Collaborative Workflow Research Articles

Collaborative Forensic Autopsy Documentation and Supervised Report Generation Using a Hybrid Mixed-Reality Environment and Generative AI.

Forensic investigation is a complex procedure involving experts working together to establish cause of death and report findings to legal authorities. While new technologies are being developed to provide better post-mortem imaging capabilities-including mixed-reality (MR) tools to support 3D visualisation of such data-these tools do not integrate seamlessly into their existing collaborative workflow and report authoring process, requiring extra steps, e.g. to extract imagery from the MR tool and combine with physical autopsy findings for inclusion in the report. Therefore, in this work we design and evaluate a new forensic autopsy report generation workflow and present a novel documentation system using hybrid mixed-reality approaches to integrate visualisation, voice and hand interaction, as well as collaboration and procedure recording. Our preliminary findings indicate that this approach has the potential to improve data management, aid reviewability, and thus, achieve more robust standards. Further, it potentially streamlines report generation and minimise dependency on external tools and assistance, reducing autopsy time and related costs. This system also offers significant potential for education. A free copy of this paper and all supplemental materials are available at https://osf.io/ygfzx.

Optimization of architectural design and construction with integrated BIM and PLM methodologies.

Digital transformation in the architecture industry encounters challenges such as data silos within design stages, between design and construction, and across the entire industry chain, including BIM and project management. This study introduces a pioneering approach for seamlessly integrating building information modeling (BIM) and product lifecycle management (PLM) within the management framework and collaborative workflows of architectural design and construction. The proposed methodology was implemented in two major projects, namely, the Wuhan Next-Generation Weather Radar Construction Project and the Hubei Center for Disease Control and Prevention Comprehensive Capacity Enhancement Project (Phase I), with the former being China's first end-to-end digitally integrated construction project. Compared with traditional projects, these implementations achieved improvements of 24.39% and 38.04%, respectively, in objective function values. The findings highlight the unique advantages of BIM-PLM integration in optimizing lifecycle management, enhancing cross-disciplinary, cross-enterprise, and cross-regional collaboration, improving project design efficiency and quality, and reducing costs and waste. This integration provides valuable insights into the digital advancement of the construction industry.

The Digital Decathlon

The “Digital Decathlon” Erasmus+ project addresses the critical need for digital and green transitions in the Architecture, Engineering and Construction (AEC) sector by proposing an innovative approach for higher education. The project aims to prepare the next generation of professionals through a BIM-based design competition, designed as a novelty learning/gaming pathway for university students. By engaging participants from diverse countries and related academic backgrounds, the project fosters collaborative workflows and interdisciplinary teamwork by adopting a digital and gamified approach, providing hands-on learning and design experience. This paper presents the conceptual framework, methodologies and materials defining the prototypical learning format, which integrates online learning resources and tools, collaboration and mentoring, subject to a quality assessment for improvement and replication. Overall, the Digital Decathlon contributes to the advancement of educational methods necessary to address current challenges and to create the digitalised and sustainable built environment of tomorrow.

Empowering decentralized production: A distributed manufacturing system for additive manufacturing processes

This work presents a pilot distributed manufacturing system for decentralized additive manufacturing, focusing on the Interdisciplinary Center for Advanced Manufacturing Systems (ICAMS) capabilities at Auburn University. The paper outlines the first phase of a multi-phase implementation plan and demonstrates the developed capabilities. The vision is to coordinate geographically separated manufacturing facilities as a cohesive unit. In our work, we prioritize instantaneous communication for file and information sharing. The Manufacturing Hub and Remote Cell, two facilities within driving distance, are coordinated in terms of part design, printing, and inspection procedures for a distributed Additive Manufacturing process. To enable coordination between the two facilities, ICAMS addresses three technological needs. These needs consider information sharing, process standardization, and data collection and monitoring. A network attached storage facilitates information sharing, a database-connected graphical user interface streamlines and standardizes the manufacturing process, and a data collection system facilitates process monitoring. The graphical user interface allows for order placement, progress monitoring, and communication updates. The developed phased plan, collaborative workflow, technological solutions, and production protocols demonstrate the potential for decentralized additive manufacturing. Successful integration of communication, design, printing, and quality assurance processes sets the foundation for future advancements in decentralized manufacturing systems.

Evaluating the effectiveness of large language models in abstract screening: a comparative analysis

ObjectiveThis study aimed to evaluate the performance of large language models (LLMs) in the task of abstract screening in systematic review and meta-analysis studies, exploring their effectiveness, efficiency, and potential integration into existing human expert-based workflows.MethodsWe developed automation scripts in Python to interact with the APIs of several LLM tools, including ChatGPT v4.0, ChatGPT v3.5, Google PaLM 2, and Meta Llama 2, and latest tools including ChatGPT v4.0 turbo, ChatGPT v3.5 turbo, Google Gemini 1.0 pro, Meta Llama 3, and Claude 3. This study focused on three databases of abstracts and used them as benchmarks to evaluate the performance of these LLM tools in terms of sensitivity, specificity, and overall accuracy. The results of the LLM tools were compared to human-curated inclusion decisions, gold standard for systematic review and meta-analysis studies.ResultsDifferent LLM tools had varying abilities in abstract screening. Chat GPT v4.0 demonstrated remarkable performance, with balanced sensitivity and specificity, and overall accuracy consistently reaching or exceeding 90%, indicating a high potential for LLMs in abstract screening tasks. The study found that LLMs could provide reliable results with minimal human effort and thus serve as a cost-effective and efficient alternative to traditional abstract screening methods.ConclusionWhile LLM tools are not yet ready to completely replace human experts in abstract screening, they show great promise in revolutionizing the process. They can serve as autonomous AI reviewers, contribute to collaborative workflows with human experts, and integrate with hybrid approaches to develop custom tools for increased efficiency. As technology continues to advance, LLMs are poised to play an increasingly important role in abstract screening, reshaping the workflow of systematic review and meta-analysis studies.

BneR - A collaborative workflow for air quality modeling and uncertainty characterization using the Bayesian Nonparametric Ensemble

bneR - A collaborative workflow for air quality modeling and uncertainty characterization using the Bayesian Nonparametric Ensemble

Feature-Driven Next View Planning for Cutting Path Generation in Robotic Metal Scrap Recycling

Metal recycling in scrapyards, where workers cut decommissioned structures using gas torches, is labor-intensive, difficult, and dangerous. As global metal scrap recycling demands are rising, robotics and automation technologies could play a significant role to address this demand. However, the unstructured nature of the scrap cutting problem—due to highly variable object shapes and environments—poses significant challenges to integrate robotic solutions. We propose a novel collaborative workflow for robotic metal cutting that combines worker expertise with robot autonomy. In this workflow, the skilled worker studies the scene, determines an appropriate cutting reference, and marks it on the object with spray paint. The robot, then, autonomously explores the surface of the object for identifying and reconstructing the drawn reference, converts it to a cutting trajectory, and finally executes the cut. This paper focuses on the surface exploration and cutting reference reconstruction tasks, which require appropriate next view planning (NVP) algorithms. We devise three NVP algorithms enabling the robot to explore and extract desired features from the scene, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.</i> , the drawn reference, without requiring any <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a priori</i> object model. Contrasting with global or feature-agnostic NVP algorithms, our approaches guide the robot via desired local features to increase the efficiency of the exploration. We evaluate our NVP algorithms against six categories of objects both in simulation and in physical experiments. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This work is motivated by the need of extracting a desired cutting reference determined and drawn on the object by scrap yard workers. From the robot’s perspective, it must explore and reconstruct the drawing, starting from an unknown scene containing an unknown object featuring an unknown drawing. We assume that an RGB-D camera is attached to the tool-tip of the robot, and the color of the drawn path is significantly different from the object’s color. The goal of the robotic system is to explore the object surface to uncover the drawn path entirely without colliding with the object. The exploration algorithm must overcome complex object shapes and must be fast enough for practical use in scrap yards. This means conventional exploration (active vision) techniques are insufficient since they focus on exploring the entirety of the object, which is unnecessary for our task and is time-consuming. Our methods exploit the drawing information to guide the exploration for quickly determining a suitable viewpoint, which results in an efficient extraction of the entire cutting reference, without needing to explore the entire object’s surface. Our algorithms are robust against adversarial features such as discontinuous, non-smooth, or self-occluded object surfaces. Our feature-driven strategies are not limited to robotic scrap cutting as they are applicable to any viewpoint planning problem requiring high performance while extracting the local features in the scene.

Research on man-machine cooperation and safety in intelligent manufacturing

Securing our organizations safety in this dynamic environment demands an all-encompassing approach, encompassing the physical, virtual, and human dimensions. It is imperative to understand that true security transcends the digital realm, encompassing the very physical spaces where innovation unfolds and the people who drive it. In order to effectively recognize and mitigate urgent threats in real-time scenarios, a commitment to adhering to established standards and leveraging state-of-the-art sensors becomes indispensable. These sensors serve as the vigilant sentinels of collaborative spaces, tirelessly monitoring interactions, and swiftly identifying anomalies. By adhering to rigorous standards, organizations ensure that their security protocols remain robust and responsive. Collaboration safety, meanwhile, hinges on the proficiency of trained and informed personnel. Properly equipping the human element within this collaborative landscape is paramount. Operators must be well-versed in the technologies they interact with, trained to navigate collaborative workflows, and imbued with a heightened sense of safety awareness. The success of collaborative ventures relies heavily on the competence and preparedness of the human workforce. From our extensive analysis, a resounding call to action emerges: the imperative to integrate diverse elements cohesively for optimal performance. This integration isnt merely a technological endeavor; its a holistic approach that considers people, processes, and technology.

Study on the Optimization and Expansion of the Architectural Design Process by BIM Technology

In the contemporary realm of architecture, Building Information Modeling (BIM) technology is gradually reshaping the holistic management of architectural design, construction, and operation with its distinctive advantages. Despite the widespread adoption of BIM technology, numerous challenges persist in its practical implementation, such as the prevalence of information silos and hindered collaborative workflows. These impediments constrain the further advancement of BIM technology, consequently jeopardizing the quality and efficiency of architectural projects. Confronted with this reality, there exists a pressing need to delve deeply into the optimization pathways of BIM technology in the architectural design process, aiming to devise effective remedial strategies. This article will embark from the current application status of BIM technology in architectural design, expounding upon the fundamental principles, scope of application, and optimization strategies of BIM technology. Through this analysis, it seeks to explore avenues for maximizing the utilization of BIM technology in optimizing architectural design processes, thereby enhancing the overall quality and efficiency of architectural projects. This study not only contributes to propelling technological innovation within the architecture industry but also furnishes novel perspectives and directions for subsequent related research endeavors.

Study Identifies Opportunities for Intervention Improvement With Collaborative Workflows

_ This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 212922, “The Intervention Opportunity: Why the Industry Does Not Do More and How New Collaborative Workflows With Aligned Outcomes Can Change This,” by Matthew E. Billingham, SPE, SLB; Fraser J. Proud, North Sea Transition Authority; and Pierre Ramondenc, SPE, SLB. The paper has not been peer reviewed. _ The authors write that their analysis presented in the complete paper challenges the typical way interventions have been planned and executed, both from an operational and commercial basis, and examines where room exists for significant improvement. The paper examines the case for performing interventions and aims to identify opportunities for both financial and net-zero-goal achievement. By appreciating the issues operators face when justifying and designing intervention activity, challenges can thus be addressed by proper alignment for the best outcome. The Complexity of Interventions Downhole issues can be broken into two main categories: reservoir-based bottlenecks, and well-integrity and completion hardware issues. Problems categorized as reservoir-based can manifest either in the formation or in the wellbore. For instance, scaling and sand production are processes that originate from the reservoir but must be dealt with at least partially in the wellbore. The same is true for downhole flow-assurance challenges, which often find their root cause in the reservoir. The Value of Intervention In the UK, operators complete an annual stewardship survey (also known as the UKSS) for which a large amount of data is collected, especially around wells. The average production added from many subsea intervention jobs is significant, with reperforations, for example, adding approximately 120,000 BOE/yr per intervention, a more than 300-BOEPD uplift. Clearly, opportunities exist to increase production in the UK Continental Shelf (UKCS). The question becomes whether the investment in intervention is economical. Not all operators use well interventions to their maximum potential. A large variance exists in the number of jobs an operator completes; the operators seeing the most production added generally are the ones performing the most interventions. Many operators may be capital-constrained and, thus, cannot invest in more well intervention. However, it is clear that operators that do invest consistently see good value returns. Intervention Challenges Platform/Wellsite Access. A major obstacle to performing interventions is the logistical bottleneck created by additional persons on board (POB) and deck-space limitations. This applies to operations on land as well, where lack of facilities, especially in remote locations, may cause similar bottlenecks. Asset Mindset. Another difficulty is sometimes referred to as the “asset mindset,” whereby the asset-management team might regard interventions as a high-risk operation, which jeopardizes the existing production base as opposed to gaining a potential uplift. The asset mindset looks at the intervention not so much as a chance to increase production, but as a potential risk to lose base-case existing production. However, technology leaps have been made in the provision of intervention services to ensure safe entry and exit of wells, with zero damage to the completion or formation, and provide excellent chances of a production increase.

Effectiveness of an Artificial Intelligence–Enabled Intervention for Detecting Clinical Deterioration

Inpatient clinical deterioration is associated with substantial morbidity and mortality but may be easily missed by clinicians. Early warning scores have been developed to alert clinicians to patients at high risk of clinical deterioration, but there is limited evidence for their effectiveness. To evaluate the effectiveness of an artificial intelligence deterioration model-enabled intervention to reduce the risk of escalations in care among hospitalized patients using a study design that facilitates stronger causal inference. This cohort study used a regression discontinuity design that controlled for confounding and was based on Epic Deterioration Index (EDI; Epic Systems Corporation) prediction model scores. Compared with other observational research, the regression discontinuity design facilitates causal analysis. Hospitalized adults were included from 4 general internal medicine units in 1 academic hospital from January 17, 2021, through November 16, 2022. An artificial intelligence deterioration model-enabled intervention, consisting of alerts based on an EDI score threshold with an associated collaborative workflow among nurses and physicians. The primary outcome was escalations in care, including rapid response team activation, transfer to the intensive care unit, or cardiopulmonary arrest during hospitalization. During the study, 9938 patients were admitted to 1 of the 4 units, with 963 patients (median [IQR] age, 76.1 [64.2-86.2] years; 498 males [52.3%]) included within the primary regression discontinuity analysis. The median (IQR) Elixhauser Comorbidity Index score in the primary analysis cohort was 10 (0-24). The intervention was associated with a -10.4-percentage point (95% CI, -20.1 to -0.8 percentage points; P = .03) absolute risk reduction in the primary outcome for patients at the EDI score threshold. There was no evidence of a discontinuity in measured confounders at the EDI score threshold. Using a regression discontinuity design, this cohort study found that the implementation of an artificial intelligence deterioration model-enabled intervention was associated with a significantly decreased risk of escalations in care among inpatients. These results provide evidence for the effectiveness of this intervention and support its further expansion and testing in other care settings.

The Intervention Opportunity: Why the Industry Does Not Do More and How New Collaborative Workflows with Aligned Outcomes Can Change This

Summary This analysis challenges the typical way interventions have been planned and executed, both on an operational and a commercial basis, and examines where there is room for significant improvement in the industry. Perhaps more importantly, it examines the case for performing interventions and tries to explain the challenges (“headwinds”) in what is an opportunity to achieve both financial and net-zero emissions goals. Benchmarked data have already shown that opportunity absolutely exists to do more, and we investigate why the intervention opportunity is underserved. By appreciating the issues operators face when justifying and designing intervention activities, the challenges can thus be addressed by proper alignment to the best outcome. Intervention global expenditure is a small percentage of the total cost of exploration and production, and yet there is a strong value case for such operations. This study examines why this is so and then looks at how to address those issues. There is a huge array of well integrity and reservoir performance challenges that can bottleneck production, and the industry has delivered many innovative solutions to address these issues. Reduced capital expenditure over the past years and the pressure to maintain production sustainably should create a perfect climate for intervention. However, an asset mindset that is often risk averse to entering a producing well, as well as complex workflows, will too often detract from the opportunity to intervene. New workflows—including digital—can simplify the identification of candidate wells, and intervention techniques can help determine the success rate of the operations, as well as incremental production gains, more reliably to enable more robust outcomes. However, current contracting techniques and conventional key performance indicators can also cause further misalignment as to the true goal of interventions being to increase production sustainably. Those issues and how they have been resolved are addressed in this study. New workflows and commercial models have been used to facilitate the quicker identification of intervention opportunities, enabling collaborative planning and optimal solution identification, combined with feedback mechanisms to ensure continuous close collaboration between technical experts enabled by digital tools, which can disrupt the conventional intervention model. Case examples support the arguments made and demonstrate a new way of performing interventions. New digital workflows combined with strong collaborative, technical domain knowledge and a wide array of possible intervention solutions can change current typical intervention models. With these changes, further improvements can then be made to the conventional business models used to maximize the intervention opportunity and the sustainability opportunities it brings with regard to getting the most out of existing infrastructure.

Advancements in GitHub Automation and Workflow: A Comprehensive Exploration

The landscape of software development has been significantly transformed by the integration of automation and streamlined workflows, with GitHub emerging as a pivotal platform in this evolution. This research paper delves into the multifaceted realm of GitHub automation and workflow, investigating key aspects that contribute to enhanced efficiency, collaboration, and code quality in modern development practices. The paper begins by exploring the utilization of GitHub Actions for establishing robust Continuous Integration and Continuous Deployment (CI/CD) pipelines. Best practices for designing reliable workflows are discussed, along with insights into customizing workflows to suit diverse project requirements through the use of custom actions and templates. The automation of code reviews is scrutinized, with a focus on tools and practices that facilitate objective and efficient evaluation of code quality. The paper also investigates GitHub's role in security automation, covering strategies for vulnerability detection and integration of security checks into the development lifecycle. Collaborative workflows on GitHub, including branch management, pull requests, and code reviews, are explored as pivotal components fostering teamwork. The integration of GitHub into DevOps practices is analyzed, showcasing its synergy with popular DevOps tools and platforms. As a forward-looking endeavor, the research paper concludes by examining emerging trends and technologies in GitHub automation. By encapsulating a comprehensive overview of the current state and future trajectories of GitHub automation and workflow, this paper aims to contribute to the collective understanding of best practices, challenges, and opportunities in contemporary software development.

DMLBC: Dependable machine learning for seaports using blockchain technology

The technological shifts driven by Industry 4.0 and the impact of the COVID-19 pandemic has ushered new challenges for seaports, necessitating a transformation in their information and communications systems to enhance global competitiveness. As the United Nations (UN) International Maritime Organization mandates the adoption of a Maritime Single Window in short time, seaports are compelled to adapt their operations. Addressing these challenges, this research introduces the Dependable Machine Learning for seaports using Blockchain (DMLBC) method, offering a secure technological system that integrates transactional data among various logistics stakeholders. DMLBC enhances efficiency in document control, traceability, loading processes, and collaborative workflows. The method employs a architecture grounded in Blockchain (BC) and harnesses Machine Learning Techniques. In a practical application, DMLBC is implemented in a real case study, demonstrating its efficacy for decision making of port operations. The research discusses the contributions that the DMLBC method has compared to what exists in the bibliographic review and in other port industries worldwide. Describes future exploration directions and It emphasizes the potential for generating additional predictions by incorporating others Key Performance Indicators (KPI)s, integrating DMLBC with Decision Support System (DSS), and delving into the realm of Post-Quantum Cryptography (PQC) to fortify the security of seaport operations in the evolving technological landscape.

Knowledge Graphs in Practice: Characterizing their Users, Challenges, and Visualization Opportunities.

This study presents insights from interviews with nineteen Knowledge Graph (KG) practitioners who work in both enterprise and academic settings on a wide variety of use cases. Through this study, we identify critical challenges experienced by KG practitioners when creating, exploring, and analyzing KGs that could be alleviated through visualization design. Our findings reveal three major personas among KG practitioners - KG Builders, Analysts, and Consumers - each of whom have their own distinct expertise and needs. We discover that KG Builders would benefit from schema enforcers, while KG Analysts need customizable query builders that provide interim query results. For KG Consumers, we identify a lack of efficacy for node-link diagrams, and the need for tailored domain-specific visualizations to promote KG adoption and comprehension. Lastly, we find that implementing KGs effectively in practice requires both technical and social solutions that are not addressed with current tools, technologies, and collaborative workflows. From the analysis of our interviews, we distill several visualization research directions to improve KG usability, including knowledge cards that balance digestibility and discoverability, timeline views to track temporal changes, interfaces that support organic discovery, and semantic explanations for AI and machine learning predictions.

A Systematic Analysis of Problems in Open Collaborative Data Engineering

Collaborative workflows are common in open-source software development. They reduce individual costs and improve the quality of work results. Open data shares many characteristics with open-source software, as it can be used, modified, and redistributed by anyone, for free. However, in contrast to open-source software engineering, collaborative data engineering on open data lacks a shared understanding of processes, methods, and tools. This article presents a systematic literature review of collaboration processes, methods, and tools in data engineering as performed by open data users. An additional interview study with practitioners confirms and enhances the findings and strengthens the resulting insights. We find an ecosystem with heterogeneous participants and no standardized processes, methods, and tools. Participants face a variety of technical and social challenges during their work. Our work provides a structured overview of collaboration systems in open collaborative data engineering, enabling further research. Additionally, we contribute preliminary guidelines for successful open collaborative data engineering projects and recommendations to increase its adoption for open data ecosystems.

Condition Assessment of Heritage Buildings via Photogrammetry: A Scoping Review from the Perspective of Decision Makers

In recent years, advanced digital technologies have driven an outstanding paradigm shift in the field of architectural heritage, particularly for building modelling, historical documentation and touristic promotion. Nonetheless, they show great potentialities in the field of assessment and control of the state of conservation of heritage buildings. In particular, close-range and aerial photogrammetry have increasingly relied on low-cost and user-friendly tools and procedures, with a high degree of automation that makes them accessible to specialists who are foremost involved in architectural diagnosis and conservation, rather than in remote sensing sciences. In this framework, this paper provides a scoping review of 117 publications, based on the PRISMA protocol, from Scopus and Web of Science databases, related to the employment of photogrammetric models and methods, with specific focus on the targets and purposes of the diagnostic process, including decay mapping, structural monitoring and modelling, non-destructive investigation and multi-source documentation. In detail, the results point out that current studies mainly support robust processing of large amounts of information from direct observation of surface alterations, systematic correlation between materials, construction characteristics, visible anomalies and experimental measurements, as well as multi-disciplinary collaborative workflows through remote inspection and harmonized data management. Further improvements were identified, including standardization of acquisition procedures, automatization of elaboration pipelines, integration of real-time data, validation of diagnosis decision-making support tools and scalability to networks of assets.

User Perspectives on Branching in Computer-Aided Design

Branching is a feature of distributed version control systems that facilitates the "divide and conquer" strategy present in complex and collaborative work domains. Branching has revolutionized modern software development and has the potential to similarly transform hardware product development via CAD (computer-aided design). Yet, contrasting with its status in software, branching as a feature of commercial CAD systems is in its infancy, and little research exists to investigate its use in the digital design and development of physical products. To address this knowledge gap, in this paper, we mine and analyze 719 user-generated posts from online CAD forums to qualitatively study designers' intentions for and preliminary use of branching in CAD. Our work contributes a taxonomy of CAD branching use cases, an identification of deficiencies of existing branching capabilities in CAD, and a discussion of the untapped potential of CAD branching to support a new paradigm of collaborative mechanical design. The insights gained from this study may help CAD tool developers address design shortcomings in CAD branching tools and assist CAD practitioners by raising their awareness of CAD branching to improve design efficiency and collaborative workflows in hardware development teams.

Generative design of terraced concert hall – a case study of Taipei music and library centre

ABSTRACT The terraced concert hall offers a wide range of design options. Yet the knowledge barrier within a design team makes it difficult to effectively deliver a design that satisfies both the needs of creativity and acoustics. The study aims to explore the integration of generative parametric design collaboration workflow into the design of terraced concert halls and apply the cumulative results of the pilot study to the Taipei Music and Library Centre design competition. We propose an enhanced collaborating model between architects and acoustic consultants, integrating geometric design with acoustic verification in concert hall design. This cooperating model embraces and integrates three key steps: defining basic parameters and reference geometries, efficiently generating and composing geometric elements, and conducting geometric and acoustic statistical assessments. This design strategy enables integration of diverse viewpoints, covering both the acoustics within the hall and the space integration with the surroundings. The outcome is a terraced concert hall with an acoustic performance comparable to traditional shoebox-shaped halls.

Spatial planning of urban communities via deep reinforcement learning.

Effective spatial planning of urban communities plays a critical role in the sustainable development of cities. Despite the convenience brought by geographic information systems and computer-aided design, determining the layout of land use and roads still heavily relies on human experts. Here we propose an artificial intelligence urban-planning model to generate spatial plans for urban communities. To overcome the difficulty of diverse and irregular urban geography, we construct a graph to describe the topology of cities in arbitrary forms and formulate urban planning as a sequential decision-making problem on the graph. To tackle the challenge of the vast solution space, we develop a reinforcement learning model based on graph neural networks. Experiments on both synthetic and real-world communities demonstrate that our computational model outperforms plans designed by human experts in objective metrics and that it can generate spatial plans responding to different circumstances and needs. We also propose a human-artificial intelligence collaborative workflow of urban planning, in which human designers can substantially benefit from our model to be more productive, generating more efficient spatial plans with much less time. Our method demonstrates the great potential of computational urban planning and paves the way for more explorations in leveraging computational methodologies to solve challenging real-world problems in urban science.