On the logics of artificial intelligence and geographic information systems, with a case study in the Alas Merta Jati in Central Bali, Indonesia

FAIN: FEL-288605-23

Marc R. Bohlen
SUNY Research Foundation, University at Buffalo (Amherst, NY 14228-2577)

Research and writing leading to a web-based publication that explores how Artificial Intelligence, Geographic Information Systems, and satellite imagery can be deployed to describe land use in the Alas Merta Jati forest of Bali, and how these descriptions interact with local knowledge and sustainability strategies.

The nexus of geographic information systems (GIS) and artificial intelligence (AI) has created a powerful class of analytical visual products that offer new perspectives on planet earth. High resolution satellite imagery – once a rarefied asset reserved for military intelligence operations and geoscience experts - is now hyper-available, and algorithm-derived insights gained from those images percolate into numerous fields. In this project, I will attend to the pathways along which satellite networks, GIS, and AI (S-GIS-AI) create visual artifacts that describe landscapes and land use. I will reflect on the logic of assumptions made and arguments constructed by S-GIS-AI machinery in a specific context: the forests of Alas Merta Jati on Bali, Indonesia. Specifically, I will reflect on how the creation of land-cover categories by these systems can be deployed to support particular needs, ambitions, and opportunities related to sustainability. I seek an NEH-Mellon Fellowship for Digital Publication to complete a multimedia and software-in-action research artifact that tells a story of how this nexus operates in debates over the Alas Merta Jati.

Associated Products

On the Logics of Planetary Computing: Artificial Intelligence and Geography in the Alas Mertajati (Book)
Title: On the Logics of Planetary Computing: Artificial Intelligence and Geography in the Alas Mertajati
Author: Marc Böhlen
Abstract: A new breed of low Earth orbit satellites is making planetary-scale observation and analysis ubiquitous. This book explores how this condition feeds spatially explicit artificial intelligence, GeoAI, in redefining the study of landscapes, and how it impacts one particular land dispute in the Alas Mertajati in Central Bali, Indonesia. This book combines scholarship from the humanities and engineering to forge a novel way of presenting planetary computing in its GeoAI vernacular. From data collection to model evaluation, the book describes how multi-spectral, high-resolution satellite data and machine learning algorithms respond to uncommon land cover conditions, including sustainable land care practices such as agroforestry while contextualizing the operations within science and media studies. Together with the installation logics-of-geoai.org, this book offers full-spectrum immersion into the unstable nexus of geography and artificial intelligence. This book will be of interest to any experimental artist, social scientist, curious AI engineer or a free-range scholar. It will likewise appeal to students and scholars of science technology studies, media studies, geography, and ethnography.
Year: 2024
Primary URL: https://www.routledge.com/On-the-Logics-of-Planetary-Computing-Artificial-Intelligence-and-Geography-in-the-Alas-Mertajati/Bohlen/p/book/9781032857527
Publisher: Routledge
Type: Single author monograph
ISBN: 9781032857527
Copy sent to NEH?: No

AGROFORESTRY IN THE ALAS MERTAJATI OF BALI, INDONESIA. A CASE STUDY IN SUSTAINABLE SMALL-SCALE FARMING PRACTICES AND GEOAI (Article)
Title: AGROFORESTRY IN THE ALAS MERTAJATI OF BALI, INDONESIA. A CASE STUDY IN SUSTAINABLE SMALL-SCALE FARMING PRACTICES AND GEOAI
Author: Marc Böhlen
Author: R. Iryadi
Author: J. Liu
Abstract: This paper describes new results from a land survey of the Alas Mertajati in Central Bali based on multi-spectral data collected from a new class of commercially available satellites. We use these assets to create the first representations of sustainable small-scale farming, agroforestry, in the study area. We describe the process of producing the results, specifically establishing ground truth for complex land cover and land use classes, and discuss how input from stakeholders can be included in the creation of these representations. Furthermore, we describe an open-source software environment developed to create our classification pipeline with a focus on shallow learners, collaborative workflows and intuitive visualization results. The text ends with a discussion of bad maps; maps that contain outdated data, and why such maps are now problematic, particularly in resource constrained contexts.
Year: 2023
Primary URL: https://doi.org/10.5194/isprs-archives-XLVIII-4-W7-2023-101-2023
Format: Journal
Periodical Title: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publisher: Copernicus Publications

Digital twins, uncertainty, and model diversity (Conference Paper/Presentation)
Title: Digital twins, uncertainty, and model diversity
Author: Marc Böhlen
Abstract: A.I. models have unique predictive powers yet do not acknowledge their limitations. I will discuss consequences of this condition in NVIDIA’s digital twin of Earth. Based on research in A.I. enabled remote sensing, I will suggest how model diversity can produce counter-weights to large A.I. models.
Date: 07/16/2024
Primary URL: https://nomadit.co.uk/conference/easst-4s2024/paper/82814
Conference Name: EASST-4S 2024 Amsterdam: Making and Doing Transformations

On the Logics of Planetary Computing: Geography and Artificial Intelligence in the Alas Mertajati (Web Resource)
Title: On the Logics of Planetary Computing: Geography and Artificial Intelligence in the Alas Mertajati
Author: Marc Bohlen
Abstract: Research and writing leading to a web-based publication that explores how Artificial Intelligence, Geographic Information Systems, and satellite imagery can be deployed to describe land use in the Alas Merta Jati forest of Bali, and how these descriptions interact with local knowledge and sustainability strategies.
Year: 2024
Primary URL: https://logics-of-geoai.org/

---