Skip to content

Commit

Permalink
add citation references
Browse files Browse the repository at this point in the history
  • Loading branch information
fmigneault committed Oct 21, 2024
1 parent 58dfaec commit 3ecaf20
Showing 1 changed file with 216 additions and 0 deletions.
216 changes: 216 additions & 0 deletions CITATION.cff
Original file line number Diff line number Diff line change
@@ -0,0 +1,216 @@
cff-version: 1.2.0
title: Machine Learning Model Extension Specification for SpatioTemporal Asset Catalog
alias: mlm
message: >-
If you use this standard or software, please cite it using the metadata from this file.
type: standard
repository: "https://github.com/crim-ca/mlm-extension"
repository-code: "https://github.com/stac-extensions/mlm"
license: Apache-2.0
license-url: https://github.com/stac-extensions/mlm/blob/main/LICENSE
identifiers:
- type: doi
value: "10.1145/3681769.3698586"
description: "Conference paper presenting the standard."
- type: url
value: "https://stac-extensions.github.io/mlm/"
description: "The URL of the specific extension used in 'stac_extensions' references."
authors:
- given-names: Francis
family-names: Charette-Migneault
alias: fmigneault
email: [email protected]
affiliation: Computer Research Institute of Montréal (CRIM)
orcid: "https://orcid.org/0000-0003-4862-3349"
- given-names: Ryan
family-names: Avery
alias: rbavery
email: [email protected]
affiliation: "Wherobots, Inc."
orcid: "https://orcid.org/0000-0001-7392-1474"
- name: Computer Research Institute of Montréal
city: Montréal
region: Québec
alias: CRIM
website: "https://www.crim.ca/"
email: [email protected]
tel: 1 (514) 840-1234
country: CA
post-code: H3N 1M3
address: "101 – 405, avenue Ogilvy"
- name: "Wherobots, Inc."
address: 350 California St
city: San Francisco
country: US
post-code: "94104"
region: California
website: "https://www.wherobots.ai/"
location: Floor 1 - Lincoln Towne Center
references:
- type: software-code
name: stac_model
repository-code:
repository-artifact: "https://pypi.org/project/stac-model/"
url: "https://github.com/crim-ca/mlm-extension/tree/main/stac_model"
authors:
- given-names: Ryan
family-names: Avery
alias: rbavery
email: [email protected]
affiliation: "Wherobots, Inc."
orcid: "https://orcid.org/0000-0001-7392-1474"
- given-names: Francis
family-names: Charette-Migneault
alias: fmigneault
email: [email protected]
affiliation: Computer Research Institute of Montréal (CRIM)
orcid: "https://orcid.org/0000-0003-4862-3349"
- type: report
title: Project CCCOT03 – Technical Report
alias: dlm
repository: "https://raw.githubusercontent.com/crim-ca/CCCOT03/main/CCCOT03_Rapport%20Final_FINAL_EN.pdf"
repository-code: "https://github.com/crim-ca/dlm-extension"
license: Apache-2.0
license-url: https://github.com/crim-ca/dlm-extension/blob/main/LICENSE
date-released: "2020-12-14"
languages:
- en
authors:
- given-names: Francis
family-names: Charette-Migneault
alias: fmigneault
email: [email protected]
affiliation: Computer Research Institute of Montréal (CRIM)
orcid: "https://orcid.org/0000-0003-4862-3349"
- given-names: Samuel
family-names: Foucher
alias: sfoucher
orcid: "https://orcid.org/0000-0001-9557-6907"
- given-names: David
family-names: Landry
orcid: "https://orcid.org/0000-0001-5343-2235"
- given-names: Yves
family-names: Moisan
alias: ymoisan
- name: Computer Research Institute of Montréal
city: Montréal
region: Québec
alias: CRIM
website: "https://www.crim.ca/"
email: [email protected]
tel: 1 (514) 840-1234
country: CA
post-code: H3N 1M3
address: "101 – 405, avenue Ogilvy"
- name: "Natural Resources Canada"
country: CA
website: "https://natural-resources.canada.ca/"
- name: "Canada Centre for Mapping and Earth Observation"
alias: CCMEO
country: CA
website: "https://natural-resources.canada.ca/research-centres-and-labs/canada-centre-for-mapping-and-earth-observation/25735"
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.
keywords:
- STAC
- Catalog
- Machine Learning
- Spatio-Temporal Models
- Search
preferred-citation:
type: conference-paper
doi: "10.1145/3681769.3698586"
title: Machine Learning Model Specification for Cataloging Spatio-Temporal Models
conference:
name: 3rd ACM SIGSPATIAL International Workshop on Searching and Mining Large Collections of Geospatial Data
alias: GeoSearch’24
date-released: "2024-10-29"
year: 2024
month: 11
pages: 4
location:
name: Georgia Tech Hotel and Conference Center
city: Atlanta
region: Georgia
country: US
languages:
- en
contact:
- given-names: Francis
family-names: Charette-Migneault
email: [email protected]
affiliation: Computer Research Institute of Montréal (CRIM)
orcid: "https://orcid.org/0000-0003-4862-3349"
authors:
- given-names: Francis
family-names: Charette-Migneault
email: [email protected]
affiliation: Computer Research Institute of Montréal (CRIM)
orcid: "https://orcid.org/0000-0003-4862-3349"
- given-names: Ryan
family-names: Avery
email: [email protected]
affiliation: "Wherobots, Inc."
orcid: "https://orcid.org/0000-0001-7392-1474"
- given-names: Brian
family-names: Pondi
email: [email protected]
affiliation: "Institute for Geoinformatics, University of Münster"
orcid: "https://orcid.org/0009-0008-0367-1690"
- given-names: Joses
family-names: Omojola
affiliation: University of Arizona
email: [email protected]
orcid: "https://orcid.org/0000-0001-5807-2953"
- given-names: Simone
family-names: Vaccari
email: [email protected]
affiliation: Terradue
orcid: "https://orcid.org/0000-0002-2757-4165"
- given-names: Parham
family-names: Membari
email: [email protected]
affiliation: Terradue
orcid: "https://orcid.org/0009-0004-7594-4011"
- given-names: Devis
family-names: Peressutti
email: [email protected]
affiliation: "Sinergise Solutions, a Planet Labs company"
orcid: "https://orcid.org/0000-0002-4660-0576"
- given-names: Jia
family-names: Yu
email: [email protected]
affiliation: "Wherobots, Inc."
orcid: "https://orcid.org/0000-0003-1340-6475"
- given-names: Jed
family-names: Sundwall
email: [email protected]
affiliation: Radiant Earth
orcid: "https://orcid.org/0000-0001-9681-230X"

0 comments on commit 3ecaf20

Please sign in to comment.