AtmosGrid — Planetary IntelligenceCOMMERCIAL PRODUCT
Solar panels and wind turbines at sunset

SOLAR ENERGY / DECISION WORKSPACE

Make the next energy decision with atmosphere in view.

Four diagnostic tools for solar operators, air quality teams and environmental analysts — grounded in satellite observations, GFS fields and honest data limits.

Satellite context · Atmospheric forecasts · Operator-led decisions
Illustrative energy infrastructure imagery · Not a live satellite observation

FROM ORBIT TO OPERATIONS

Four signals.
One clearer picture.

Start with the diagnostic your team needs. Each module explains the question it answers, the inputs it requires and what still needs local validation — so solar operators and analysts know what to do next.

01

Attribute forecast errors to atmosphere

02

Monitor dust and cloud in real time

03

Flag low-confidence air quality cells

04

Track land-cover and dust-source change

THE SOLAR TOOLKIT

Choose the diagnostic
you need to run.

Open a module for its workflow, example scenarios, required inputs, API request and capability boundaries.

Cloud shadows passing over a utility-scale solar farm01 / SOLAR PRODUCT
Solar forecast error attributionAVAILABLE · POST ENDPOINT

Why did this hour's generation differ from the forecast?

Compare observed versus forecast generation for each hour. Isolate the contribution of cloud cover, aerosol optical depth, dust risk and panel temperature to the error. Improve future forecasts with transparent, machine-readable attribution.

DATA SIGNALS

Hourly forecast (kWh/kWp) · Hourly observed (kWh/kWp) · Cloud cover (%)

Explore product ↗
Atmospheric dust plume crossing the Gulf coast02 / SOLAR PRODUCT
Dust & cloud observation feedAVAILABLE · GET ENDPOINT

What did the atmosphere look like above the plant in the past 24 hours?

A maintained regional feed of cloud cover, aerosol optical depth, shortwave radiation and estimated PV generation potential. Gives solar operators a consistent satellite-derived input feed to cross-check internal forecasts and diagnose persistent biases.

DATA SIGNALS

Latitude / Longitude · hours_back (1–72)

Explore product ↗
Gulf coastal city seen through morning atmospheric haze03 / SOLAR PRODUCT
Air quality data confidenceAVAILABLE · GET ENDPOINT

Which cells in the air quality map can we publish confidently — and which need a caution flag?

A grid of observation age, satellite coverage fraction, nearby ground-station count and uncertainty flags for each map cell. Helps air quality teams distinguish well-supported estimates from sparse-observation zones before publishing public air quality maps.

DATA SIGNALS

resolution_km (10–100) · lat_min, lat_max · lon_min, lon_max

Explore product ↗
Desert, coast, and cultivated land in the UAE from above04 / SOLAR PRODUCT
UAE environmental change feedAVAILABLE · GET ENDPOINT

Which areas in the UAE have changed — and what kind of change is it?

Timestamped imagery pairs, spectral change scores, cover-class transitions and review status for UAE cells. Supports solar-site monitoring, dust source tracking and urban-growth analysis without manufacturing conclusions from uncertain signals.

DATA SIGNALS

change_class · confidence_min (0–1) · limit (1–100)

Explore product ↗

CLEAR ABOUT THE DATA

Satellite signals guide attention.
Plant measurements guide action.

Satellite and forecast products describe atmospheric conditions at their own resolution and update cadence. They can help operators spot patterns, correlate errors and schedule maintenance.

Panel soiling, tracker faults, inverter curtailment, and ground irradiance calibration are not inferred when they are missing. Review each module's data gaps before using a result operationally.

Read the API documentation ↗