# Forest Carbon Diligence

Planet — version 1.3.0

## Description

This dataset quantifies aboveground live carbon density (Mg C/ha), canopy cover (%), and canopy height (m) of vegetation at 30 m spatial resolution. Data has global coverage and annual temporal resolution, available from 2013 onwards. Data includes pixel-level variable uncertainties (90% prediction intervals).

## Summary

- **ID:** 53738a57-a889-43c9-8f7a-7cb306831700
- **Type:** Raster
- **CRS:** EPSG:4326
- **Spatial coverage:** Global
- **Spatial resolution:** 30 m
- **Temporal coverage:** 2013+
- **Temporal resolution:** Annual

## Usage notes

New time points are delivered 5-6 months after year end. Spatial coverage is limited to land surfaces between 76°N and 56°S. In urban areas, double-bounce radar backscatter among buildings may result in over-predictions. Circular spatial artefacts can lead to temporal differences between adjacent pixels.

## Variables

### aboveground_live_carbon_density
- **Type:** int16
- **Units:** Mg C/ha
- **NoData:** 32767
Density of carbon stored in live woody vegetation on a per hectare basis. Data is generated using LightGBM regression models trained to predict GEDI L4A aboveground biomass carbon from modelled canopy height, modelled canopy cover, elevation, and location.

### aboveground_live_carbon_density_lower_bound
- **Type:** int16
- **Units:** Mg C/ha
- **NoData:** 32767
90% prediction interval lower bound for aboveground live carbon density variable.

### aboveground_live_carbon_density_upper_bound
- **Type:** int16
- **Units:** Mg C/ha
- **NoData:** 32767
90% prediction interval upper bound for aboveground live carbon density variable.

### canopy_cover
- **Type:** uint8
- **Units:** %
- **NoData:** 255
Relative cover of trees. Data is generated using U-Net image regression models trained to predict > 9 million km² of airborne LiDAR data from a combination of spaceborne remote sensing datasets.

### canopy_cover_lower_bound
- **Type:** uint8
- **Units:** %
- **NoData:** 255
90% prediction interval lower bound for canopy cover variable.

### canopy_cover_upper_bound
- **Type:** uint8
- **Units:** %
- **NoData:** 255
90% prediction interval upper bound for canopy cover variable.

### canopy_height
- **Type:** uint8
- **Units:** m
- **NoData:** 255
Average height (m) of trees. Data is generated using U-Net image regression models trained to predict > 9 million km² of airborne LiDAR data from a combination of spaceborne remote sensing datasets.

### canopy_height_lower_bound
- **Type:** uint8
- **Units:** m
- **NoData:** 255
90% prediction interval lower bound for canopy height variable.

### canopy_height_upper_bound
- **Type:** uint8
- **Units:** m
- **NoData:** 255
90% prediction interval upper bound for canopy height variable.

### day_of_year
- **Type:** uint16
- **NoData:** 32767
Calendar day of the satellite observation.

### observation_quality
- **Type:** uint8
- **NoData:** 255
Planet observation quality score.

## Pricing

This dataset adds a new time point annually. A new subscription returns the full archive up to the most recent time point. Data acquisition costs are per hectare for the full archive:

| Volume | Price |
| --- | --- |
| Any | $0.10 / ha |