Intelligent Landscape Architecture as an Approach to Addressing Critical Issues

Abstract

It is a valuable tradition of landscape architecture to focus on the critical challenges to the humanity and to provide spatial solutions. Facing the major issues of global governance, such as climate change, resource scarcity and environmental constraints, abrupt disasters, and even the emergence of disruptive technologies, an "intelligent transformation" of landscape architecture is a compelling way to address them. Recently, driven by the great progress of new technologies including ubiquitous sensing, artificial intelligence, and virtual reality, the intelligent transformation not only helps landscape architecture better respond to the critical issues in the entire process of situational awareness, problem analysis, scheme making, outcome representation, effectiveness evaluation, and governance and optimization, but also provides new opportunities for the discipline's own transformation in terms of research objects, methodologies, and key skills.

Keywords

Landscape Architecture / Critical Issues / Disruptive Technologies / Disciplinary Transformation / Intelligent Transformation / Global Governance

Similar to its sister disciplines of architecture^[1] and urban planning^[2], landscape architecture in its modern form originated as a strategy to address critical challenges facing humanity^[3]. Drastic urbanization since the industrial revolution has imposed humanity with a new Zeitgeist, and simultaneously brought new challenges, such as human's increasing anxiety of separating from nature during the process of urbanization^[4][5], social disorders in the process of cultural transformation^[6][7], as well as environmental pollution and ecological crises^[8][9], all of which have become major concerns in the development of the discipline and practice of landscape architecture. Until today, such social commitments continue to be a valuable asset to the field.

The humanity in this era, featuring ubiquitous dwelling in high-density urban environments, continues to face critical challenges of the time. These challenges include climate change, resource scarcity and environmental constraints, and abrupt disasters, which are among the main topics of global governance today^[10] and also worthy of the attention of landscape architects. In addition, the landscape architecture discipline itself, along with the society in general, is facing significant impacts by the emergence of disruptive technologies such as artificial intelligence (AI). How to respond to these challenges by means of landscape planning and design and to provide cross-scale spatial solutions for higher quality urban lifestyles constitute a crucial topic urgently to be responded to by the discipline and also the profession.

In this regard, the ongoing "intelligent transformation," driven by the great progress of new technologies such as ubiquitous sensing, AI, and virtual reality in recent years provides new opportunities for landscape architecture to better respond to the above challenges along its entire professional chain: situational awareness, problem analysis, scheme making, outcome representation, effectiveness evaluation, and governance and optimization. Indeed, it is right about time to explore how these new ideas and methods can be applied in the efforts in this field to respond to major real-world challenges such that a socio-technical fit is reached.

A precondition for solving a problem is situational awareness, adequately and accurately. Thanks to advances in data acquisition channels such as remote sensing, infrastructural sensing, and Social Sensing^[11], new situational awareness tools, with their ubiquity, usability, and cost-effective advantages, not only provide new choices for landscape architects' toolbox, but also inspire new perspectives. New design paradigms that emphasize the importance of data, with various prefixes such as "data-informed"^[12], "data-driven"^[13], and "data-augmented"^[14], demonstrate the enormous potential of landscape architecture based on larger-sized and more adequate, integrated, and accurate data.

Data does not usually speak for itself, and astute problem analysis is a sure way to realize the above-mentioned potential. Design analysis used to have been criticized for being actually irrelevant from the scheme it is supposed to support. To some extent, this is due to the limitations of conventional data analysis tools themselves. Admittedly, landscape architecture, as a branch of geography in a broad sense, had also been heavily influenced by the "quantitative revolution," and the "requiem for large-scale models"^[15] has also inevitably collected its toll on the discipline's confidence on the meaning of data analytics. Nevertheless, with the advances in complex systems science, statistics, and data science in the past few decades, complexity^[16] and credibility^[17] revolutions have emerged in data analytic methodologies. New data analytic tools, such as causal inference, complex network analysis, and machine learning and deep learning, have transcended the mechanistic, deterministic world picture of the early quantitative revolution ages, and their efficacy has been tangibly demonstrated in a variety of fields. In landscape architecture, algorithm-driven problem analysis has been hence becoming feasible, allowing designers to understand, explain, and interpret the scientific aspects of design in a more rigorous and robust way, thus truly bridging the gap between observation and analysis with planning and design scheme generation.

In the stage of planning and design scheme formulation that has traditionally been regarded as the core skill of the designer, the emergent generative AI technologies, represented by applications such as ChatGPT (Dalle-E) and Midjourney empowered by the revolutionary algorithms of Attention^[18] and Diffusion^[19], have not just proven powerful tools for designers, but even appeared to pose a potential threat to the designer profession itself. Today's state-of-the-art AI-generated content (AIGC) programs have long been able to easily pass various forms of Turing tests, even demonstrating their capability to outperform human designers in certain built-environment planning and design tasks^[20]. However, the generative AI technology in its current form has innate limitations, and an objective assessment of its effectiveness and capability boundaries when applied in landscape architecture is crucial for both the discipline and the profession. As such, ways forward can be directed and offer advices on continued knowledge and skill learning for practitioners. Meanwhile, in terms of the representation of design schemes, with the urban science pioneers' advocacy of "digital twins"^[21], new tools for representing designs in a more immersive and interactive way with the real world are also rapidly evolving. Apparently, assessing the applicability and capability boundaries of these tools is an equally important task.

Finally, landscape architecture is, after all, about people. This means that human beings ourselves should be taken into account as an explicit factor in the full realization of design effects, as well as in evaluating such effectiveness. This has inspired various approaches to social mobilization around design, as well as evidence-based design evaluation paradigms^[22]. For the former, conventional means of public engagement is still in effect, while new approaches to audience education and social mobilization, such as participatory interactions and gaming^[23], are also thriving. For the latter, in parallel with advances in environmental cognition and behavioral sciences, VR/XR technologies have been introduced to establish immersive virtual environment exposures, and wearable biosensors such as eye-tracking, electroencephalography (EEG), electrocardiography (ECG), electromyography (EMG), and functional near-infrared imaging (fMRI), among other cognitive technologies, have been applied to observe humanistic physiological, psychological, and behavioral feedbacks. Thus, by directly establishing the association between design schemes and user preferences to formulate and improve landscape architecture solutions, one seeks a human-centered understanding of the design, which is also a notable future direction of the field.

This edition of Landscape Architecture Frontiers hosts a forum for in-depth discussion of the above topics. Responding to the critical challenges of climate change and decarbonization efforts, natural disaster prevention and resilience-building, effective use of compact urban space, and social and professional impacts of disruptive technologies, this edition applies various intelligent approaches including ubiquitous sensing, AI, and digital twining techniques to explore the scientific issues involved, and try to offer solutions from the landscape architecture perspective. We hope to trigger a broader discussion to advance the vision of intelligent landscape architecture as an approach to addressing the critical issues of the world.

References

[1] Corbusier, L. (1973). The Athens Charter. Grossman Publishers.

[2] Howard, E. (1902). Garden City of To-morrow. Swan Sonnenschein & Co., Ltd.

[3] Yu, K. , & Li, D. (2004) An introduction to Landscape Architecture: The profession and education. Chinese Landscape Architecture, (5), 10– 11.

[4] Thoreau, H. D. (2001). Walden Pond. Commonwealth Editions.

[5] Tuan, Y.-F. (1974). Topophilia: A Study of Environmental Perception, Attitudes, and Values. Prentice-Hall.

[6] Tönnies, F. & Harris, J. (2001). Tönnies: Community and Civil Society. Cambridge University Press.

[7] Jacobs, J. (1961). The Death and Life of Great American Cities. Vintage Books.

[8] Carson, R. (2002). Silent Spring. Houghton Mifflin Harcourt.

[9] Meadows, D. H., Meadows, D. L., Randers, J., & Behrens, W. W. (Eds.). (1972). The Limits to Growth: A Report for the Club of Rome's Project on the Predicament of Mankind. Universe Books.

[10] Hewson, M., & Sinclair, T. J. (Eds.). (1999). Approaches to Global Governance Theory. State University of New York Press.

[11] Liu, Y. , Liu, X. , Gao, S. , Gong, L. , Kang, C. , Zhi, Y. , Chi, G. , & Shi, L. (2015) Social sensing: A new approach to understanding our socioeconomic environments. Annals of the Association of American Geographers, 105 (3), 512– 530.

[12] Tang, Z. , Ye, Y. , Jiang, Z. , Fu, C. , Huang, R. , & Yao, D. (2020) A data-informed analytical approach to human-scale greenway planning: Integrating multi-sourced urban data with machine learning algorithms. Urban Forestry & Urban Greening, (56), 126871.

[13] Kitchin, R. (2015, August 10). Data-driven, networked urbanism. Social Science Research Network.

[14] Long, Y. , & Shen, Y. (2015) Data augmented design: Urban planning and design in the new data environment. Shanghai Urban Planning Review, (2), 81– 87.

[15] Lee, D. B. (1973) Requiem for large-scale models. Journal of the American Institute of Planners, (39), 163– 178.

[16] Batty, M. (2005). Cities and Complexity: Understanding Cities With Cellular Automata, Agent-based Models, and Fractals. MIT Press.

[17] Angrist, J. D. , & Pischke, J. S. (2010) The credibility revolution in empirical economics: How better research design is taking the con out of econometrics. Journal of Economic Perspectives, 24 (2), 3– 30.

[18] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (Eds.). (2017). Attention is All You Need. Advances in Neural Information Processing Systems 30. NeurIPS.

[19] Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems 33. NeurIPS.

[20] Zheng, Y. , Lin, Y. , Zhao, L. , Wu, T. , Jin, D. , & Li, Y. (2023) Spatial planning of urban communities via deep reinforcement learning. Nature Computational Science, 3 (9), 748– 762.

[21] Batty, M. (2018) Digital twins. Environment and Planning B: Urban Analytics and City Science, 45 (5), 817– 820.

[22] Ye, Y., & Qiang, D. (Eds.). (2022). Attempts on computational urban design: Little Lujiazui public space quality improvement plan in Shanghai. New Architecture, (4), 94–99.

[23] Abt, C. C. (1987). Serious Games. University Press of America.

RIGHTS & PERMISSIONS

© Higher Education Press 2024