Skip to main content
WeatherXM
Data & Forecasts

Weather data anchored in ground truth.

Access physical observations, site forecasts and forecast verification through one commercial interface. Use existing Network coverage, your own WeatherXM stations, or dedicated deployments where the data is missing.

GROUND TRUTH ENGINE
1-MIN INGESTION ACTIVE
01 · OBSERVE QoD 0.998
Physical Ground Truth
Station #WXM-PULSE-4802
38.25°N, 21.74°E · Elev 112m
Ambient Temp 21.4°C
Pressure 1014.2 hPa
Wind Velocity 14.8 km/h NW
ATECC608 Hardware Signed
02 · FORECAST +48h Lead
Site-Anchored Model
Microclimate downscaling
Trained on local ground series
Calibrated Coarse NWP
Bias Adjusted: -2.1°C Local Inversion
03 · VERIFY FACT AUDIT
Continuous Verification
Historical forecast vs observed
Site, variable & horizon score
MAE (Temperature) 0.58°C
RMSE (Wind Speed) 0.74 m/s
Error Reduction -68% vs NWP
Audit Validated Against Ground
DELIVERY: WeatherXM Pro / REST API / x402 Agentic / Akave S3 Bulk
GLOBAL REPUTATION & PROVENANCE
Ground truth observations

Measurements from the places where decisions happen.

WeatherXM observations come from physical stations deployed at homes, farms, industrial sites, ports, energy assets and other real-world locations. They make local conditions measurable where reference networks are too sparse for the decision at hand.

Use current and historical observations for monitoring, analytics, model training, forecast validation and applications that need evidence closer to the ground.

Real-time + history
Temperature, humidity, pressure, wind, precipitation and supported station variables.
Quality + provenance
Station metadata and quality context help explain where a measurement came from and how to use it.
Existing coverage
Use observations already available through the WeatherXM Network where coverage matches your need.
Fill the gaps
Add dedicated WeatherXM stations where the existing observation layer is not dense enough.
LIVE STATION TELEMETRY
WXM-D2-DELTA-9921 · Ground Observation Node
QoD: 0.998
Hardware: WeatherXM D2 Mesh | ATECC608A Signed
Peer Validated (8 stations) GNSS: 37.984°N, 23.727°E
Air Temperature
22.4°C
Dew: 12.1°C Max: 24.6°C
Barometric Pressure
1015.4 hPa
+0.3 hPa/3h (Steady)
Wind Velocity
16.2 km/h
NW · 315° Gust: 26.8
Relative Humidity
52%
Heat Index: 22.1°C
Solar Irradiance
840 W/m²
UV Index: 6.4 High
Precipitation Rate
0.0 mm/h
24h Acc: 4.2 mm
24-Hour Continuous Ground Truth Series (1-min native sample)
Temperature & Solar Cycle
Peak: 24.6°C @ 13:45 UTC
00:00 UTC 04:00 08:00 12:00 16:00 20:00 NOW (22.4°C)
Physical Microclimate Resolution: Captures localized coastal thermal gradient missed by 9km coarse grids.
Commercial interface

WeatherXM AG provides the commercial data and service relationship. The independent WeatherXM Network Association manages Network participation, rewards, governance and Network Dataset licensing. Commercial customers work with WeatherXM AG for delivery, APIs, analytics, support and project-specific requirements.

SITE FORECAST HORIZON
Alpine Basin Renewable Site · Station #4102 (Elev 640m)
Model Cycle: 06:00 UTC Site-Calibrated
Ground Truth (Observed)
WeatherXM Calibrated (+48h)
ECMWF IFS (9km Grid)
GFS (13km Grid)
PAST 24H · GROUND TRUTH
NEXT 48H · FORWARD FORECAST
NOW: 18.2°C
Terrain Bias -3.4°C:
Global model misses nocturnal cold pool
T - 24h T - 12h NOW (00h) T + 12h T + 24h T + 36h T + 48h
WeatherXM Calibrated
MAE: 0.61°C
Anchored to local terrain observations
ECMWF IFS (9km)
MAE: 1.84°C
Coarse grid averages out valley depth
GFS NOAA (13km)
MAE: 2.38°C
4-hour frontal passage phase lag
Forecasts

Put the forecast next to the ground truth.

A forecast becomes more useful when it can be examined against the weather measured at the same location. WeatherXM brings site forecasts and observations into the same workflow so operational users and data teams can see both the prediction and the evidence around it.

1
Site context. View forecasts together with measured weather at the locations and assets you monitor.
2
Provider-agnostic evaluation. Compare supported forecast sources without assuming one model is universally best.
3
Local improvement. Where sufficient history exists, use observations to support calibration, bias correction and site-specific forecast workflows.
Forecast Accuracy Tracking · FACT

Don't guess which forecast is best. Measure it.

FACT archives a forecast before the event, then compares it with the WeatherXM observations collected afterward at the same place and time. That turns forecast quality into something measurable by site, variable and lead time.

Compare
Forecast vs. observation
01
Measure
MAE · RMSE · bias
02
Decide
By site · variable · horizon
03
FACT VERIFICATION ENGINE
Rotterdam Maritime Asset · Station #3104
Lead: Day 1 (24h)
Observed Ground Truth
WeatherXM Calibrated
ECMWF IFS (9km)
GFS (13km)
Audit Sample: 720 Hours
Passing Weather Front · Cold Air Advection & Wind Shift
Global NWP Lag: 3.2 Hours Coarse models delayed rapid frontal cooling.
WeatherXM tracked drop within 12 min.
T - 18h T - 12h T - 6h FRONT ARRIVAL (00h) T + 6h T + 12h T + 18h
Objective Benchmark Scorecard (24h Lead Horizon) -68% Error Reduction
Rank & Model MAE (Temp) RMSE Directional Bias Audit Status
1 WeatherXM Calibrated 0.58°C 0.72°C +0.04°C (Unbiased) Ground Verified ✓
2 ECMWF IFS (0.25°) 1.82°C 2.15°C +1.35°C (Warm bias) Standard NWP
3 GFS NOAA (0.25°) 2.38°C 2.89°C +1.82°C (Warm bias) Standard NWP
4 Customer Model (BYOF) 1.95°C 2.31°C -0.42°C (Cold bias) Custom Ingest

Bring your own forecast.

WeatherXM can evaluate customer-supplied or third-party forecasts against local observations. FACT remains useful even when WeatherXM is not the source of the forecast itself.

Discuss Forecast Verification →
Commercial data products

Use the observation layer at the scale your application needs.

Start with the stations you already operate, add existing Network coverage, license a regional dataset, or deploy new density where the current observation layer is not enough.

01 · Your stations

Monitor deployed sites

Use observations, forecasts and verification around WeatherXM hardware at locations you operate.

02 · Network data

Add existing ground truth

Use existing WeatherXM Network observations in products, analytics, model workflows and operational systems.

03 · Regional datasets

License data at scale

Access historical or ongoing observations across custom geographic areas and larger data pipelines.

04 · Dedicated deployment

Deploy where data is missing

Add station density, connectivity and custom delivery around the exact locations your application needs.

Access layer

Explore in the Portal. Integrate through the API.

WeatherXM Pro is the interactive interface for people working with sites, observations, forecasts and verification. The API exposes the same underlying weather intelligence to software and operational workflows.

For people
WEB INTERFACE

WeatherXM Pro

Explore stations and sites, inspect observations, compare forecasts and analyse forecast performance in one interface.

WeatherXM Pro showing forecast verification and FACT analytics Open WeatherXM Pro ↗
For software
REST API

WeatherXM API

Bring observations, forecasts and analytics directly into software, operational workflows and research pipelines.

GET /api/v1/stations/{station_id}/fact/ranking
FACT
Request
curl -X GET
https://pro.weatherxm.com/api/v1/stations/{station_id}/fact/ranking
-H "X-API-KEY: YOUR_API_KEY"
Response shape
best model per variable / horizon
{
"temperature": [ { "daysAhead": 0, "model": { "name": "WXMv1", "errorDistance": 0.5 } } ],
"humidity": [ ... ],
"precipitation": [ ... ],
"windSpeed": [ ... ],
"windDirection": [ ... ]
}
temperature humidity precipitation windSpeed windDirection
Real WeatherXM Pro API endpoint X-API-KEY authenticated
Read API Documentation ↗
Developer extensions

Machine-native access when you need it.

The WeatherXM API is the primary integration surface. MCP and machine-oriented interfaces extend it for agent and automated workflows where those patterns are useful.

MACHINE-NATIVE DATA ARCHITECTURE HTTP 402 + Model Context Protocol (MCP)
01 Client Layer
Autonomous Agent
LLM agent, MCP tool-caller, or algorithmic trading node querying site ground truth.
MCP Tool: get_current_weather
02 HTTP 402 Protocol
x402 Micropayment
Pay-per-request settlement at $0.001 per request. Zero subscriptions or API key provisioning required.
Sub-second cryptographic settlement
03 Settlement Data
Signed Weather Evidence
Raw or enhanced atmospheric observations with hardware signature and QoD audit context.
agent.weatherxm.com ✓ Signed
Supported Machine Interfaces: Model Context Protocol (MCP) x402 Agent API Akave O3 Parquet
Ready for Production Autonomous Workflows →
Ground truth weather, everywhere.

Tell us where you need weather evidence.

We can start from existing coverage, identify the gaps, and combine observations, forecasts and verification around the locations and decisions that matter to your application.