Skip to content
ModelEarth · planetary-scale climate resilience intelligence

Earth is already instrumented. The warning still does not arrive.

Satellites overhead, gauges in the water, sensors in the soil, thirty years of record on disk. Observation stopped being the hard part decades ago. What is missing is the layer that turns all of it into a decision somebody can act on tonight.

02 · the climate intelligence layer

We sit between the observation and the decision.

One engine takes what the sky, the rivers and the historical record already know, resolves it against each location’s own thirty-year baseline, and issues a call with the reasoning attached. Hazard-agnostic by design.

03 · planetary resilience intelligence

Planetary means the ungauged parts too.

Most of the inhabited world has no local model for what reaches it: water, heat, or a season that fails. That is where a warning is worth the most, so this makes a defensible call from a thin record and sharpens as the record fills in.

04 · resilience

Measured in hours of warning, not points of accuracy.

The unit that matters is lead time: the hours a district gets to move people, grain and livestock before it lands. Water tonight, heat in May, a sowing window closing. One engine, one number, whatever the hazard.

ALT
19.0 km
REACH
01 · HIRAKUD
Scroll to fly the reach
01 · Why a real basin changes the room

A generic valley is a screensaver. Your valley is evidence.

Every flood platform demo opens with terrain. Almost all of it is invented, and everyone in the room knows it, so the visual carries no weight at all. It is treated as wallpaper and skipped.

The moment the terrain is the actual basin, the hero stops being decoration and starts doing the same job as the replay: it is a claim that can be checked. An officer can look at where we put Cuttack and tell us if we are wrong.

Mahanadi reach
02 · What runs on that ground

Five cities, every thirty minutes, wet or dry.

A rule engine an engineer wrote and a district can argue with. Rainfall against each location’s own thirty-year threshold, yesterday’s rain that stops decaying during an active flood, and a river term that only counts when the gauge is genuinely live.

The position, August 2026 - stated the way we would want it stated back to us

0

cities alerting: Bhubaneswar, Cuttack, Puri, Sambalpur, Rourkela

Live
0min

scoring cycle, every day of the year, wet or dry

Live
0h

lead on all six onsets in the August 2026 north Odisha replay

Backtest
14/18

location-days scored LOW while people were still displaced

Miss

The ML model runs beside the engine in shadow and cannot alter a user-facing score. Heat has no live mode in the code at all. There is no signed MoU and no paying customer.

03 · The position, August 2026

The trust gate is not passed, and the hero does not pretend otherwise.

The flood engine alerts on five cities. The ML model runs beside it in shadow and cannot alter a user-facing score. Heat has no live mode in the code at all. There is no signed MoU and no paying customer.

Live

In production, driving user-facing alerts.

Backtest

Measured on history. Never quoted as live accuracy.

Shadow

Computed and published, structurally unable to alert.

Miss

The engine was wrong, and here is the write-up.

Every claim on this site carries one of those labels. Read the evidence before you believe the thesis, including the numbers that went against us.

The only metric that matters: one family, one more day

Name a flood. We will fly it and replay it.

Pick an event your district remembers. We run the unmodified engine on the forecast as it was issued that week, over the ground it actually happened on, and you see exactly when it would have fired, or that it would not have.

District pilot

One district, one monsoon, and a standing invitation to tell us every time we were wrong.

Replay request

Name an event your district remembers. We run the unmodified engine on the forecast exactly as it was issued that week.

Investors

We are raising a pre-seed. The engine already runs in production. What it lacks is reach, so the raise buys an ML engineer and a partnerships lead.