IrriGator

Irrigation optimizer for crops, focused on maize in the South-Western part of France.

Balthy Macchiadon

7/16/20261 min read

This project has been inspired by Edouard Truffaux, a french farmer who detailed the need for a tool supporting the day-to-day irrigation decision. The aim is to develop an optimizer, specific for the client, that exploits pedology, hydrogeology and meteorology.

We will only present one parcel for this article, but more can be discussed based on demand (who cares?).

To develop such pipeline, we used various tools/datasets, across several domains/scientific fields:

  • Aquacrop model from the FAO (add ref), used to follow the growth and hydraulic stress,

  • Hydrosoil data grids from the XXX (add link), to approximately know the pedology of a given parcel,

  • ERA5 data from the Copernicus project (add link), for historical weather,

  • COMPEHORE data from MeteoFrance, for adjusting the precipitation,

  • AROME forecasts from MeteoFrance for short-term deterministic forecasts (0-2 days)

  • IFS forecasts from ECMWF for mid-term ensemble forecasts (2-15 days)

Parcel

We start by presenting the parcel that is core of our study, we name it "Billac" because it's it initial name. It is located in Dordogne (24), near Périgueux or Bergerac:

We will consider two years, the current (2026) and previous (2025) ones. The same planting date is considered: 10/04/202X. The Maize variety is considered the same (DKC4951 from Bayer), it is a half-tardif crop (G4), relatively easy to grow and with flowering at 1000°, grain at 32% H20 at 1900°.