An official website of the United States government
To date, Deep Learning models for archaeological feature detection have generally been built on the back of off-the-shelf convolutional neural networks (CNNs) and vision Transformer (ViT) models, which are pretrained on a variety of image types, sources, and subjects that are not specific to analyzing high-resolution satellite imagery. Recent advances in transformer-based vision models and self-supervised training approaches make it possible for researchers to generate foundation models that are more finely attuned to specific domains, without huge amounts of human-annotated training data. We discuss the development of two such models employing Meta's transformer-based DINOv2 framework. The first, DeepAndes, is based on the ingestion of a 3 million chip sample from a two million square km area of high-resolution multispectral satellite imagery of the Andean region. This foundation model has broad utility across the social and earth sciences. The second, DeepAndesArch is fine-tuned labeled archaeological training data collected by the GeoPACHA project to create an archaeology-focused version of DeepAndes. We present the processes involved in generating DeepAndes and DeepAndesArch and discuss prospects for foundation models in archaeological research
more »
« less
Ours Is the Earth: Science and Human History in the Anthropocene
Abstract History at one time drew unproblematically on records produced by human societies about themselves and their doings. Advances in biology and the earth sciences introduced new narrative resources that repositioned the human story in relation to the evolution of all else on the planet, thereby decentering earlier conceptions of time, life, and human agency. This essay reflects on what it means for our understanding of the human that the history of our species has become so intimately entangled with the material processes that make up the biosphere, while concurrently the temporal horizon of our imagination has been stretched forward and back, underscoring the brevity of human existence in relation to earthly time. I suggest that, despite significant changes in the resources with which we can rethink the human condition, drawing upon the sciences, history’s fundamental purposes have not been rendered irrelevant. These center, as before, on the normative project of connecting past and future in ways that make sense of human experience and give meaning to it. In particular, the question of how humans should imagine the stewardship of the Earth in the Anthropocene remains an ethical project for history and not primarily the domain of the natural sciences.
more »
« less
- Award ID(s):
- 1856215
- PAR ID:
- 10285116
- Date Published:
- Journal Name:
- Journal of the Philosophy of History
- Volume:
- 14
- Issue:
- 3
- ISSN:
- 1872-2636
- Page Range / eLocation ID:
- 337 to 358
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We studied 11 long-term data infrastructure projects, most of which focused on the Earth Sciences, to understand characteristics that contributed to their project sustainability. Among our sample group, we noted the existence of three different types of project groupings: Database, Framework, and Middleware. Most efforts started as federally funded research projects, and our results show that nearly all became organizations in order to become sustainable. Projects were often funded for short time scales but had the long-term burden of sustaining and supporting open science, interoperability, and community building–activities that are difficult to fund directly. This transition from ‘project’ to ‘organization’ was challenging for most efforts, especially in regard to leadership change and funding issues.Some common approaches to sustainability were identified within each project grouping. Framework and Database projects both relied heavily on the commitment to, and contribution from, a disciplinary community. Framework projects often used bottom-up governance approaches to maintain the active participation and interest of their community. Database projects succeeded when they were able to position themselves as part of the core workflow for disciplinary-specific scientific research. Middleware projects borrowed heavily from sustainability models used by software companies, while maintaining strong scientific partnerships. Cyberinfrastructure for science requires considerable resources to develop and sustain itself, and much of these resources are provided through in-kind support from academics, researchers, and their institutes. It is imperative that more work is done to find appropriate models that help sustain key data infrastructure for Earth Science over the long-term.more » « less
-
Abstract Active investigation of students engaging in problem solving in natural settings has consistently been shown to greatly benefit their learning process. They gain skills and knowledge, while increasing their interest, aspirations, and motivation to learn more. But how can we provide these rich opportunities in densely populated urban areas where resources and access to natural areas are limited? The Curriculum + Community Enterprise for Restoration Science (CCERS) project has developed and begun testing an educational model of curriculum and community enterprise to address that issue within the nation's largest urban school system. Middle school students study the New York Harbor estuary and the extensive watershed that empties into it, while conducting field research in support of restoring native oyster habitats. This project builds on the existing Billion Oyster Project, and is being implemented across different settings by a broad partnership of institutions and community stakeholders, including Pace University, the New York City Department of Education, the Columbia University Lamont-Doherty Earth Observatory, the New York Academy of Sciences, the New York Harbor Foundation, the New York Aquarium, the River Project, the University of Maryland’s Center for Environmental Science, and Good Shepherd Services.more » « less
-
Rajala, A; Cortez, A; Hofmann, R; Jornet, A; Lotz-Sisitka, H; Markauskaite, L (Ed.)Not AvailableAn emerging body of work in the learning sciences has examined how computational models can support teachers in responding to students' prompts, inquiry, and ideas. This work has highlighted how teachers make discursive moves in relation to computational models to support classroom discussion. In this paper, we focus on a complementary phenomenon: teachers' design of code reflections, or curricular modifications that deepen students' engagement with one another's code for scientific and computational sensemaking. We highlight how these code reflections advanced student discourse and how both the code reflections and discourse became more sophisticated over time, shifting towards making connections across code, behaviors, simulation outcomes, data and the scientific process being represented. We reflect on how this progression was driven by shifts in the teachers’ comfort with code and computational modeling and the resources designers can offer to educators to support the development of code reflections.more » « less
-
Active investigation of students engaging in problem solving in natural settings has consistently been shown to greatly benefit their learning process. They gain skills and knowledge, while increasing their interest, aspirations, and motivation to learn more. But how can we provide these rich opportunities in densely populated urban areas where resources and access to natural environments are limited? The Curriculum + Community Enterprise for Restoration Science (CCERS) project has developed and begun testing an educational model of curriculum and community enterprise to address that issue within the nation's largest urban school system. Middle school students study the New York Harbor estuary and the extensive watershed that empties into it, while conducting field research in support of restoring native oyster habitats. This project builds on the existing Billion Oyster Project, and is being implemented across different settings by a broad partnership of institutions and community stakeholders, including Pace University, the New York City Department of Education, the Columbia UniversityLamont-Doherty Earth Observatory, the New York Academy of Sciences, the New York Harbor Foundation, the New York Aquarium, the River Project, the University of Maryland’s Center for Environmental Science, and Good Shepherd Services. Keywords: community, curriculum, New York Harbor, restoration science, middle school, STEM-Cmore » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1163/18722636-12341447
