings by sampling the latent space of a graph auto- encoder. Graph representations of three-dimensional buildings can store more data and hence reduce t...
Sustainable design is no longer an emerging debate. Data-driven urban and architectural design faces several potential threats related to airflow modelling, including extreme wind environments, pollutant emissions, and the potential for new wind energy in design. Designers require advanced design tools to address these airflow modelling challenges....
Industry 4.0 has the potential to revolutionise design-to-fabrication processes in the Architecture, Engineering, and Construction (AEC) industry. However, early adoption of Industry 4.0 technology has led to challenges related to data consistency, interoperability, and collaboration among stakeholders. To address these challenges of interoperabili...
This paper proposes a computational design education approach where students learn to develop their own geometric and logical workflows beyond specific software and platform. The course’s objectives are to familiarize architecture students with computational geometry, foster computational thinking that stays relevant over time, and promote democrat...
Die aktuelle Generation von Planern ist mit der Aufgabe konfrontiert, neue, nachhaltigere Bausysteme zu entwickeln, um der Problematik der Ressourcenknappheit, der Verstädterung, dem Klima‐, aber auch dem demografischen Wandel entgegenzuwirken. Hierbei ist die Frage nach deren effizienter Herstellung unter Nutzung nachwachsender Rohstoffe in den Fo...
The integration of data from various disciplines, including requirements and regulations, is essential in the co-design of buildings. Constraints that arise during design, fabrication, or construction are mainly considered in the later stages of the design process. This often leads to costly revisions during fabrication or construction. While there...
The design of mass housing projects, with their complex array of apartment types and constraints, can be challenging for architects. Automated-organizing programs can assist in exploring various design alternatives, but the computational cost of checking all possible building organizations grows exponentially. This paper describes a method that uti...
Sustainable design requires holistic decision making already in the feasibility stage. One critical aspect of a buildingś sustainability is its operational energy consumption, but energy simulations typically are too time‐consuming for early, fast‐paced design phases. Data‐based, Machine Learning models – so called surrogates – can replace time‐con...
Sustainable design requires holistic decision makingalready in the feasibility stage. One critical aspect of abuildings' sustainability is its operational energyconsumption, but energy simulations typically are tootime-consuming for early, fast-paced design phases.Data-based, Machine Learning models--so calledsurrogates--can replace time-consuming...
This research proposes a design to fabrication data framework for multi-actor fabrication environments with robotic and human actors. The framework generates and exchanges fabrication data between the design elements and the fabrication environment. It features a uniform task data model to represent all processes in the fabrication procedure and li...
Design or construction constraints are often considered only in later phases of a linear design process, which leads to costly revisions during construction. Knowledge bases can include logic rules to check constraints and are a powerful tool for representing knowledge on the Semantic Web. Knowledge bases contain facts and rules. The Buildings and...
AI planning aims to automate the reasoning process that underlies the plan formulation
to achieve a particular goal for a particular problem. Research in this field has focused on symbolic methods -which represent knowledge with human readable symbols- to efficiently and systematically produce plans, i.e., sequences of actions to be performed, from...
Der Aufsatz bietet eine Übersicht über aktuelle Methoden der Datenintegration, künstlichen Intelligenz (KI), Optimierung und Regelungstechnik und ihre (potenziellen) Anwendungen in Gebäudeplanung und Bau. Die Übersicht behandelt sowohl symbolische KI‐Methoden als auch subsymbolische KI‐Methoden bzw. maschinelles Lernen. Der Aufsatz stellt diese Met...
In the building industry, disciplines have specific requirements for capturing, storing and representing information. As a result, one physical object yields several disciplinary representations, allowing designers to describe design options discipline-specifically and thus explore design differently. In a co-design approach, data from disciplines...
Architecture, engineering, and construction (AEC) projects require multidisciplinary solutions; therefore, one physical asset results in several disciplinary representations. Interoperability problems between different software often hinder disciplinary data integration, which prevents the recognition of violated design constraints until it is too...
At the Institute for Computational Design and Construction (ICD) at the University of Stuttgart, its founding director Achim Menges, who also directs the Cluster for Excellence for Integrative Computational Design and Construction for Architecture (IntCDC), and tenure‐track professor Thomas Wortmann illustrate some of their group's research into th...
This study proposes and tests methods for computational multi-objective optimization (MOO) for circular economy (CE) product design. Current CE design frameworks and assessments fail to address two key areas in which computational optimization can add value: identifying the best-performing solutions among many options and managing multiple potentia...
This paper develops a workflow to train machine learning (ML) models with a small dataset from physical samples to predict the curvatures of self-shaping wood bilayers based on local variations in the grain. In contrast to state-of-the-art predictive models, specifically 1.) a 2D Timoshenko model and 2.) a 3D numerical model with a rheological mode...
In this article, we present a procedure to derive algebraic descriptions from geometric descriptions of trimmed hyperbolic paraboloid (or ‘hypar’) surfaces. We contextualise this procedure historically, and we illustrate its application using the 1958 Philips Pavilion by Le Corbusier and Iannis Xenakis as a case study. The procedure uses parametric...
Bending Blossom provides visitors with the feeling of being in a bamboo forest. The structure takes advantage of bamboo’s elasticity. Bent bamboo poles of the structure transfer horizontal loads and reduce the risk of buckling under vertical loads. A green roof serves as a thermal buffer that provides a comfortable micro-climate with natural ventil...
Although there is a substantial body of academic literature on Architectural Design Optimization (ADO), not much is known about actual ADO practices and user experiences. This paper presents results from an international user study of ADO with 186 respondents from various disciplines in architecture and building engineering. Compared to earlier use...
This paper describes a method to understand and digitally reconstruct two sculptures by Gertrud Goldschmidt, a German-born, Venezuelan artist also called Gego. Gego is best known for her series of works called “Reticuláres”. These three-dimensional and open installations, mostly hanging freely in space, are playing with the concept and perception o...
This paper addresses the limitations of existing Solar Envelope (SE) methods to explore the trade-offs of solar radiation and urban shading, and to simultaneously account for several different Key Performance Indicators (KPIs). It offers an alternative parametric workflow-the Solar Block Generator (SBG)-which is based on an additive voxelization me...
This paper explores the trade-off between redeveloping an urban site with higher density and maintaining solar access for the surrounding context in the hot and dry climate of Tel Aviv. Such trade-offs are important for future urban development in the Middle East, where densification is a demographic and environmental need. We explore this trade-of...
This paper explores the use of autoencoders and function approximation to explore design spaces and fitness landscapes resulting from optimization, i.e., post-optimization results. The paper proposes a methodology exploring high-dimensional design space and how it relates to performance. We use dimensionality reduction to reduce complexity and to c...
Computational Fluid Dynamics (CFD) simulation is an important tool in the built environment to analyse wind flow. However, long simulation times limit their utility in fast-paced design processes, especially in larger (urban) scales and in design exploration methods. Two possible approaches to reduce computational cost are: (1) Simplified models su...
For almost two decades, the Zero Energy Buildings (ZEB) standard has epitomized a commitment to the high energy performance of buildings. Nevertheless, the applicability of ZEB in hot climates is currently limited and furthermore, in light of the current limitations of traditional building energy modeling methods, new methods are necessary to effec...
Using an integrated workflow with parametric design, Computational Fluid Dynamic (CFD) and Fast Fluid Dynamic (FFD) simulations, structural analysis and optimization, this paper evaluates the relative suitability of CFD and FFD simulations for Aerodynamic Shape Optimization (ASO). Specifically, it applies RBFOpt, a model-based optimization algorith...
This paper analyzes eight assumptions that underlie the general consensus in the computer-aided architectural design community that multi-objective optimization is more appropriate for and more analogous to architectural design processes than single-objective optimization. The paper discusses whether (a) architectural problems are best formulated a...
The interest to find cost-optimal zero-energy solutions for building, using multi-objective optimization, has risen dramatically over the last decade. Accordingly, several studies have been carried out, proposing new methods and tools. None, however, has introduced a simplified approach that is viable by a broader range of users. This study address...
Environmental simulation supports the design of more sustainable, zero-energy neighborhoods, especially when leveraged with multi-objective optimization. This study explores the tradeoff between urban density and energy balance-specifically, monthly load match between energy usage and generation-in terms of courtyard, slab, and tower typologies for...
In this paper, we present a procedure to derive algebraic parameters from geometrically described truncated hyperbolic paraboloid surfaces. The procedure uses parametric modelling and optimisation to converge on close algebraic approximations of hyperbolic paraboloid geometry through a successive breakdown of vast search spaces. We illustrate this...
In sustainable building design, daylight improves occupants' wellbeing and reduces electric lighting use, but glazed areas can increase energy consumption for heating and cooling. Conflicting objectives such as daylight and energy consumption are the primary motivation behind multi-objective optimization. This paper presents the multi-objective opt...
Although there is a substantial body of academic literature on Architectural Design Optimization (ADO), not much is known about actual ADO practices. This paper presents results from a user study of ADO in Grasshopper and compares them with previous studies. Compared to these studies, this anonymous, web-based survey employed a more relevant sample...
Structural membranes exhibit advantages over slab and frame structures, accommodating large deformations while still elegantly combining spatial enclosure with material efficiency. One of the most promising types of membrane structures are membrane tensegrity structures, which are composed of discontinuous struts embedded in a tensile membrane. To...
When applying black-box optimization (BBO) algorithms there seems to be a lack of guidelines on which algorithm to select and how to properly tune their algorithmic parameters. Many benchmarks are conducted either on large sets of mathematical test functions or on few building simulation problems. This inhibits us from drawing generalizable conclus...
This paper introduces performance-informed design space exploration (DSE) to question the relationship between explicit, quantitative optimization problems and "wicked", co-evolving architectural design problems and to support the reframing of architectural design optimization as a medium for reflection. The paper proposes selection, refinement, an...
This study investigates the performance of a wide selection of single objective black-box optimization algorithms (optimizers) when applied to a large set of building energy simulation problems from the literature. Optimizers include randomized, deterministic and model-based algorithms. We also study the impact of tunable hyper-parameters on perfor...
This study investigates the performance of a wide selection of single objective black-box optimization algorithms (optimizers) when applied to a large set of building energy simulation problems from the literature. Optimizers include randomized, deterministic and model-based algorithms. We also study the impact of tunable hyper-parameters on perfor...
Increasing applications of parametric design and performance simulations by architectural designers present opportunities to design more resource and energy efficient buildings via optimization. But Architectural Design Optimization (ADO) is less widespread that one might expect, due to, among other challenges, the problematic integration of optimi...
This article presents benchmark results from seven simulation-based problems from structural, building energy, and daylight optimization. Growing applications of parametric design and performance simulations in architecture, engineering, and construction allow the harnessing of simulation-based, or black-box, optimization in the search for less res...
Increasing applications of parametric design and performance simulations by architectural designers present opportunities to design more resource and energy efficient buildings via optimization. But Architectural Design Optimization (ADO) is less widespread than one might expect, due to, among other challenges, (1) lacking knowledge on simulation-b...
Computer-based shape grammar implementations aim to support creative design exploration by automating rule-application. This paper reviews existing shape grammar implementations in terms of their algorithmic complexity, extends the definition of shape grammars with sets of transformations for rule application, categorizes (parametric and non-parame...
This chapter presents black-box (or derivative-free) optimization from the perspective of architectural design optimization. We introduce and compare single- and multi-objective optimization, discuss applications from architectural design and related fields, and survey the three main classes of black-box optimization algorithms: metaheuristics, dir...
Model-based optimization is an innovative optimization strategy and particularly appropriate for time-intensive performance simulations. To demonstrate this appropriateness, the paper reviews simulation-based optimization algorithms and benchmarks several (single- and multi-objective) optimization tools on two problems involving annual daylight and...
This paper examines Parametric Design (PD) in contemporary architectural practice. It considers three case studies: The Future of Us pavilion, the Louvre Abu Dhabi and the Morpheus Hotel. The case studies illustrate how, compared to non-parametrically and older parametrically designed projects, PD is employed to generate, document and fabricate des...
This paper considers which black-box optimization methods are most appropriate for building energy optimization by revisiting a seminal work concerned with this question. We benchmark three categories of black-box optimization methods—(1) direct search, (2) metaheuristics and (3) model-based methods—on three building energy optimization problems. C...
This paper presents Opossum, a new optimization plug-in for Grasshopper, a visual data-flow modelling software popular among architects. Opossum is the first publicly available, model-based optimization tool aimed at architectural design optimization and especially applicable to problems that involve time-intensive simulations of for example day-li...
This article presents a method to visualize high-dimensional parametric design spaces with applications in computational design processes and interactive optimization. The method extends Star Coordinates using a triangulation-based interpolation with Barycentric Coordinates. It supports the understanding of design problems in architectural design o...
The " future of us " exhibition celebrated Singapore's Golden Jubilee. The visitors of the exhibition experienced a stunning play of light and shade cast by a metal lattice, composed of a main steel structure that supports 11000 perforated aluminium panels, spanning approx. 50m and rising to 16m. From start of design to completion of installation w...
This paper presents a novel method to visualize high dimensional parametric design spaces with applications in computational design space exploration. Specifically, the visualization method presented here supports the understanding of design problems in architectural design optimization by allowing designers to move between a high dimensional desig...