Global Models and Local Knowledges
On machine learning and politics in flood forecasting
OPEN ACCESS
Author / Producer
Date
2023
Publication Type
Master Thesis
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
Abstract
Climate change is expected to increase the frequency and intensity with which flooding occurs. Framed as an invading force (Brooks 2005), both public and private organizations seek ways to fight this harmful phenomena back. Regularly proposed in contemporary discourse as a potent weapon in this battle is artificial intelligence. The urgency and scale of the climate crisis calls for solutions with speed and reach. However, what is often obscured in grand visions of a sustainable future for all, is how we imagine and act to get there. With this project, I inquire into the politics of flood forecasting with machine learning. I study visions of the global with climate disasters, how these visions are operationalized with machine learning, and how such projects form together with identities, norms, and practices in specific localities. To understand how flood forecasting models are political, I ask what is being optimized, for whom, and who gets to decide.
Permanent link
Publication status
published
External links
Editor
Contributors
Examiner: Boenig-Liptsin, Margarita
Book title
Journal / series
Volume
Pages / Article No.
Publisher
ETH Zurich
Event
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Science and Technology Studies (STS); Machine learning; Climate change; Flood forecasting; Situated knowledges; Politics
Organisational unit
09772 - Boenig-Liptsin, Margarita / Boenig-Liptsin, Margarita