Microsoft AI's text-to-speech model for keeping one voice across 23 languages, with voice cloning from short audio
NASA-IBM Lunar Foundation Model
Open-source model from IBM and NASA for lunar remote sensing, with ViT-B encoding and LoRA fine-tuning
About NASA-IBM Lunar Foundation Model
IBM and NASA released the NASA-IBM Lunar Foundation Model on 10 September 2026. It is an open-source AI model for remote sensing of the Moon, intended to help researchers map craters, volcanic features and areas that may hold ice, using orbital imagery.
Where it sits in IBM's Prithvi family
IBM places the model within its Prithvi family of open scientific foundation models, which already includes geospatial, weather and heliophysics models. The Universities Space Research Association contributed planetary science expertise, dataset work and evaluation, and published its own note about the release on 18 September.
Architecture and training data
The architecture pairs a ViT-B encoder with a decoder of twelve layers, and the model was built from the ground up, with masked-token training that borrows from the TerraMind Earth observation model. The pretraining set, SomBench, holds around two million co-registered lunar tile bundles spanning 11 modalities at two scales: roughly 1 meter per pixel from the narrow-angle camera on the Lunar Reconnaissance Orbiter, and 100 meters per pixel from its wide-angle camera. The model also takes terrain, slope and sun-angle geometry alongside imagery, and map layers such as thermal, radar, mineralogy, gravity and hydrogen data.
Fine-tuning and licensing
Users adapt it with IBM's TerraTorch toolkit, which is open source, and the developers recommend LoRA as the method. The weights and code carry an Apache 2.0 license, and the training dataset and benchmarks are published alongside them, so other research groups can reuse the work.
Reported results and stated limits
In the technical paper from the developers, error in lunar ice prospectivity mapping falls by up to 22 percent against an ImageNet-pretrained SwinV2-B baseline. It also improved crater detection at about 100-meter resolution by nearly 19 percent while using half the training data. The developers call it a research tool rather than a generator of scientific-grade output. It has no geodetic reference frame, its generated values are uncalibrated, and its ice output reproduces a prospectivity map rather than measured ice. The developers do not present it for operational use such as certifying landing sites.
TrustList summary
The NASA-IBM Lunar Foundation Model is an open-source model for remote sensing of lunar surfaces, released by IBM and NASA on 10 September 2026. It belongs to IBM's Prithvi family of open scientific models, and the Universities Space Research Association, which contributed planetary expertise and evaluation, published its own note on 18 September.
What NASA-IBM Lunar Foundation Model does
- Encoder and decoder: a ViT-B encoder paired with a 12-layer decoder, built from scratch using a masked-token approach adapted from TerraMind.
- Training data: about two million multimodal lunar image bundles across 11 modalities, captured at roughly 1 metre and 100 metres per pixel.
- Fine-tuning: adapts through IBM's open-source TerraTorch toolkit, with LoRA recommended.
- Open release: weights, code, training dataset and benchmarks under Apache 2.0.
Who it works with
Researchers mapping craters, volcanic features and possible lunar ice, using imagery, terrain and map-level context.
Key facts
- Benchmarks: the developers report up to 22% lower error in mapping ice prospectivity than an ImageNet-pretrained SwinV2-B baseline, and nearly 19% better crater detection at about 100-metre resolution using half the training data.
- Limits: the model has no geodetic reference frame, its outputs are uncalibrated, and it is not validated for operational decisions such as landing-site certification.
Summary written by TrustList from the business's own published information, Nov 2026.
Benchmarks & AI stats
| Benchmark | Official | Community avg |
|---|---|---|
| No benchmark scores yet. Be the first to add one. | ||
“Official” values are editor-approved and feed the ranking. “Community avg” is the mean of member submissions (shown for transparency; it never affects the ranking until an editor approves a value).
Sign in to add a benchmark score for this model.
NASA-IBM Lunar Foundation Model launches
Request a demo or quote from NASA-IBM Lunar Foundation Model
Reviews
Write the first review of NASA-IBM Lunar Foundation Model
Used it? Your experience helps other buyers decide.
Write a reviewQuestions & answers
No questions yet. Be the first to ask about NASA-IBM Lunar Foundation Model.
NASA-IBM Lunar Foundation Model alternatives
Similar listings buyers compare against this one.
Cantina Security's first open-weight security model, a post-trained GLM-5.3-Flash for vulnerability research and exploit checks
Open-source 2B decision model from AWS's Strands Agents project that picks options and returns scores with a reliability figure
Google's open multimodal embedding model that maps text, images, audio and video into one vector space, under Apache 2.0
Open-weight translation model from Bilibili's Index team, covering 150 languages and following glossary and style instructions
Aleph Alpha's open-weight English-German mixture-of-experts model for self-hosting, released under Apache 2.0 in October 2026
Anthropic's smallest and fastest Claude 5.5 model, available on its own API and three cloud platforms
Microsoft AI's real-time speech-to-text model for voice agents, transcribing 60 languages with continuous language detection
More on TrustList
Everything here links back to the same verified catalogue. Pick your next stop.
- Write a reviewHelp other buyers decide
- CompaniesAgencies, consultancies and IT service providers, ranked by verified reviews.
- ProductsSoftware and SaaS with pricing, features, integrations and alternatives.
- ArticlesGuides, comparisons and research from the editorial desk and the community.
- AwardsAnnual recognition decided by verified reviews and an independent jury.
- LaunchesNew products and releases, voted up by the community every day.
- RequestsBuyers describe what they need; vendors respond directly.
- PeopleReviewers, authors and makers with public profiles.
- ComparePut up to four listings side by side before you shortlist.