Introduction
In this episode of the MaCAD Theory podcast, we explore with our guest Mr. Alessandro Grossi the growing importance of sustainable practices in the AEC sector, driven by climate change and resource scarcity. We dive into how integrating sustainability principles early in the design process can impact lifecycle costs and environmental outcomes.
Listen to how AI-enhanced workflows are revolutionizing environmental analysis, optimizing energy efficiency, and enabling data-driven decision-making from the outset. These innovations not only improve the building process, but also ensure that design and environmental stewardship go hand in hand.
Tune in to discover how sustainable design and cutting-edge technology are shaping the future of the built environment.
Our Guest: Alessandro Grossi
Alessandro Grossi is an architect with international experience across Europe and South America. He holds a Master’s degree in Sustainable Architecture and Energy from Pontificia Universidad Católica de Chile and is a certified LEED Green Associate, specializing in Environmental Design.
In 2024, he served as an AI-Powered Environmental Educator at Nordfy. Currently, he works as an Environmental Designer at infrared.city, where he leads AI-driven environmental analyses.
Sustainability Core Principles and AI-enhanced Computational Design Workflows
Sustainability in project development, emphasizing that the AEC industry traditionally relies on the three pillars for sustainability: environmental, social, and economic aspects. Among them, the environmental aspect is paramount, since addressing climate change now is viewed as the essential starting point.
AI-powered tools are instrumental in tackling environmental aspects. They significantly reduce computational time for tasks like environmental analyses that can now be executed accurately enough in the early design stages, enabling rapid evaluations and informed design decisions that enhance energy building performance and lower environmental impact in urban development.
Traditional vs. AI-powered Computational Workflows in Early Design Stages
Traditional sustainability workflows in architecture and construction are limited because they tend to delay integrating sustainable design until later project stages. The effects of this delay is illustrated by the MacLeamy Curve, which shows that the potential to cost-effectively influence a project decreases as it progresses. In conventional methods, if sustainability isn’t built into the project from the start, engineers must later invest extra time and energy to fix issues—resulting in higher costs and inefficiencies.
By addressing sustainability early—ideally through an integrative process enhanced by AI-powered tools—the design decisions that drive long-term efficiency and cost savings are made at a stage when changes are still relatively less expensive. This proactive approach not only streamlines workflows, but also sets the project on a better path for overall success in terms of environmental impact.
AI models and AI-enhanced Computational Workflows for Sustainability
AI models, particularly those based on machine learning and deep learning, are trained on large datasets—in this case, data from many sustainable (e.g., LEED-certified) projects. The model learns patterns about how sustainable design elements are implemented and how projects perform. Once trained, the AI can predict design outcomes and simulate performance almost instantly, bypassing the need for time-consuming manual analysis. This predictive capability is integrated into a computational design workflow by feeding in project-specific parameters (such as location or project type), allowing the model to offer real-time insights and recommendations for achieving sustainability goals.
Incorporating AI early in the design process is critical because the cost-effectiveness of design changes is highest at the outset, as illustrated by concepts like the MacLeamy Curve. Although early-stage predictions from AI may not be perfect, they provide valuable directional guidance. Firms can integrate these AI tools by establishing dedicated departments or teams with the necessary expertise and by investing in the appropriate software—even though these solutions can be expensive. The idea is that upfront investments in AI-enhanced workflows not only streamline decision-making, but also lead to significant cost savings and efficiency improvements over the project’s life cycle, ultimately supporting more sustainable outcomes.
Obstacles for a broader adoption of AI in the AEC industry and Existing Applications
In practice, AI-driven workflows are beginning to make a real impact in the AEC sector by dramatically improving project efficiency and sustainability outcomes. For instance, one example shared involves a project where AI automation streamlined processes so effectively that it reportedly saved around 10,000 design work hours —transforming a standard project into one completed with unprecedented speed and precision. This kind of acceleration means that firms can scale up from handling a handful of projects a year to potentially hundreds, thereby increasing the volume of sustainable designs implemented and contributing significantly to environmental goals.
However, despite these promising results, several obstacles hinder broader adoption of AI in AEC. Financially, the upfront costs, especially acquiring extensive datasets for training AI models, can be steep. Technologically, developing robust AI solutions requires advanced expertise and significant resources, which not all firms currently possess. Perhaps the biggest challenge, though, is cultural. Many professionals are hesitant or even fearful of AI because of concerns over job security and the radical changes it demands in traditional workflows. Convincing all stakeholders to embrace sustainable design as a non-negotiable component of early project stages remains a critical hurdle.
Regarding tools, the conversation often shifts to scripting and data management frameworks that form the backbone of AI applications. Tools like Ladybug Tools are highlighted as essential for sustainability consultants. There are then AI emerging platforms such as infrared.city—currently in beta version— being developed to provide real-time simulations and actionable insights. These tools not only enhance data-driven decision-making, but also help integrate sustainable practices into the very fabric of design workflows, paving the way for a future where AI can truly “save the planet.”
The Future of AI-driven Sustainability
The future of AI-driven sustainability is moving at an extraordinary pace, with advancements that promise to revolutionize not just early-stage design but potentially even the construction phase itself. Recent breakthroughs, like daylight simulations that once took hours now being completed in seconds with AI, highlight how rapidly computational capabilities are evolving. The dream is to see AI integrated seamlessly throughout the entire design and construction process, where predictive models not only inform initial designs but also adapt and refine strategies throughout a project’s lifecycle.
If technical and financial barriers were removed, the vision would be one of large-scale, AI-powered adaptation—where sustainability initiatives move from incremental improvements to massive, systemic transformation. For example, in Italy, current efforts might focus on renewing a single house per day, but with AI, the ambition would be to scale that up to thousands daily, making sustainability a widespread reality rather than an exception.
Empowering the Future: Cultivating Skills and Mindsets for a more Sustainable World
For students and professionals eager to shape this future, the key is relentless curiosity and deep understanding. AI is just a tool—what truly matters is knowing how to apply it effectively. The industry needs individuals who are not only skilled in technology, but who also grasp the bigger picture of sustainability and design. Success comes from constant learning, networking, and pushing the boundaries of knowledge, always questioning and refining approaches to make AI a powerful ally in the fight for a more sustainable world.
