For peatland restoration managers, water companies, and field researchers

Peatland
flux, forecast.

We'll find a way.

Restored peatlands take decades to recover, but management decisions can't wait for annual surveys. MAZE produces 96-hour net ecosystem exchange forecasts for any UK peatland — calibrated to the European flux tower network, validated against ground truth, delivered without on-site instrumentation. Catch heatwave-driven respiration before it happens. See your site breathing, hour by hour.

Today, peatland decisions
wait for annual surveys.

01

Restoration moves in years; decisions don't

A typical restoration site is monitored through annual or biennial chamber surveys, with results returned months later. By then, the management window for responding to a dry summer or a hydrological intervention has closed.

02

Flux towers are out of reach

Eddy-covariance towers produce the gold standard for site-level carbon flux, but cost £50,000–100,000 to install and require specialist maintenance. Fewer than 20 operate across the UK — none on most active restoration projects.

03

Sites fly blind during the seasons that matter most

Carbon flux is most volatile and most consequential during summer growing seasons. Without continuous forecasting, anomalous flux events — heatwave-driven respiration, hydrological tipping points — are only discovered after the fact, in retrospective analyses.

04

Research-grade monitoring stops at the research site

The UK has world-leading peatland flux research at Auchencorth Moss, Forsinard, and a handful of others. The 99% of restoration projects without research infrastructure rely on emission-factor estimates and visual inspection.

A 96-hour forecast,
calibrated to ground truth.

i.

Locate

Draw a site polygon, classify the peatland (blanket bog, raised bog, fen), and we pull historical flux dynamics for the site's ecosystem class. No on-site instrumentation required to get started.

No on-site instrumentation required
ii.

Forecast

A fine-tuned 80M-parameter time-series foundation model produces a 96-hour hourly NEE forecast. Pre-trained on diverse temporal signals across multiple domains, adapted on European peatland flux tower records, and validated against held-out FLUXNET2015 sites.

Validated R² = 0.68–0.74 on held-out sites
iii.

Monitor

Ensemble disagreement provides per-hour 95% confidence intervals. High-uncertainty regimes — typically summer high-VPD days — are flagged explicitly. Track day-to-day changes, catch anomalies, support management decisions with evidence.

Calibrated uncertainty bounds

See a live forecast
for a real bog.

These are live 96-hour forecasts from MAZE's fine-tuned TEMPO-80M models, benchmark-validated against held-out FLUXNET2015 eddy-covariance sites. The preset markers return instantly from pre-computed forecasts; draw your own site on the map and you're watching real inference run — up to ~90 seconds on our CPU instance.

draw your site →
Loading sites…

96-hour mean NEE
μmol CO₂ m⁻² s⁻¹
95% CI: — to —
Forecast skill (R²)
High-uncertainty hours
%
flagged for review
96-hour NEE forecast — μmol CO₂ m⁻² s⁻¹ · with 95% bootstrap interval
Loading forecast…
Model unavailable — try again shortly.
No forecast here
Select a location on a peatland landmass. MAZE's validated region is the UK.
live · —

Continuous forecasting
vs. periodic monitoring.

Conventional approach

Periodic chamber surveys

Frequency Annual or biennial
Temporal resolution Snapshot in time
Coverage Field campaigns only
Anomaly detection Retrospective only
Cost per site / year £5,000–15,000
Decision support
Months delayed
Annual summary returned post-season
MAZE

MAZE 96-hour forecasting

Frequency Continuous (rolling forecast)
Temporal resolution Hourly · 96 h ahead
Coverage Any UK peatland with a polygon
Anomaly detection 96 h forecast horizon
Cost per site / year £500–2,000 (subscription)
Decision support
Live operational forecast
Validated R² = 0.68–0.74 against held-out flux towers

Built on peer-reviewed research, not buzzwords.

Methodology

Foundation-model carbon flux forecasting

MAZE's predictor is a fine-tuned TEMPO-80M time-series foundation model, evaluated for cross-ecosystem carbon flux forecasting across seven European FLUXNET sites including held-out wetland and forest reference sites.

Validation

Reproduced against held-out FLUXNET sites

MAZE's carbon flux models are validated against held-out FLUXNET2015 eddy-covariance sites, reproducing measured net ecosystem exchange to R² = 0.60 (same-ecosystem wetland, UK-AMo) and R² = 0.73 (cross-ecosystem forest, SE-Htm) at the 96-hour horizon. Forest-TEMPO lifts forest performance to R² = 0.77.

Deployed-model validation report →

Roadmap

Annual carbon balance methodology in development

The current product delivers 96-hour operational forecasts validated against the published benchmark. Extending the methodology to a defensible annual carbon balance — the Peatland Code use case — is on the roadmap, planned as a separate product line.

Talk to us
about your project.

Early Access · Pilot Partners