skip to main content
10.1145/3681769.3698586acmconferencesArticle/Chapter ViewAbstractPublication PagesgisConference Proceedingsconference-collections
short-paper

Machine Learning Model Specification for Cataloging Spatio-Temporal Models (Demo Paper)

Published: 29 October 2024 Publication History

Abstract

The Machine Learning Model (MLM) extension is a specification that extends the SpatioTemporal Asset Catalogs (STAC) framework to catalog machine learning models. This demo paper introduces the goals of the MLM, highlighting its role in improving searchability and reproducibility of geospatial models. The MLM is contextualized within the STAC ecosystem, demonstrating its compatibility and the advantages it brings to discovering relevant geospatial models and describing their inference requirements.
A detailed overview of the MLM's structure and fields describes the tasks, hardware requirements, frameworks, and inputs/outputs associated with machine learning models. Three use cases are presented, showcasing the application of the MLM in describing models for land cover classification and image segmentation. These examples illustrate how the MLM facilitates easier search and better understanding of how to deploy models in inference pipelines.
The discussion addresses future challenges in extending the MLM to account for the diversity in machine learning models, including foundational and fine-tuned models, multi-modal models, and the importance of describing the data pipeline and infrastructure models depend on. Finally, the paper demonstrates the potential of the MLM to be a unifying standard to enable benchmarking and comparing geospatial machine learning models.

References

[1]
Samuel Foucher, Francis Charette-Migneault, and David Landry. 2020. Project CCCOT03: Proposal for a STAC Extension for Deep Learning Models. Technical Report. Computer Research Institute of Montréal (CRIM). https://doi.org/10.13140/RG.2.2.27858.68804
[2]
Patrick Helber, Benjamin Bischke, Andreas Dengel, and Damian Borth. 2018. Introducing EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification. In IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 204--207.
[3]
Patrick Helber, Benjamin Bischke, Andreas Dengel, and Damian Borth. 2019. EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (2019). https://github.com/phelber/EuroSAT
[4]
Jason Jones, Wenxin Jiang, Nicholas Synovic, George K. Thiruvathukal, and James C. Davis. 2024. What do we know about Hugging Face? A systematic literature review and quantitative validation of qualitative claims. arXiv:2406.08205 [cs.SE] https://arxiv.org/abs/2406.08205
[5]
Zhuozhao Li, Ryan Chard, Logan Ward, Kyle Chard, Tyler J Skluzacek, Yadu Babuji, Anna Woodard, Steven Tuecke, Ben Blaiszik, Michael J Franklin, et al. 2021. DLHub: Simplifying publication, discovery, and use of machine learning models in science. J. Parallel and Distrib. Comput. 147 (2021), 64--76.
[6]
Matei Zaharia, Andrew Chen, Aaron Davidson, Ali Ghodsi, Sue Ann Hong, Andy Konwinski, Siddharth Murching, Tomas Nykodym, Paul Ogilvie, Mani Parkhe, et al. 2018. Accelerating the machine learning lifecycle with MLflow. IEEE Data Eng. Bull. 41, 4 (2018), 39--45.

Index Terms

  1. Machine Learning Model Specification for Cataloging Spatio-Temporal Models (Demo Paper)

        Recommendations

        Comments

        Information & Contributors

        Information

        Published In

        cover image ACM Conferences
        GeoSearch '24: Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Searching and Mining Large Collections of Geospatial Data
        October 2024
        53 pages
        ISBN:9798400711480
        DOI:10.1145/3681769
        Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

        Sponsors

        Publisher

        Association for Computing Machinery

        New York, NY, United States

        Publication History

        Published: 29 October 2024

        Permissions

        Request permissions for this article.

        Check for updates

        Author Tags

        1. Catalog
        2. Machine Learning
        3. STAC
        4. Search
        5. Spatio-Temporal Models

        Qualifiers

        • Short-paper
        • Research
        • Refereed limited

        Conference

        SIGSPATIAL '24
        Sponsor:

        Contributors

        Other Metrics

        Bibliometrics & Citations

        Bibliometrics

        Article Metrics

        • 0
          Total Citations
        • 153
          Total Downloads
        • Downloads (Last 12 months)153
        • Downloads (Last 6 weeks)4
        Reflects downloads up to 30 Jan 2025

        Other Metrics

        Citations

        View Options

        Login options

        View options

        PDF

        View or Download as a PDF file.

        PDF

        eReader

        View online with eReader.

        eReader

        Figures

        Tables

        Media

        Share

        Share

        Share this Publication link

        Share on social media