Geology Reports⌕ Search
Home/Archive/USGS

USGS · 70024295

A strategy for estimating the rates of recent United States land-cover changes

Thomas R. Loveland·Terry L. Sohl·S.V. Stehman·Alisa L. Gallant·K. L. Sayler·D.E. Napton
View original source ↗Export metadata ↓

Abstract

Information on the rates of land-use and land-cover change is important in addressing issues ranging from the health of aquatic resources to climate change. Unfortunately, there is a paucity of information on land-use and land-cover change except at very local levels. We describe a strategy for estimating land-cover change across the conterminous United States over the past 30 years. Change rates are estimated for 84 ecoregions using a sampling procedure and five dates of Landsat imagery. We have applied this methodology to six eastern U.S. ecoregions. Results show very high rates of change in the Plains ecoregions, high to moderate rates in the Piedmont ecoregions, and moderate to low rates in the Appalachian ecoregions. This indicates that ecoregions are appropriate strata for capturing unique patterns of land-cover change. The results of the study are being applied as we undertake the mapping of the rest of the conterminous United States.

Explore related subjects

Photogrammetric Engineering and Remote SensingArticle

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Thomas R. Loveland, Terry L. Sohl, S.V. Stehman, Alisa L. Gallant, K. L. Sayler, D.E. Napton. 2002. A strategy for estimating the rates of recent United States land-cover changes. https://pubs.usgs.gov/publication/70024295

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related USGS reports

USGS2025

Evaluating Three-Dimensional Elevation Program lidar consistency and accuracy at scale using cloud-native, open-source methods

The U.S. Geological Survey three-dimensional elevation program (3DEP) has significantly expanded national lidar coverage, necessitating scalable, reproducible methods for assessing data quality across diverse terrains and acquisition conditions. This study introduces a cloud-native, open-source workflow designed to evaluate the geometric accuracy and consistency of 3DEP lidar data sets at a national scale. Leveraging tools such as the Point Data Abstraction Library, Open3D, and Amazon Web Services infrastructure, the workflow integrates global navigation satellite system‐surveyed ground control points and terrestrial laser scanning data to validate airborne lidar collections. Two case studies demonstrate the application of this process. In Puerto Rico, the process identified vertical biases and inconsistencies in vegetated areas, while in Iowa and Arizona, the process confirmed high vertical accuracy with minimal bias. The results underscore the effectiveness of combining cloud computing with open-source tools to perform large-scale lidar data quality assessments. This process offers a reproducible, efficient solution for nationwide validation of 3DEP data sets, supporting enhanced decision-making in geospatial applications.

Photogrammetric Engineering and Remote Sensing↗
USGS2025

Artificial neural network multilayer perceptron models to classify California’s crops using Harmonized Landsat Sentinel (HLS) data

Advances in remote sensing and machine learning are enhancing cropland classification, vital for global food and water security. We used multispectral Harmonized Landsat 8 Sentinel-2 (HLS) 30-m data in an artificial neural network (ANN) multi-layer perceptron (MLP) model to classify five crop classes (cotton, alfalfa, tree crops, grapes, and others) in California's Central Valley. The ANN MLP model, trained on 2021 data from the United States Department of Agriculture's Cropland Data Layer, was validated by classifying crops for an independent year, 2022. Across the five crop classes, the overall accuracy was 74%. Producer's and user's accuracies ranged from 65% to 87%, with cotton achieving the highest accuracies. The study highlights the potential of using deep learning with HLS time series data for accurate global crop classification.

California↗