AI Powered Agronomic Platform

Monitoreo Computacional de Cultivos para la Agricultura Digital del Futuro

Integrate satellite remote sensing, climate analytics, crop data, computer vision, and AI-powered agronomic recommendations in a single platform for any crop, anywhere.

0 yrs
Climate History
0
Spectral Indices
0
Scientific Sources
0
Countries
app.agragent.com Open →

Built for every agricultural professional

Researchers

Access genomic DEG data, yield models with full feature importance, published RNA-seq datasets, and peer-reviewed bibliographic search across 19,000+ INIA publications.

RNA-seqDEG AnalysisPublications

Farm Managers

Draw your field polygon and instantly see NDVI, climate KPIs, frost alerts, yield predictions, and phenological stage calendar. No technical expertise needed.

NDVI MapsYield ForecastAlerts

Everything you need for precision agriculture

A comprehensive suite of tools designed for researchers, agronomists, and farm managers to monitor and optimize crop production.

13 spectral indices · 10m resolution · 5-day revisit

See your field from space, in real time

Sentinel-2 imagery via Google Earth Engine, cloud-free composites updated every 5 days, clipped to your exact polygon.

  • 13 vegetation indices: NDVI, NDRE, MSAVI, TCARI, EVI, NDMI, NDWI, BSI and more for full crop health monitoring
  • Split-screen temporal comparison to track crop evolution between any two dates
  • Early detection of water stress, pest pressure, and nutritional deficiencies weeks before visible symptoms
Open platform →
8 KPIs · 80 years of historical data · worldwide

Make decisions with climate on your side

Real-time climate data from Open-Meteo for any location on Earth. No API key, no limits, no excuses.

  • GDD, chill hours, frost days, heat waves, water balance, solar radiation, and ET₀ (FAO Penman-Monteith)
  • Automatic phenological alerts calibrated to your crop and southern-hemisphere season calendar
  • Multi-period GDD comparison to benchmark current season against historical averages
Open platform →
3,603 DEGs · 8 phenological stages · 68 RNA-seq samples

Genomics meets the vineyard

Real RNA-seq differential expression data from Altimiras et al. (2024), published science directly in your browser.

  • Interactive DEG tables with logFC and FDR values across 8 E-L growth stages of Vitis vinifera
  • Gene Ontology enrichment, UniProt annotations, and AlphaFold 3D protein structures on demand
  • RNA-seq pipeline visualization from raw reads to differential expression to ML classification
Open platform →
300+ annotated images · 5 grape varieties · YOLOv11

Identify and count clusters from the field

State-of-the-art computer vision trained on WGISD (Embrapa). Upload your own image and get results in seconds.

  • YOLOv11 model trained on Chardonnay, Cabernet Franc, Cabernet Sauvignon, Sauvignon Blanc, and Syrah
  • Real-time inference in the cloud: send a field photo, get annotated bounding boxes and cluster count
  • WGISD dataset browser with color-coded bounding boxes and berry-count estimates
Open platform →
R² = 0.972 · MAPE = 3.8% · 15 weighted features

Predict your harvest with 97% accuracy

PyCaret Extra Trees Regressor combining 15 satellite + climate features, updated automatically when you load a new polygon.

  • Predicted yield (t/ha), total production, and estimated harvest date from GDD-based phenological model
  • Dynamic feature importance: see which variables (NDVI, ET₀, GDD…) drive your prediction
  • Multi-model comparison: Extra Trees, CatBoost, Random Forest, XGBoost, SVR, side by side
Open platform →
11 autonomous tools · INIA RAG · 266M+ publications

Your expert agronomist, available 24/7

Claude-powered agent with real-time access to your field data, climate, satellite indices, and the full INIA Chile scientific library.

  • Soil and foliar report analysis, irrigation scheduling, and N-P-K fertilization plans, from uploaded PDFs
  • Semantic RAG search over 19,000+ INIA Chile technical publications for evidence-based recommendations
  • Context-aware: knows your polygon, active satellite indices, climate alerts, and yield prediction automatically
Open platform →

From field to insight in minutes

Upload your field boundaries, connect to satellite and climate data sources, and receive AI-powered recommendations.

1
Define Your Field
Draw or upload your polygon on the interactive map.
2
Fetch Live Data
Sentinel-2 imagery and 80 years of climate data load automatically.
3
Analyze & Visualize
NDVI, climate KPIs, yield predictions and genomic data in one view.
4
Ask the AI Agent
Get instant agronomic recommendations with INIA bibliographic support.
Field Polygon: Valle del Aconcagua
-32.8421, -70.6234
12.4 ha
Vitis vinifera
Fetching real-time data…
Sentinel-2 SR Harmonized
NDVI 0.72
Open-Meteo Archive
ET₀ 4.2mm
Biblioteca INIA Chile
447 docs
Yield Model (Extra Trees)
R²=0.972
Field Dashboard: Live KPIs
NDVI
0.72
Dense vegetation
GDD
1,240
Base 10°C, Sep–Mar
ET₀
4.2 mm
FAO Penman-Monteith
Yield Forecast
18.4 t/ha
±3.8% MAPE
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Monthly ET₀ (mm)
agragent AI: Agronomic Advisor
¿Qué dice INIA sobre riego en uva de mesa Aconcagua?
Buscando en biblioteca INIA…
Según Ferreyra & Selles (INIA, 2001), el riego de alta frecuencia en uva de mesa requiere 4–5 mm/día en floración. Tu ET₀ actual de 4.2 mm/día está dentro del rango, el sistema de goteo es adecuado para tu suelo franco.
Consulta sobre tu cultivo…

Powered by open, scientific data

Source Type Access Usage Volume
Sentinel-2 SR Harmonized
Satellite imagery (10m) Google Earth Engine Vegetation indices, RGB composites 13 índices · 10m · revisita 5 días
Open-Meteo Archive API
Historical weather Free Temperature, precipitation, humidity, radiation, ET₀ 7 variables · hasta 80 años históricos
WGISD (Embrapa)
Crop images (300+) Public dataset Object detection annotations 300+ imágenes · 5 variedades de uva
Biblioteca Digital INIA Chile
Agricultural publications (19K+) Open access Agronomic bibliography, RAG semantic search 19.146 documentos · boletines · revistas
RNA-seq (Altimiras et al. 2024)
Genomic DEG data Published 3,603 DEGs across 8 phenological stages 68 muestras · 1.336M reads · 87 GB
OpenAlex
Academic literature (250M+) Open access Peer-reviewed papers, citations, abstracts 250M+ papers · 200+ countries · all disciplines
AGRIS (FAO)
Agricultural literature (16.5M+) Open access Grey literature, regional reports, Latin America 16.5M+ records · 258 languages · 1975-present
FAOSTAT
Agricultural statistics Free Production, yield, harvested area by country 245 countries · 200+ crops · 1961-present
AgriRxiv
Preprints (agricultural sciences) Open access Pre-publication research, rapid knowledge transfer Open preprints · CAB International · 2017-present
UC Davis AgriGuide
Curated research databases Open access Agricola, AGRIS, data repositories, statistics 100+ sources · USDA NAL · CAB · FAOSTAT

Peer-reviewed publications

agragent is grounded in published scientific research in precision & digital agriculture.

3 Publications
5 Institutions
2024–26 Active Research
2024

Transcriptome Data Analysis Applied to Grapevine Growth Stage Identification

Agronomy · MDPI · Q1

Francisco Altimiras, Leonardo Pavéz, Alireza Pourreza, Osvaldo Yañez, Lisdelys González-Rodríguez, José García, Claudio Galaz, Andrés Leiva-Araos, Héctor Allende-Cid

Agronomy, 14(3), 613, 2024

2025

A Computational Framework for Crop Yield Estimation and Phenological Monitoring

EPIA · Springer LNCS

Francisco Altimiras, Sofía Callejas, Rayner de Ruyt, Natalia Vidal, Astrid Reyes, Mia Elbo, Luis Martí, Nayat Sánchez-Pi

Progress in Artificial Intelligence, EPIA 2024. LNCS vol. 15400, pp. 161–174, Springer, 2025

2026

agragent: A Multimodal AI Platform for Integrated Computational Crop Monitoring

White Paper · 2026

Francisco Altimiras, Leonardo Pavéz, Alireza Pourreza, Héctor Allende-Cid

NIDS, Universidad de Las Américas · PUCV · UC Davis · Fraunhofer IAIS · Lamarr Institute

Start monitoring your crops today

agragent works with any crop and any location worldwide. No installation required.

agragent
agragent
Impulsado por agragent