Buenos Aires, Argentina

Crop yield forecasts that get sharper every week of the campaign.

Rindecast combines Sentinel-2 imagery, weather records and on-farm management data into probabilistic yield forecasts for the Argentine Pampas โ€” delivered per field and per 300 mยฒ hexagon, updated from planning through harvest.

Sentinel-2 ยท 10 m ยท every 5 days H3 resolution 12 grid Early maize, first crop
The problem

Every input decision is made months before anyone knows what the field will do.

A grower commits seed, hybrid, density and fertiliser in September. The yield that actually arrives in April can swing between 6 and 14 t/ha on the same field, largely on how much rain falls in a two-week flowering window in December. Most tools answer late, with one number, for a whole field.

Decisions are staged, forecasts aren't

Choosing which crop, choosing how to sow it, and managing a standing crop are three different questions asked by three different people at three different times. A single end-of-season estimate helps none of them.

A field average hides the field

A lot averaging 10 t/ha routinely contains zones at 6 and zones at 14. Variable-rate seeding and fertilisation need that structure, not the mean.

A point estimate hides the risk

"9.8 t/ha" and "9.8 t/ha, 80% chance between 7 and 12" support completely different decisions about how much nitrogen to buy.

The product

One model family, three decision moments.

The forecast is re-issued as information arrives. It starts as a wide distribution built from field history and seasonal ENSO signal, and tightens each week once the crop is visible from orbit.

4โ€“6 months out ยท strategic

Planning

Before the crop is chosen. Field history, soil analysis, previous crop and seasonal outlook produce a yield scenario for each candidate crop โ€” maize, soy, wheat/soy double-crop, sunflower, sorghum. Answers: what should this field grow?

1โ€“2 months out ยท tactical

Organisation

The crop is set; the management is not. Sowing date, hybrid, density and the N-P-S plan enter the model against a 30โ€“60 day sub-seasonal forecast. Answers: how should we sow it?

Weekly, from emergence ยท operational

In-crop

The crop is growing and observable. NDVI and vegetation indices, actual rainfall and temperature, accumulated stress, achieved stand and phenological stage refresh the forecast every week. Answers: what will it actually yield?

Forecast distribution through one campaign
Early maize ยท one field ยท uncertainty narrows as the season resolves
Median forecast (P50) 80% interval (P10โ€“P90) Observed at harvest
View as table
StageP10 (t/ha)P50 (t/ha)P90 (t/ha)Interval width
Illustrative product output showing the intended behaviour of the forecast โ€” not validated model results. The December step reflects a dry spell during flowering pulling the median down while the interval keeps contracting.
Resolution

Forecasts at 300 mยฒ, not per farm.

Every source โ€” harvest monitor, satellite, weather, soil โ€” is normalised onto a shared Uber H3 resolution-12 hexagonal grid. That makes heterogeneous datasets from different companies directly comparable, and it puts the prediction at the scale precision equipment actually operates on.

Predicted yield within a single 104 ha field
Each hexagon โ‰ˆ 300 mยฒ (H3 r12), aggregated for display
6 t/ha 14 t/ha
Illustrative product output, not validated model results. Field mean 9.8 t/ha โ€” the same field contains zones a full 8 t/ha apart.

Why the grid matters

  • Hexagons have uniform neighbour distance, unlike squares โ€” spatial features like local slope and neighbourhood stress behave consistently.
  • One join key across every source. Sentinel-2 pixels, radar rainfall, soil samples and combine yield monitors all land in the same cell.
  • Prescription-ready output. Sub-field predictions map straight onto variable-rate seeding and fertilisation.
  • Recoverable coverage. Where harvest maps are missing or unreliable, satellite-to-yield relationships learned on clean fields fill the gap.
The signal

The crop tells you what it's doing โ€” if you're watching every five days.

Sentinel-2 returns a 10 m multispectral image of every field roughly every five days. The shape of the vegetation-index curve โ€” when it rises, how high it peaks, how fast it senesces โ€” carries most of the in-crop yield signal, and a departure from the historical curve is an early warning long before harvest.

NDVI trajectory ยท early maize
Current campaign against the five-season median for the same field
Current campaign 5-season median
View as table
DateCurrent campaign5-season medianฮ”
Illustrative product output, not validated model results. The post-January divergence is the pattern the in-crop model is built to catch: a strong vegetative phase followed by accelerated senescence during grain fill.
Platform

A spatial feature store is the asset.

Models come and go. What compounds is a clean, quality-scored, spatially standardised record of what was planted, what the weather did, what the satellite saw and what the combine measured โ€” across many farms and many seasons.

Farm management records Harvest monitor maps Soil analysis Sentinel-2 Weather radar & stations ENSO / sub-seasonal forecasts
โ†“
Ingestion & normalisationโ†’ QA/QC & reliability scoringโ†’ H3 r12 standardisation
โ†“
Spatial feature store
โ†“
Planning model Organisation model In-crop model
โ†“
Probabilistic yield ยท per field & per hexagon

Cloud-native by necessity

A single Pampas season is millions of hexagons ร— a 5-day image cadence ร— a decade of history. Ingestion, index computation and backfill run as elastic batch jobs against object storage rather than on fixed hardware.

Open data where it exists

Sentinel-2 is published as cloud-optimised imagery in public cloud registries, so imagery is read in place instead of being copied. Public soil, climate and radar products are integrated the same way.

Physiology plus learning

Process-based crop models supply physiological structure โ€” degree-day accumulation, stage-specific stress sensitivity โ€” that machine learning alone tends to get wrong in seasons unlike the training set.

Where we are

Development roadmap.

Rindecast is an early-stage company building on applied research into combining process-based crop modelling with machine learning for early maize in the Argentine Pampas.

MilestoneHorizonOutcome
Data architectureMonths 0โ€“6 Common data model across partner farms, H3 r12 grid implemented, first formal QA/QC pass and per-source reliability diagnosis.
First predictive modelMonth 12 In-crop dynamic model for early maize with temporal and regional validation; probabilistic output per field and per hexagon.
Multi-model, multi-cropMonth 24 Planning, organisation and in-crop models across maize, soy, wheat/soy, sunflower and sorghum on a stable feature store.
Decision simulationMonth 36 Prescriptive layer โ€” simulate management and climate scenarios, evaluate technical and economic impact.
Get in touch

Partner farms and agtech collaborators welcome.

We work with Argentine agricultural companies willing to contribute historical production data in exchange for forecasts on their own fields.

hello@rindecast.com