Posts Tagged ‘machine learning’

LIVE AND LEARN

BY MIMI ZEIGER

Algorithms are bringing new kinds of evidence and predictive powers to the shaping of landscapes.

FROM THE FEBRUARY 2019 ISSUE OF LANDSCAPE ARCHITECTURE MAGAZINE.

 

Tree. Person. Bike. Person. Person. Tree. Anya Domlesky, ASLA, an associate at SWA in Sausalito, California, rattles off how she and the firm’s innovation lab team train a computer to recognize the flora and fauna in an urban plaza.

The effort is part of the firm’s mission to apply emergent technologies to landscape architecture. In pursuing the applied use of artificial intelligence (AI) and machine learning, the research and innovation lab XL: Experiments in Landscape and Urbanism follows a small but growing number of researchers and practitioners interested in the ways the enigmatic yet ubiquitous culture of algorithms might be deployed in the field.

Examples of AI and machine learning are all around us, from the voice recognition software in your iPhone to the predictive software that drives recommendations for Netflix binges. While the financial and health care industries have quickly adopted AI, and use in construction and agriculture is steadily growing, conversations within landscape architecture as to how such tools translate to the design, management, and conservation of landscapes are still on the periphery for the field. This marginality may be because despite their everyday use, mainstream understandings of AI are clouded by clichés—think self-actualized computers or anthropomorphic robots. In a recent essay on Medium, Molly Wright Steenson, the author of Architectural Intelligence: How Designers and Architects Created the Digital Landscape (The MIT Press, 2017), argued that we need new clichés. “Our pop culture visions of AI are not helping us. In fact, they’re hurting us. They’re decades out of date,” she writes. “[W]e keep using the old clichés in order to talk about emerging technologies today. They make it harder for us to understand AI—what it is, what it isn’t, and what impact it will have on our lives.”

So then, what is a new vision—a vision of AI for landscape? (more…)

Read Full Post »

BY KEVAN KLOSTERWILL

A custom geodesign process aims to help prototype solutions for the health of a rural watershed.

FROM THE NOVEMBER 2017 ISSUE OF LANDSCAPE ARCHITECTURE MAGAZINE.

Sam Ziegler, a corn-and-soybean farmer in southern Minnesota, had a chance to try out a new geodesign tool that could change the way he plants his crops. “It’s always on your mind what you can do better, but it’s hard to physically take an acre or a hundred out of production just to try something,” Ziegler says. “You can’t afford it. But this computer model allows you to play with things and get an understanding of what potentially would be the ramifications and benefits of switching things around.” The tool, operated with a touchscreen, was developed by a team of University of Minnesota (UM) researchers from the fields of landscape architecture, urban planning, economics, and soil and water science.

In the fall of 2013, the research team brought together about 40 community members, including farmers and environmental advocates, who were interested in improving the health of the Seven Mile Creek Watershed near Mankato, Minnesota. The group participated in a series of workshops that culminated with their generating alternative scenarios using an interactive computer model of the watershed. This investigation was supported by background layers such as aerial photographs, parcel lines, and topographic data that would feel familiar to regular users of geographic information systems. Using a 55-inch touchscreen, participants could assign various agricultural land uses to the landscape, including conventional corn and soybeans and perennial prairie grasses. “Basically, it was like painting a map, with some boundaries,” Ziegler says.

Once participants settled on a design, the geodesign program would analyze its environmental performance around various factors such as (more…)

Read Full Post »

%d bloggers like this: