Detecting the Distribution of Callery Pear (<i>Pyrus calleryana</i>) in an Urban U.S. Landscape Using High Spatial Resolution Satellite Imagery and Machine Learning
Using Planetscope imagery, we trained a random forest model to detect Callery pear (<i>Pyrus calleryana</i>) throughout a diverse urban landscape in Columbia, Missouri. The random forest model had a classification accuracy of 89.78%, a recall score of 0.693, and an F1 score of 0.819. The...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/8/1453 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850144465461706752 |
|---|---|
| author | Justin Krohn Hong He Timothy C. Matisziw Lauren S. Pile Knapp Jacob S. Fraser Michael Sunde |
| author_facet | Justin Krohn Hong He Timothy C. Matisziw Lauren S. Pile Knapp Jacob S. Fraser Michael Sunde |
| author_sort | Justin Krohn |
| collection | DOAJ |
| description | Using Planetscope imagery, we trained a random forest model to detect Callery pear (<i>Pyrus calleryana</i>) throughout a diverse urban landscape in Columbia, Missouri. The random forest model had a classification accuracy of 89.78%, a recall score of 0.693, and an F1 score of 0.819. The key hyperparameters for model tuning were the cutoff and class–weight parameters. After the distribution of Callery pear was predicted throughout the landscape, we analyzed the distribution pattern of the predictions using Ripley’s K and then associated the distribution patterns with various socio-economic indicators. The analysis identified significant relationships between the distribution of the predicted Callery pear and population density, median household income, median year the housing infrastructure was built, and median housing value at a variety of spatial scales. The findings from this study provide a much-needed method for detecting species of interest in a heterogenous landscape that is both low cost and does not require specialized hardware or software like some alternative deep learning methods. |
| format | Article |
| id | doaj-art-34aa0f69626f4bc9b70d58ea60a535e1 |
| institution | OA Journals |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-34aa0f69626f4bc9b70d58ea60a535e12025-08-20T02:28:20ZengMDPI AGRemote Sensing2072-42922025-04-01178145310.3390/rs17081453Detecting the Distribution of Callery Pear (<i>Pyrus calleryana</i>) in an Urban U.S. Landscape Using High Spatial Resolution Satellite Imagery and Machine LearningJustin Krohn0Hong He1Timothy C. Matisziw2Lauren S. Pile Knapp3Jacob S. Fraser4Michael Sunde5Institute for Data Science and Informatics, University of Missouri, Columbia, MO 65211, USASchool of Natural Resources, Institute for Data Science and Informatics, University of Missouri, Columbia, MO 65211, USADepartment of Geography, Department of Civil & Environmental Engineering, Institute for Data Science and Informatics, University of Missouri, Columbia, MO 65211, USAUS Department of Agriculture Forest Service, Columbia, MO 65211, USAUS Department of Agriculture Forest Service, Columbia, MO 65211, USAMU Extension, School of Natural Resources, University of Missouri, Columbia, MO 65211, USAUsing Planetscope imagery, we trained a random forest model to detect Callery pear (<i>Pyrus calleryana</i>) throughout a diverse urban landscape in Columbia, Missouri. The random forest model had a classification accuracy of 89.78%, a recall score of 0.693, and an F1 score of 0.819. The key hyperparameters for model tuning were the cutoff and class–weight parameters. After the distribution of Callery pear was predicted throughout the landscape, we analyzed the distribution pattern of the predictions using Ripley’s K and then associated the distribution patterns with various socio-economic indicators. The analysis identified significant relationships between the distribution of the predicted Callery pear and population density, median household income, median year the housing infrastructure was built, and median housing value at a variety of spatial scales. The findings from this study provide a much-needed method for detecting species of interest in a heterogenous landscape that is both low cost and does not require specialized hardware or software like some alternative deep learning methods.https://www.mdpi.com/2072-4292/17/8/1453<i>Pyrus calleryana</i> Decnedigital image processingspatial clusteringspecies inventoryPlanetscope |
| spellingShingle | Justin Krohn Hong He Timothy C. Matisziw Lauren S. Pile Knapp Jacob S. Fraser Michael Sunde Detecting the Distribution of Callery Pear (<i>Pyrus calleryana</i>) in an Urban U.S. Landscape Using High Spatial Resolution Satellite Imagery and Machine Learning Remote Sensing <i>Pyrus calleryana</i> Decne digital image processing spatial clustering species inventory Planetscope |
| title | Detecting the Distribution of Callery Pear (<i>Pyrus calleryana</i>) in an Urban U.S. Landscape Using High Spatial Resolution Satellite Imagery and Machine Learning |
| title_full | Detecting the Distribution of Callery Pear (<i>Pyrus calleryana</i>) in an Urban U.S. Landscape Using High Spatial Resolution Satellite Imagery and Machine Learning |
| title_fullStr | Detecting the Distribution of Callery Pear (<i>Pyrus calleryana</i>) in an Urban U.S. Landscape Using High Spatial Resolution Satellite Imagery and Machine Learning |
| title_full_unstemmed | Detecting the Distribution of Callery Pear (<i>Pyrus calleryana</i>) in an Urban U.S. Landscape Using High Spatial Resolution Satellite Imagery and Machine Learning |
| title_short | Detecting the Distribution of Callery Pear (<i>Pyrus calleryana</i>) in an Urban U.S. Landscape Using High Spatial Resolution Satellite Imagery and Machine Learning |
| title_sort | detecting the distribution of callery pear i pyrus calleryana i in an urban u s landscape using high spatial resolution satellite imagery and machine learning |
| topic | <i>Pyrus calleryana</i> Decne digital image processing spatial clustering species inventory Planetscope |
| url | https://www.mdpi.com/2072-4292/17/8/1453 |
| work_keys_str_mv | AT justinkrohn detectingthedistributionofcallerypearipyruscalleryanaiinanurbanuslandscapeusinghighspatialresolutionsatelliteimageryandmachinelearning AT honghe detectingthedistributionofcallerypearipyruscalleryanaiinanurbanuslandscapeusinghighspatialresolutionsatelliteimageryandmachinelearning AT timothycmatisziw detectingthedistributionofcallerypearipyruscalleryanaiinanurbanuslandscapeusinghighspatialresolutionsatelliteimageryandmachinelearning AT laurenspileknapp detectingthedistributionofcallerypearipyruscalleryanaiinanurbanuslandscapeusinghighspatialresolutionsatelliteimageryandmachinelearning AT jacobsfraser detectingthedistributionofcallerypearipyruscalleryanaiinanurbanuslandscapeusinghighspatialresolutionsatelliteimageryandmachinelearning AT michaelsunde detectingthedistributionofcallerypearipyruscalleryanaiinanurbanuslandscapeusinghighspatialresolutionsatelliteimageryandmachinelearning |