Yield of agricultural fields

Contexte and problematic

Axa Climate is launching a parametric insurance offer which includes drought insurance dedicated to European farmers. In order to provide this insurance, Axa needs to predict field rates of return primarily from soil moisture levels. We enrich this data with multiple Open Data sources: Raster, shapefiles, era5, copernicus, etc..


In the area of Germany :
Enrich internal data with Open Data
Préedict the yield throught the soil moisture rate by region and by crop (regression problem)
Dectection of drought years by region (classification problem)

Our intervention

2 Data Scientist, 1 Lead Data Scientist

  • Data collection from internal sources (Axa business partners)
  • Open Data collection: shapefiles, era5 copernicus, etc.
  • Preparation and transformation of multi-source aggregated data
  • Dataset rebalancing
  • Modeling and benchmarking of neural networks, LSTM, Random Forest, Gradient Boosting, LGBM, etc.
  • Selection and deployment of the model with the best performance: Random Forest
  • Interoperability of the model through heatmaps on geographic maps


Enrichment of data by variables such as soles (raster), delimitation of regions (shapefile) and meteorological variables (era5)
Regression problem: RMSE ~ 30 for values of around 400 (tons /hectare) (tonnes/hectare)
Classification problem: accuracy = 0.88 / precision = 0.74 / recall = 0.61

Technical environment

Python – geoPandas – RasterIO – Shapely Jupyter – Pyzo
Sk-learn – Tensorflow – Keras
API Rest

Together with our customers, we build solutions that change and facilitate their daily lives.

Aide à la création de médicaments

Plateforme d’analyse de besoins clients

Conception et industrialisation du SI analytics

Prédiction de retards

Analyse de visage pour recommandation produits

Application d’optimisation de la Supply Chain

Scoring et analyse
de la peau

Analyse de Forums

Personnalisation de contenu

Analyse des activités de support IT

Détection de tendances sur les réseaux sociaux

de beaconing

Outil de classification de documents

Détection de cancer via Deep Learning

Conception de plateforme de veille stratégique

des champs agricoles

Conception du Data Hub et implémentation

Analyse et prévention des problèmes Skype

Assistant d’aide à la recherche

Classification de pages Web