A spatial intelligence layer for agriculture
We reconstruct every plant in a greenhouse from a simple weekly camera pass, and turn that continuously updated 3D state into harvest forecasts a grower can commit retail volume on. The forecast is the first thing we ship. The deeper aim is what the data makes possible — a learned model of how living systems grow, ripen, and fail.
Greenhouse growers commit to retailers and labour crews weeks before fruit ripens; today they bridge the gap with manual sampling and gut feel. We replace the sample with a census — every plant captured weekly and reconstructed in 3D1, read directly by modern computer-vision and forecasting models alongside the climate sensors growers already run. Harvest forecasting is where we start, because it is the problem growers pay to solve. But the weekly 3D record it produces is the real asset: the substrate for learned models of how living systems grow, ripen, and fail.
The 3D reconstruction and the harvest forecast are real, and they ship first — but they are the foothold, not the destination. Underneath them we are accumulating something rarer: a continuously growing, plant-resolution record of how living things develop in space and over time, joined to what they actually go on to do. Text taught machines to write; video is teaching them physics. A dense, four-dimensional record of growing systems — tied to real outcomes — is the training ground for something that hasn't existed before: a learned model of the living world3. That is what we mean by Earth Models.
Yield forecasting on greenhouse tomato is the wedge — a problem growers pay to solve, on a crop that lets us validate weekly. It funds the work, and it switches on the data engine. The forecast is the first thing we ship; it was never meant to be the last thing we build.
Every weekly pass extends a four-dimensional archive — each plant, each fruit, in geometry, across time — joined to the harvest weights, the stress events, the response to every change in water and light. Not block averages reconstructed after the fact, but the living system measured as it unfolds. This corpus is the asset; the product is how we earn the right to grow it.
Train on that substrate and the geometry stops being a record and becomes a model — one that learns how living systems grow, ripen, respond, and fail. One crop, then many; the greenhouse, then the open field. World models, for the living world. The tomato is simply where it starts.
Existing yield systems count in 2D and pay for it twice — fruit hidden behind leaves goes uncounted, and the same fruit gets re-counted across frames as the camera moves. Our edge is to reconstruct the canopy in 3D, so we see around occlusions, never double-count, and recover the metric that operators actually trade on: kilograms, not counts.
A handheld or rail-mounted camera (an Insta360 works) sweeps each row weekly. We pair an off-the-shelf detector stack (YOLO6 + SAM) with structure-from-motion and 3D Gaussian Splatting1 to lift every row into a geometrically faithful, spatially registered 3D scene — each fruit a tracked instance with a position, a size, and a persistent identity across captures — building on recent work in 3D plant capture4 and photorealistic greenhouse reconstruction5.
Each tracked fruit is staged green → breaker → ripe from its 3D appearance. Knowing where each fruit sits in the ripening pipeline — not just how many there are — is what lets us forecast a harvest curve rather than a single number. Robustness across glazing, supplemental LEDs, and Mediterranean tunnel light is the open frontier we're investing in.
Tomato and pepper ripening is dominantly temperature-driven2. We pair the per-fruit pipeline from M.01–M.02 with greenhouse climate data (temperature, daily light integral) to project when each cohort ripens and what it will weigh — kilograms harvestable per zone, per week, with uncertainty bands. Calibration is per-house and improves with every harvest cycle.
The 3D capture is what makes everything downstream tractable: a weekly geometric record of the operation is a state representation in the modern ML sense — the kind of input recent computer-vision and forecasting research has learned to consume directly. Sized cohorts and ripening stages drive the harvest forecast. Geometry-and-colour anomalies can feed stress and disease detectors. Plant-level response to a fertigation change becomes attributable instead of averaged out. Pair that with the operator's existing climate and soil sensors and the result is a closed loop: measure → predict → act → re-measure.
| Manual sampling | Earth Models (target) | |
|---|---|---|
| Coverage | ~ 10 plants / block | Census of every plant we walk |
| Volume / weight | Sparse sample, extrapolated | Per-fruit, from 3D geometry (target ± 5 %) |
| Cadence | Weekly, sparse | Weekly, exhaustive |
| Forecast horizon | Gut-feel | 1 – 3 weeks, calibrated |
FIRST PRODUCT
A grower commits twice before any fruit is in hand: to a marketer for retail volume, and to a labour contractor for the picking crew. Both are paid for in days, not weeks. Under-deliver and you eat penalties or lose the listing; over-produce and you dump ripe fruit at fire-sale prices. We replace gut-feel with measured geometry — the same number drives both commitments.
Retail supply contracts run on volume and consistency. A credible weekly forecast earns better terms — and avoids the fill-rate penalties and lost listings that follow a miss.
Pickers are booked days ahead. Knowing the ripening load by zone means no idle crews on slow days and no over-ripe fruit on heavy ones.
A ripe tomato has days, not weeks. Forecast accuracy is the difference between selling at a contracted price and dumping the surplus into the wholesale market.
The same forecast sizes packing-line shifts, graders, cold-chain, and transport. Get the forecast right and the whole post-harvest chain stops absorbing slack.
A startup learns at the rate of its predict → harvest → compare cycle. Crops with one harvest a year — apples, grapes, wheat — give a single validation event per season; we'd fail once and die. We pick continuously-harvested crops in controlled environments, where calibration is weekly.
Tabletop day-neutral strawberry
Flower-to-ripe in 3–4 weeks, picked every 2–3 days, day-neutral varieties fruit continuously. Tabletop systems hang fruit below the canopy, so occlusion is minimal — the cleanest substrate to converge the perception model fast. We can validate a one-week forecast every week.
Indeterminate greenhouse tomato
An 8–11 month cycle harvested weekly yields 30–40 prediction-vs-actual events from a single crop, with hundreds of fruit per plant. It is the dominant Mediterranean greenhouse crop, the substrate the existing players validate on, and the natural commercial home for the product.
Each direction below has the same shape: feed the weekly canopy state into a learned model, get back a decision a grower used to make on intuition. These are bets, not shipping features — but they are the reason we build the measurement layer in the first place. The shorter the capture-to-action loop, the more the operation shifts from managed to self-correcting.
Each tracked fruit becomes a time series — size, shape, ripening rate per cultivar and per zone. Phenotype data dense enough to inform variety selection and crop steering.
Anomalies in geometry, colour, and growth rate often precede the visible disease signal by days. With a weekly baseline of "normal" per zone, the deviations become detectable.
Irrigation, fertigation, and climate setpoints are decided today against per-block averages. Plant-resolution measurement makes it possible to tie input changes to actual fruit-load response.
Premium-grade volume is what moves price. Per-fruit geometry plus illumination-corrected appearance is the route to forecasting it — once the underlying staging model is robust enough.
3D capture is the input. Learned models on that state are the engine. Less waste, better decisions, faster response is the output. Yield forecasting is simply the first place we ship it.
If you run a tomato or strawberry operation under glass or tunnel and want a forecast credible enough to commit retail volume on, we're looking for a few partner sites for the 2026 season. Concierge capture, your harvest logs as ground truth, transparent reporting.
contact@earthmodels.ag