Combining Open-Source Machine Learning and Publicly Available Aerial Data (NAIP and NEON) to Achieve High-Resolution High-Accuracy Remote Sensing of Grass–Shrub–Tree Mosaics
Woody plant encroachment (WPE) is transforming grasslands globally, yet accurately mapping this process remains challenging. State-funded, publicly available high-resolution aerial imagery offers a potential solution, including the USDA’s National Agriculture Imagery Program (NAIP) and NSF’s Nationa...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/13/2224 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849427532140511232 |
|---|---|
| author | Brynn Noble Zak Ratajczak |
| author_facet | Brynn Noble Zak Ratajczak |
| author_sort | Brynn Noble |
| collection | DOAJ |
| description | Woody plant encroachment (WPE) is transforming grasslands globally, yet accurately mapping this process remains challenging. State-funded, publicly available high-resolution aerial imagery offers a potential solution, including the USDA’s National Agriculture Imagery Program (NAIP) and NSF’s National Ecological Observatory Network (NEON) Aerial Observation Platform (AOP). We evaluated the accuracy of land cover classification using NAIP, NEON, and both sources combined. We compared two machine learning models—support vector machines and random forests—implemented in R using large training and evaluation data sets. Our study site, Konza Prairie Biological Station, is a long-term experiment in which variable fire and grazing have created mosaics of herbaceous plants, shrubs, deciduous trees, and evergreen trees (<i>Juniperus virginiana</i>). All models achieved high overall accuracy (>90%), with NEON slightly outperforming NAIP. NAIP underperformed in detecting evergreen trees (52–78% vs. 83–86% accuracy with NEON). NEON models relied on LiDAR-based canopy height data, whereas NAIP relied on multispectral bands. Combining data from both platforms yielded the best results, with 97.7% overall accuracy. Vegetation indices contributed little to model accuracy, including NDVI (normalized digital vegetation index) and EVI (enhanced vegetation index). Both machine learning methods achieved similar accuracy. Our results demonstrate that free, high-resolution imagery and open-source tools can enable accurate, high-resolution, landscape-scale WPE monitoring. Broader adoption of such approaches could substantially improve the monitoring and management of grassland biodiversity, ecosystem function, ecosystem services, and environmental resilience. |
| format | Article |
| id | doaj-art-e8e777f7d99f4168b07fb2a9f4a667fa |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-e8e777f7d99f4168b07fb2a9f4a667fa2025-08-20T03:28:59ZengMDPI AGRemote Sensing2072-42922025-06-011713222410.3390/rs17132224Combining Open-Source Machine Learning and Publicly Available Aerial Data (NAIP and NEON) to Achieve High-Resolution High-Accuracy Remote Sensing of Grass–Shrub–Tree MosaicsBrynn Noble0Zak Ratajczak1Division of Biology, Kansas State University, 116 Ackert Hall, Manhattan, KS 66506, USADivision of Biology, Kansas State University, 116 Ackert Hall, Manhattan, KS 66506, USAWoody plant encroachment (WPE) is transforming grasslands globally, yet accurately mapping this process remains challenging. State-funded, publicly available high-resolution aerial imagery offers a potential solution, including the USDA’s National Agriculture Imagery Program (NAIP) and NSF’s National Ecological Observatory Network (NEON) Aerial Observation Platform (AOP). We evaluated the accuracy of land cover classification using NAIP, NEON, and both sources combined. We compared two machine learning models—support vector machines and random forests—implemented in R using large training and evaluation data sets. Our study site, Konza Prairie Biological Station, is a long-term experiment in which variable fire and grazing have created mosaics of herbaceous plants, shrubs, deciduous trees, and evergreen trees (<i>Juniperus virginiana</i>). All models achieved high overall accuracy (>90%), with NEON slightly outperforming NAIP. NAIP underperformed in detecting evergreen trees (52–78% vs. 83–86% accuracy with NEON). NEON models relied on LiDAR-based canopy height data, whereas NAIP relied on multispectral bands. Combining data from both platforms yielded the best results, with 97.7% overall accuracy. Vegetation indices contributed little to model accuracy, including NDVI (normalized digital vegetation index) and EVI (enhanced vegetation index). Both machine learning methods achieved similar accuracy. Our results demonstrate that free, high-resolution imagery and open-source tools can enable accurate, high-resolution, landscape-scale WPE monitoring. Broader adoption of such approaches could substantially improve the monitoring and management of grassland biodiversity, ecosystem function, ecosystem services, and environmental resilience.https://www.mdpi.com/2072-4292/17/13/2224bush encroachmenteastern red cedarland useland coversupervised classification |
| spellingShingle | Brynn Noble Zak Ratajczak Combining Open-Source Machine Learning and Publicly Available Aerial Data (NAIP and NEON) to Achieve High-Resolution High-Accuracy Remote Sensing of Grass–Shrub–Tree Mosaics Remote Sensing bush encroachment eastern red cedar land use land cover supervised classification |
| title | Combining Open-Source Machine Learning and Publicly Available Aerial Data (NAIP and NEON) to Achieve High-Resolution High-Accuracy Remote Sensing of Grass–Shrub–Tree Mosaics |
| title_full | Combining Open-Source Machine Learning and Publicly Available Aerial Data (NAIP and NEON) to Achieve High-Resolution High-Accuracy Remote Sensing of Grass–Shrub–Tree Mosaics |
| title_fullStr | Combining Open-Source Machine Learning and Publicly Available Aerial Data (NAIP and NEON) to Achieve High-Resolution High-Accuracy Remote Sensing of Grass–Shrub–Tree Mosaics |
| title_full_unstemmed | Combining Open-Source Machine Learning and Publicly Available Aerial Data (NAIP and NEON) to Achieve High-Resolution High-Accuracy Remote Sensing of Grass–Shrub–Tree Mosaics |
| title_short | Combining Open-Source Machine Learning and Publicly Available Aerial Data (NAIP and NEON) to Achieve High-Resolution High-Accuracy Remote Sensing of Grass–Shrub–Tree Mosaics |
| title_sort | combining open source machine learning and publicly available aerial data naip and neon to achieve high resolution high accuracy remote sensing of grass shrub tree mosaics |
| topic | bush encroachment eastern red cedar land use land cover supervised classification |
| url | https://www.mdpi.com/2072-4292/17/13/2224 |
| work_keys_str_mv | AT brynnnoble combiningopensourcemachinelearningandpubliclyavailableaerialdatanaipandneontoachievehighresolutionhighaccuracyremotesensingofgrassshrubtreemosaics AT zakratajczak combiningopensourcemachinelearningandpubliclyavailableaerialdatanaipandneontoachievehighresolutionhighaccuracyremotesensingofgrassshrubtreemosaics |