Examining Deep Learning Pixel-Based Classification Algorithms for Mapping Weed Canopy Cover in Wheat Production Using Drone Data
Deep learning models offer valuable insights by leveraging large datasets, enabling precise and strategic decision-making essential for modern agriculture. Despite their potential, limited research has focused on the performance of pixel-based deep learning algorithms for detecting and mapping weed...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Geomatics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-7418/5/1/4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850203927941742592 |
|---|---|
| author | Judith N. Oppong Clement E. Akumu Samuel Dennis Stephanie Anyanwu |
| author_facet | Judith N. Oppong Clement E. Akumu Samuel Dennis Stephanie Anyanwu |
| author_sort | Judith N. Oppong |
| collection | DOAJ |
| description | Deep learning models offer valuable insights by leveraging large datasets, enabling precise and strategic decision-making essential for modern agriculture. Despite their potential, limited research has focused on the performance of pixel-based deep learning algorithms for detecting and mapping weed canopy cover. This study aims to evaluate the effectiveness of three neural network architectures—U-Net, DeepLabV3 (DLV3), and pyramid scene parsing network (PSPNet)—in mapping weed canopy cover in winter wheat. Drone data collected at the jointing and booting growth stages of winter wheat were used for the analysis. A supervised deep learning pixel classification methodology was adopted, and the models were tested on broadleaved weed species, winter wheat, and other weed species. The results show that PSPNet outperformed both U-Net and DLV3 in classification performance, with PSPNet achieving the highest overall mapping accuracy of 80%, followed by U-Net at 75% and DLV3 at 56.5%. These findings highlight the potential of pixel-based deep learning algorithms to enhance weed canopy mapping, enabling farmers to make more informed, site-specific weed management decisions, ultimately improving production and promoting sustainable agricultural practices. |
| format | Article |
| id | doaj-art-b8bae3bd7ce54a0aa79b2eae0b558dde |
| institution | OA Journals |
| issn | 2673-7418 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Geomatics |
| spelling | doaj-art-b8bae3bd7ce54a0aa79b2eae0b558dde2025-08-20T02:11:23ZengMDPI AGGeomatics2673-74182025-01-0151410.3390/geomatics5010004Examining Deep Learning Pixel-Based Classification Algorithms for Mapping Weed Canopy Cover in Wheat Production Using Drone DataJudith N. Oppong0Clement E. Akumu1Samuel Dennis2Stephanie Anyanwu3Department of Agricultural Science and Engineering, College of Agriculture, Tennessee State University, Nashville, TN 37209, USADepartment of Agricultural Science and Engineering, College of Agriculture, Tennessee State University, Nashville, TN 37209, USADepartment of Agricultural Science and Engineering, College of Agriculture, Tennessee State University, Nashville, TN 37209, USADepartment of Agricultural Science and Engineering, College of Agriculture, Tennessee State University, Nashville, TN 37209, USADeep learning models offer valuable insights by leveraging large datasets, enabling precise and strategic decision-making essential for modern agriculture. Despite their potential, limited research has focused on the performance of pixel-based deep learning algorithms for detecting and mapping weed canopy cover. This study aims to evaluate the effectiveness of three neural network architectures—U-Net, DeepLabV3 (DLV3), and pyramid scene parsing network (PSPNet)—in mapping weed canopy cover in winter wheat. Drone data collected at the jointing and booting growth stages of winter wheat were used for the analysis. A supervised deep learning pixel classification methodology was adopted, and the models were tested on broadleaved weed species, winter wheat, and other weed species. The results show that PSPNet outperformed both U-Net and DLV3 in classification performance, with PSPNet achieving the highest overall mapping accuracy of 80%, followed by U-Net at 75% and DLV3 at 56.5%. These findings highlight the potential of pixel-based deep learning algorithms to enhance weed canopy mapping, enabling farmers to make more informed, site-specific weed management decisions, ultimately improving production and promoting sustainable agricultural practices.https://www.mdpi.com/2673-7418/5/1/4high-resolution mappingneural network architecturesprecision agricultureremote sensing imageryvegetation segmentationweed management strategies |
| spellingShingle | Judith N. Oppong Clement E. Akumu Samuel Dennis Stephanie Anyanwu Examining Deep Learning Pixel-Based Classification Algorithms for Mapping Weed Canopy Cover in Wheat Production Using Drone Data Geomatics high-resolution mapping neural network architectures precision agriculture remote sensing imagery vegetation segmentation weed management strategies |
| title | Examining Deep Learning Pixel-Based Classification Algorithms for Mapping Weed Canopy Cover in Wheat Production Using Drone Data |
| title_full | Examining Deep Learning Pixel-Based Classification Algorithms for Mapping Weed Canopy Cover in Wheat Production Using Drone Data |
| title_fullStr | Examining Deep Learning Pixel-Based Classification Algorithms for Mapping Weed Canopy Cover in Wheat Production Using Drone Data |
| title_full_unstemmed | Examining Deep Learning Pixel-Based Classification Algorithms for Mapping Weed Canopy Cover in Wheat Production Using Drone Data |
| title_short | Examining Deep Learning Pixel-Based Classification Algorithms for Mapping Weed Canopy Cover in Wheat Production Using Drone Data |
| title_sort | examining deep learning pixel based classification algorithms for mapping weed canopy cover in wheat production using drone data |
| topic | high-resolution mapping neural network architectures precision agriculture remote sensing imagery vegetation segmentation weed management strategies |
| url | https://www.mdpi.com/2673-7418/5/1/4 |
| work_keys_str_mv | AT judithnoppong examiningdeeplearningpixelbasedclassificationalgorithmsformappingweedcanopycoverinwheatproductionusingdronedata AT clementeakumu examiningdeeplearningpixelbasedclassificationalgorithmsformappingweedcanopycoverinwheatproductionusingdronedata AT samueldennis examiningdeeplearningpixelbasedclassificationalgorithmsformappingweedcanopycoverinwheatproductionusingdronedata AT stephanieanyanwu examiningdeeplearningpixelbasedclassificationalgorithmsformappingweedcanopycoverinwheatproductionusingdronedata |