Duncan Wilson

Many ecological decisions are slowed by the gap between collecting and analysing biodiversity information. Edge computing moves data processing closer to the sensor, with edge artificial intelligence (AI) using AI models for data processing and selective data transfer. edge AI extends the scope of biodiversity monitoring by complementing retrospective ecological analysis with real‐time sensing, enabling responsive and adaptive decision‐making. However, the adoption of edge AI systems in ecological research remains fragmented because deploying efficient and reliable systems is complex. Edge hardware, on‐device AI models and network configuration are tightly linked, such that optimising any one component shapes the performance and feasibility of the others, demanding holistic system design. For the uptake of edge AI in biodiversity monitoring, it is essential to understand the design trade‐offs, performance constraints and implementation challenges faced by current systems. Here, we analyse 82 studies published between 2017 and 2025 that use edge AI systems for biodiversity monitoring across acoustic, vision‐based, tracking and multi‐modal sensing. We synthesise hardware platforms, AI model optimisation and wireless communication to assess how these design choices influence ecological inference and determine the practicality and longevity of field deployments. Annual publications rise moderately from 3 in 2017 to 19 in 2025. Across these studies, we identify four system types that represent distinct patterns of edge computing adoption in ecological monitoring. These include low‐power microcontrollers (MCUs) for single‐taxon or rare‐event detection ( Type I: TinyML ), single‐board computers (SBCs) supporting multi‐species classification and real‐time alerts ( Type II: edge AI ), distributed systems coordinating processing across multiple devices ( Type III: Distributed edge AI ) and network‐connected devices for cloud processing ( Type IV: Cloud AI ). Each type illustrates different trade‐offs among power consumption, computational capability and communication requirements. Our analysis reveals the evolution of edge AI systems from proof‐of‐concept to robust, scalable tools. We argue that edge AI systems enable timely and scalable ecological observations, but realising their full potential depends on closer collaboration between ecologists, engineers and data scientists to align AI model development and system design with ecological needs and field realities.

Capturing accurate as-built condition for complex mechanical, electrical, and plumbing (MEP) systems remains a major construction bottleneck. Despite advancements like laser scanning, conventional point cloud workflows are limited by sequential data acquisition, labour-intensive registration, and delayed office-based verification. To bridge this gap, this study formulates and field-validates a novel workflow integrating Building Information Modelling (BIM) with Augmented Reality (AR). Tested through a real-world case study, the framework shifts verification from post-processing to field-based, real-time documentation by establishing AR as an information aggregator for bidirectional data exchange. The findings demonstrate that this integration facilitates daily reporting of design deviations and compliances directly from the field, bypassing traditional data processing stages. Documented benefits include real-time as-built reporting, reduced modelling workloads, and enhanced site-to-office communication. Post-task practitioner evaluations confirm the workflow's practicality, positioning AR as a high-efficiency alternative to point clouds for complex MEP environments.

Digital twins are becoming increasingly popular in the built environment, with building users asking for greater levels of data and digitisation, and the volume of research in the field growing. There remains a question as to whether the costs of digital twins are worth the benefits they provide, both in terms of the financial cost and the environmental cost of transferring, storing, analysing, and processing a consistently growing amount of data to feed digital twins. This paper provides a literature review of studies that assess the costs and benefits of digital twins. It considers the value of digital twins and how this value is generated. This review includes an analysis of the different definitions for digital twins given in the literature, the countries of authorship, and categories of sources within the relevant literature. The analysis of digital twin definitions showed that the use of the term varied depending on the application being considered. An assessment of the data harvested and associated benefits showed that environmental conditions, especially temperature, and occupancy data were the most harvested data types in the studies considered. It was found that there is potential for digital twins to provide benefits beyond their costs if used in the correct application. However, the studies relied on simulations to quantify benefits and did not quantify the costs of live data streams in digital twins, which highlights a research gap. For the studies analysed, implementations focusing on occupancy data to provide demand-led services, machine learning to optimise equipment setpoints, and data for predictive maintenance show the greatest potential for cost and energy savings.

This chapter explores the intersection of gaming and the emerging metaverse, examining how major game worlds like Roblox, Fortnite, Minecraft, and Grand Theft Auto have effectively prototyped core metaverse concepts through innovations in world-building, asset creation, virtual economies, and social connectivity. It discusses key technological enablers such as game engines (Unity, Unreal Engine), 3D modelling tools (Blender), procedural generation techniques, and cloud gaming infrastructure that are shaping gaming's convergence with the metaverse vision. The evolution of non-player characters (NPCs) and the potential for AI to create more intelligent virtual entities are also examined. While the full vision of an interconnected digital universe remains on the horizon, the chapter argues that understanding gaming's pioneering role is critical to the metaverse's continued evolution from theory into a living, sustainable digital universe that may ultimately blur the lines between virtual and physical reality.

This chapter explores the current landscape of the metaverse and opens with the current frontier by introducing the concept of digital twins and how such twins encompass everything from the city down to buildings, rooms and, ultimately, its inhabitants in the form of avatars. This chapter provides the background of digital twins and how cities (metascapes) are being recreated in the metaverse, from early examples to Metaverse Seoul, Twinned Amsterdam, and New York. The chapter subsequently looks at the inhabitants of these worlds—avatars and how they occupy and move between these spaces. It looks at the design of avatars, styles across the platforms, and how they can be customised. In addition, it looks at the overlaps between the real word and digital space—augmented reality where cities overlap in both digital and real space, blurring the boundaries between cities and the metaverse.

This chapter explores the pivotal role of artificial intelligence (AI) in shaping the metaverse, examining how AI technologies are transforming virtual environments into increasingly immersive and realistic digital realms. It discusses key AI applications such as automated world-building, procedural content generation, and avatar creation, which enable the development of vast, dynamic virtual worlds. The chapter also delves into how AI enhances user interactions through natural language processing and gesture recognition, while improving visual and auditory realism via neural rendering and spatial audio. Additionally, it addresses AI's potential to increase accessibility and break down language barriers in the metaverse. While highlighting these advancements, the chapter also considers the ethical implications and challenges associated with AI in the metaverse, including data privacy concerns and the risk of perpetuating biases. Ultimately, it presents AI as a fundamental technology driving the evolution of the metaverse towards a more immersive, inclusive, and human-centric digital future.

This chapter explores the phenomenon of abandoned digital worlds and forgotten spaces within the metaverse. It examines three categories: abandoned worlds where activity has ceased but infrastructure remains intact, digital ruins showing signs of decay and broken functionality, and digital graveyards of platforms that have completely shut down. Through case studies of platforms like Second Life, Mozilla Hubs, and AltspaceVR, we analyse the reasons for abandonment, including shifting user interests, technological obsolescence, and strategic pivots by parent companies. The chapter considers the implications of these digital ghost towns, exploring questions of digital preservation, the role of AI in potentially reviving abandoned spaces, and the evolution of the metaverse concept itself. By examining these lost frontiers, the chapter provides an insight into the ephemeral nature of digital spaces and the challenges of building persistent virtual worlds.

This chapter explores the pioneering days of the metaverse through the lens of “30 Days in Activeworlds,” an ambitious experiment conducted in 1998 at University College London. In this virtual world, hosted on a modest Windows 95 machine, users were granted unprecedented freedom to construct anything they desired within a vast digital frontier, devoid of rules or restrictions. Over the course of 30 days, a vibrant community emerged, erecting homes, businesses, and even a church, while forging social connections that transcended physical boundaries. The chapter delves into the experiment's inception, capturing the excitement and challenges of venturing into an uncharted digital realm. It chronicles the evolution of this virtual society, from the initial surge of construction to the emergence of community rituals and the eventual decline as users migrated to newer virtual worlds. By documenting the world's detailed mapping and logging, this chapter offers a unique glimpse into the formative stages of the metaverse by documenting a true frontier land.

This chapter examines the future of the metaverse and how it represents the next step in human evolution towards true digital habitation. The future metaverse is envisioned as an immersive digital realm where photorealistic avatars are able to replicate physical movements and interactions, enabled by technologies such as brain-computer interfaces. This metaverse will be one where we increasingly live, work, and socialise, we will have our own space in these emerging digital cities with economies, and infrastructures mirroring the physical world. It will truly bring into question the future role of physical cities as people increasingly inhabit the digital realm, a new world beyond the frontier.

Cities in the Metaverse offers a comprehensive exploration of the intersection between urban environments and digital realms. The book examines: · The size and shape of cities in the Metaverse · Spatial computing and its impact on digital interaction · Digital twins in urban planning and management · Avatars and social dynamics in virtual spaces · Economic models emerging in the Metaverse · The influence of gaming on immersive digital landscapes · The impact of Artificial Intelligence on the Metaverse · Potential futures of digital habitation Drawing from architecture, computer science, urban planning, geography, social studies, and economics, the authors provide a multidisciplinary analysis of how virtual cities are shaping our digital future. Using key case studies, they trace the evolution from early cyberspace concepts to current spatial computing technologies, offering insights into both historical context and future possibilities. The book addresses key questions about the opportunities and challenges presented by metaverse technologies, including issues of accessibility, creativity, and the future of humans and artificial intelligence co-existing, side by side, in digital spaces. It serves as a practical guide, equipping readers with the knowledge they need to navigate the future of urban life in virtual environments with a thought-provoking examination of how we might build, inhabit, and govern cities in the Metaverse. The authors explore the concept of digital twins, demonstrating how these virtual replicas of physical spaces can revolutionise urban planning and management. They delve into the social aspects of the metaverse, examining how avatars shape our interactions and relationships in digital realms. Economic considerations are central to the book ethos, with an analysis of emerging models that often leverage blockchain technologies. The book addresses the challenges, potential pitfalls and ethical considerations in creating and inhabiting digital cities. At the same time, it takes a step back and examines already abandoned digital worlds, offering lessons from past attempts at creating virtual spaces. Essential reading for urban planners, geographers, economists, technologists, policymakers, and anyone interested in the future of cities and digital interaction, Cities in the Metaverse provides a balanced, informed perspective on this rapidly evolving field.