Landscape Change Monitoring System
Description
This dataset maps annual land cover, land use, and landscape change across the conterminous United States at 30 m spatial resolution. Three thematic variables are provided: land cover, land use, and change. An additional quality assessment variable is included as a packed bit string.
The dataset is produced using the LandTrendr time-series segmentation algorithm applied to Landsat and Sentinel-2 imagery. The change variable identifies the cause of short- and long-term vegetation disturbance events, as well as water desiccation or inundation and snow/ice transition, using a ruleset approach that incorporates ancillary datasets such as burn severity records, insect and disease surveys, and storm event data.
446d2f29…Usage notes
New time points are delivered approximately annually. Spatial coverage is limited to the conterminous United States. This dataset is best suited for regional to national scale assessments, including analysis of vegetation cover, land cover, or land use change trends, total extents, and aggregated summaries.
No minimum mapping unit has been applied and known features such as roads have not been manually incorporated. Users should exercise caution when applying this data at site or fine-scale levels.
Variables
change
Description
Index of the predicted landscape change class describing the cause of short- or long-term vegetation disturbance events, as well as water desiccation or inundation and snow/ice transition. Predictions are made using a machine learning model whose outputs (slow loss, fast loss, gain) are reclassified using a ruleset incorporating ancillary fire, storm, insect, disease, and land cover datasets.
Usage notes
Stable pixels and non-processing areas are included as explicit classes. Overall accuracy for the conterminous United States is 89.50% at Level 1 (disturbance, growth, or stable) and 92.48% at Level 2; insufficient validation data exists in the TimeSync interpretations to assess accuracy at the delivered Level 3.
| Index | Level 1 | Level 2 | Level 3 |
|---|---|---|---|
| 1 | Disturbance | Wind | Wind |
| 2 | Disturbance | Wind | Hurricane |
| 3 | Disturbance | Other Loss | Snow or Ice Transition |
| 4 | Disturbance | Desiccation | Desiccation |
| 5 | Disturbance | Inundation | Inundation |
| 6 | Disturbance | Fire | Prescribed Fire |
| 7 | Disturbance | Fire | Wildfire |
| 8 | Disturbance | Mechanical Land Transformation | Mechanical Land Transformation |
| 9 | Disturbance | Tree Removal | Tree Removal |
| 10 | Disturbance | Insect, Disease, or Drought Stress | Defoliation |
| 11 | Disturbance | Insect, Disease, or Drought Stress | Southern Pine Beetle |
| 12 | Disturbance | Insect, Disease, or Drought Stress | Insect, Disease, or Drought Stress |
| 13 | Disturbance | Other Loss | Other Loss |
| 14 | Vegetation Successional Growth | Vegetation Successional Growth | Vegetation Successional Growth |
| 15 | Stable | Stable | Stable |
| 16 | Non-Processing Area Mask | Non-Processing Area Mask | Non-Processing Area Mask |
land_cover
Description
Index of the predicted land cover class describing biophysical attributes of the land surface, including vegetation type and other surface conditions. Predictions are made using a machine learning model trained on Landsat and Sentinel-2 time-series data.
Usage notes
Accuracy decreases as thematic detail increases: overall accuracy for the conterminous United States is 95.71% at Level 1 (vegetated vs. non-vegetated), 87.20% at Level 2, 79.11% at Level 3, and 67.18% at the delivered Level 4.
| Index | Level 1 | Level 2 | Level 3 | Level 4 |
|---|---|---|---|---|
| 1 | Vegetated | Tree Vegetated | Tree | Tree |
| 2 | Vegetated | Tree Vegetated | Tree | Tall Shrub & Tree Mix (AK Only) |
| 3 | Vegetated | Tree Vegetated | Tree | Shrub & Tree Mix |
| 4 | Vegetated | Tree Vegetated | Tree | Grass/Forb/Herb & Tree Mix |
| 5 | Vegetated | Tree Vegetated | Tree | Barren & Tree Mix |
| 6 | Vegetated | Non-Tree Vegetated | Shrub | Tall Shrub (AK Only) |
| 7 | Vegetated | Non-Tree Vegetated | Shrub | Shrub |
| 8 | Vegetated | Non-Tree Vegetated | Shrub | Grass/Forb/Herb & Shrub Mix |
| 9 | Vegetated | Non-Tree Vegetated | Shrub | Barren & Shrub Mix |
| 10 | Vegetated | Non-Tree Vegetated | Grass/Forb/Herb | Grass/Forb/Herb |
| 11 | Vegetated | Non-Tree Vegetated | Grass/Forb/Herb | Barren & Grass/Forb/Herb Mix |
| 12 | Non-Vegetated | Non-Vegetated | Barren or Impervious | Barren or Impervious |
| 13 | Non-Vegetated | Non-Vegetated | Snow or Ice | Snow or Ice |
| 14 | Non-Vegetated | Non-Vegetated | Water | Water |
| 15 | Non-Processing Area Mask | Non-Processing Area Mask | Non-Processing Area Mask | Non-Processing Area Mask |
land_use
Description
Index of the predicted land use class describing the intended human use of the land, representing the economic and cultural activities practised at a given place. Predictions are made using a machine learning model trained on Landsat and Sentinel-2 time-series data, with class assignments further refined using ancillary land cover and built-up datasets.
Usage notes
Overall accuracy for the conterminous United States is 90.70% at Level 1 (anthropogenic vs. non-anthropogenic) and 83.93% at the delivered Level 2.
| Index | Level 1 | Level 2 |
|---|---|---|
| 1 | Anthropogenic | Agriculture |
| 2 | Anthropogenic | Developed |
| 3 | Non-Anthropogenic | Forest |
| 4 | Non-Anthropogenic | Other |
| 5 | Non-Anthropogenic | Rangeland or Pasture |
| 6 | Non-Processing Area Mask | Non-Processing Area Mask |
qa_bits
Description
Quality assessment data provided as a packed bit string. Contains ancillary information on the origin of annual pixel values, including whether an interpolated value was used, which sensor the pixel came from, and the Julian day of the year the LandTrendr pixel value was derived from.
Usage notes
Provided as an unparsed packed bit string. Bit 1 encodes whether an observation is interpolated (0) or not interpolated (1). Bits 2-6 encode the source sensor (Landsat 4, 5, 7, 8, 9, Sentinel-2a, or Sentinel-2b). Bits 7-15 encode the Julian day of year (1-365). Bitwise operations are required to unpack individual fields.
Pricing
This dataset has no data acquisition cost.
Resources
Provider
USDA
www.usda.govThe United States Department of Agriculture (USDA) is the U.S. federal agency responsible for developing and executing policy on farming, agriculture, forestry, rural economic development, and food.
USFS
www.fs.usda.govThe United States Forest Service (USFS) is an agency within USDA responsible for managing the country's national forests and grasslands. USFS also conducts forestry research and provides technical and financial assistance to state and private forest landowners.