Messis
crop-classification
Working out which crop is growing in each Swiss field from satellite pictures is otherwise a survey job. This is a downloadable model, built on an existing earth observation model, that labels crops across Swiss farmland.
QUICK INFO
SOLUTION TYPE
Models, data & tools
TECHNOLOGY CATEGORY
Models & fine-tunes
AREA OF WORK
Geospatial imagery & remote sensing
ACCESS
Free
DEPLOYMENT
Self-hosted / on-premise · Downloadable
SOURCE REVIEWED
August 17, 2026
What it helps with
- What crop is growing in this Swiss field
- Map crops across Swiss farmland
- Identify crops from satellite pictures
- Skip a field survey for crop type
- Downloadable crop mapping model for Switzerland
- Label crop types over a whole region
Scope & audience
WHO IT'S FOR
Developer / AI builder · Scientist / researcher
AREA OF WORK
Geospatial imagery & remote sensing
COMMODITY / SCOPE
Cross-commodity
Access & technical details
ACCESS
Anyone can get it
INTERFACE
Model download / weights
DEPLOYMENT
You run it yourself
LANGUAGES
Not stated by provider
Featured media
Source information
This listing was compiled from publicly available source material. Verify current details with the provider.
PROVIDER DOCUMENTATION
Reviewed August 2026
Explore more like this
FunctionGemma
Google DeepMind
Models, data & tools
A 270M-parameter Gemma model specialized for function calling. It is designed to be fine-tuned for a defined task so a small local agent can turn natural-language requests into structured API actions. It is not agrifood-specific and task-specific fine-tuning and testing are expected.
Free
Self-hosted / on-premise · Edge / local · Downloadable
Models & fine-tunes
FunctionGemma
build-integrate-ai
agrifood-data-and-ai-infrastructure
buildable-or-downloadable-component
models-and-fine-tunes
Free
Self-hosted / on-premise · Edge / local · Downloadable
August 26, 2026
- Map natural-language requests to structured calls in a tested application
- Turn spoken field commands into reviewed API calls
- Build an offline form and logging assistant
- Route common commands on device
- Fine-tune tool calling for farm operations
- Keep low-latency actions at the edge
DigiGreen/fact-relevance-score-llama-3-2-1b-lora
Digital Green
Models, data & tools
Once a system pulls out facts, you still need to know which ones actually matter for the question asked. These are downloadable adapter weights for a small language model that rates how relevant a fact is.
Free · Open source
Self-hosted / on-premise · Downloadable
Models & fine-tunes
DigiGreen/fact-relevance-score-llama-3-2-1b-lora
diagnose-protect-assure
food-safety-quality-and-nutrition
buildable-or-downloadable-component
models-and-fine-tunes
Free · Open source
Self-hosted / on-premise · Downloadable
August 17, 2026
- Which facts actually answer the question
- Rank extracted facts by relevance
- Filter out facts that do not matter
- Score relevance in a retrieval pipeline
- Keep only the useful facts
- Check whether a fact fits the question
Is this your Resource?
Contact us to claim this listing and add details, screenshots or a demo.
