# Annual National Land Cover Database

USGS — version 1.1

## Description

This dataset characterises land cover class, land cover change, impervious surface class, fractional impervious surface (%), and spectral change day of year at 30 m spatial resolution. Coverage is for the conterminous United States annually from 1985 onwards, delivered in Albers Equal Area Conic CRS. Pixels are assigned one of 16 land cover classes.

## Summary

- **ID:** 2ce9cb24-dba0-4f5e-89e1-d8fa5f5db7dc
- **Type:** Raster
- **CRS:** See description
- **Spatial coverage:** Conterminous US
- **Spatial resolution:** 30 m
- **Temporal coverage:** 1985+
- **Temporal resolution:** Annual

## Usage notes

New time points are delivered annually. Spatial coverage is limited to the conterminous United States. Land cover values are associated with a July 1st date, so changes after this date appear in the following year's data.

## Variables

### land_cover
- **Type:** uint8
- **NoData:** 250
Index of the predicted land cover class. Predictions are made using deep learning models trained on National Land Cover Database 2019 labels, Landsat data, and a range of ancillary datasets.

### land_cover_change
- **Type:** uint16
- **NoData:** 9999
Index indicating land cover change between consecutive years, if present.

### land_cover_confidence
- **Type:** uint8
- **Units:** %
- **NoData:** 250
Probability value for the land cover class. Values are calculated by transforming neural network outputs into probabilities.

### fractional_impervious_surface
- **Type:** uint8
- **Units:** %
- **NoData:** 250
Percentage of a pixel covered with artificial impermeable surfaces. Data is generated using regression models trained on National Land Cover Database 2019 impervious labels.

### impervious_descriptor
- **Type:** uint8
- **NoData:** 250
Sub-index of developed land cover classes. Predictions are made using deep learning models trained on National Land Cover Database 2019 labels, Landsat data, and a range of ancillary datasets.

### spectral_change_day_of_year
- **Type:** uint16
- **NoData:** 9999
Day of year when substantial surface reflectance changes were detected in Landsat data. Data is generated using a continuous change detection algorithm to detect deviations in spectral behaviour of Landsat data over time.

## Pricing

This dataset has no data acquisition cost.