geospatial
SkySense
Ant Group remote sensing foundation model (CVPR 2024); 16 datasets, 7 tasks; claims to beat 18 RSFMs.
Levelmodel
Classgeospatial
Parametersnot in the notes
Contextnot in the notes
Released15 Dec 2023
Opennessunknown
Runs onhyperscale cluster, single datacentre GPU
Statusactive
Lineage
successor
SkySense V2 is a child (successor)high confidencenotesWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 2 models. Confidence and evidence are the notes' own.
Identity
- Developer
- Ant Group, Wuhan University, MYBank
- Family
- not in the notes
- Released
- 15 Dec 2023 sourcesannouncement page
- Weights published
- –
- Record checked
- 10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer Factorized multi-modal spatiotemporal encoder (optical + SAR time series); Multi-Granularity Contrastive Learning; Geo-Context Prototype Learning; pre-trained on 21.5M temporal sequences
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- billion-scale
- Context length
- not in the notes
- Input
- image
- Output
- image
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- unknown
- Licence
- not in the notes sources
- Access routes
- not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- hyperscale cluster, single datacentre GPU
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Industry Use Cases
No industry use case links this model.
Links
ModelSkySenseAnt Group, geospatial
SkySenseAnt Group, geospatialR&D TopicsEarth Observation Foundation Models
Use CasesSatellite Monitoring (Land Cover, Floods, Forests)Public SectorLand Use and Crop MappingAgricultureUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
BRIN Data Science and Information Research Center (PRSDI)Research, 10 Mar 2026Deployments of these use cases; none names this model.
BRIN Data Science and Information Research Center (PRSDI)Research, 10 Mar 2026Deployments of these use cases; none names this model.Organisations 3
Sources
- CVPR 2024 Open Access Repository openaccess.thecvf.com https://openaccess.thecvf.com/content/CVPR2024/html/Guo_SkySense_A_Multi-Modal_Remote_Sensing_Foundation_Model_Towards_Universal_Interpretation_CVPR_2024_paper.html
- SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery arxiv.org https://arxiv.org/html/2312.10115v2
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "SkySense", https://aurion.semai.id/models/ant-group-skysense/, records of October 2026.