geospatial
RingMoE
AIRCAS 14.7B multimodal remote sensing model.
Levelmodel
Classgeospatial
Parameters14.7B
Contextnot in the notes
Released4 Apr 2025
Opennessunknown
Runs onhyperscale cluster
Statusactive
Identity
- Developer
- Aerospace Information Research Institute, Chinese Academy of Sciences (AIRCAS)
- Family
- RingMo family
- Released
- 4 Apr 2025 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
- MoE Hierarchical mixture of modality experts over optical, SAR and multispectral
- Total parameters
- 14.7B sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- Pre-trained on 400M multi-modal images from nine satellites
- 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
- 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.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
DeveloperAerospace Information Research Institute, Chinese Academy of Sciences (AIRCAS)national lab, China
Aerospace Information Research Institute, Chinese Academy of Sciences (AIRCAS)national lab, ChinaModelRingMoEAerospace Information Research Institute, Chinese Academy of Sciences (AIRCAS), geospatial
RingMoEAerospace Information Research Institute, Chinese Academy of Sciences (AIRCAS), 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 1
Sources
- RingMoE: Mixture-of-Modality-Experts Multi-Modal Foundation Models for Universal Remote Sensing Image Interpretation arxiv.org https://arxiv.org/abs/2504.03166
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "RingMoE", https://aurion.semai.id/models/aircas-ringmoe/, records of October 2026.