Assessing CNN and Semantic Segmentation Models for Coarse Resolution Satellite Image Classification in Subcontinental Scale Land Cover Mapping
Based on studies using high-medium resolution images, convolutional neural networks (CNNs) and semantic segmentation have shown superiority over classical machine learning (ML), particularly in small-scale mapping. However, few/no studies have assessed the techniques on coarse resolution...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10696947/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841557086268293120 |
|---|---|
| author | Tesfaye Adugna Wenbo Xu Jinlong Fan Haitao Jia Xin Luo |
| author_facet | Tesfaye Adugna Wenbo Xu Jinlong Fan Haitao Jia Xin Luo |
| author_sort | Tesfaye Adugna |
| collection | DOAJ |
| description | Based on studies using high-medium resolution images, convolutional neural networks (CNNs) and semantic segmentation have shown superiority over classical machine learning (ML), particularly in small-scale mapping. However, few/no studies have assessed the techniques on coarse resolution image classification for extensive area land cover mapping. In this study, we evaluated the performance and feasibility of three CNN models (1-D CNN, 2-D CNN, and 3-D CNN), and U-net for coarse-resolution satellite image classification and compared them to a random forest (RF) classifier. We utilized time-series, coarse resolution (1 km) composite imageries acquired by FengYun-3C visible and infrared radiometer. Labeled datasets were collected as shapefiles and split into three independent datasets: training, validation, and test datasets, and preprocessed to meet each model's input format requirements. We conducted several experiments to optimize models and select the best models. Then, the best models were evaluated on an unseen dataset. Among the DL models, one-dimensional (1-D) CNN achieved the highest overall accuracy (OA) 0. 87 and kappa (<italic>k</italic>) 0.84, 2% higher than the best results attained by 2-D CNN, 3-D CNN, and U-net models. However, 1-D CNN is outperformed by RF which achieved 0.89 (OA) and 0.87 (k). Achieving the best and the second-best results using RF and 1-D CNN models, respectively, indicates the superiority of the pixel-based method and the insignificance of spatial information in coarse-resolution image classification. Furthermore, although the DL models can yield high accuracy, especially 1-D CNN, they are less feasible than RF classifiers for coarse-resolution satellite image classification in extensive area land cover mapping. |
| format | Article |
| id | doaj-art-697aa0bacc9b48f9a074895f76a81f28 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-697aa0bacc9b48f9a074895f76a81f282025-01-07T00:00:31ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01182777279810.1109/JSTARS.2024.346972810696947Assessing CNN and Semantic Segmentation Models for Coarse Resolution Satellite Image Classification in Subcontinental Scale Land Cover MappingTesfaye Adugna0https://orcid.org/0000-0003-3235-587XWenbo Xu1https://orcid.org/0000-0001-8704-1937Jinlong Fan2https://orcid.org/0000-0001-8227-6630Haitao Jia3Xin Luo4https://orcid.org/0000-0002-9534-592XYangtze Delta Region Institute (Huzhou), University of Electronic Science and Technology of China, Huzhou, ChinaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, ChinaGeographical Sciences, Beijing Normal University, Beijing, ChinaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, ChinaBased on studies using high-medium resolution images, convolutional neural networks (CNNs) and semantic segmentation have shown superiority over classical machine learning (ML), particularly in small-scale mapping. However, few/no studies have assessed the techniques on coarse resolution image classification for extensive area land cover mapping. In this study, we evaluated the performance and feasibility of three CNN models (1-D CNN, 2-D CNN, and 3-D CNN), and U-net for coarse-resolution satellite image classification and compared them to a random forest (RF) classifier. We utilized time-series, coarse resolution (1 km) composite imageries acquired by FengYun-3C visible and infrared radiometer. Labeled datasets were collected as shapefiles and split into three independent datasets: training, validation, and test datasets, and preprocessed to meet each model's input format requirements. We conducted several experiments to optimize models and select the best models. Then, the best models were evaluated on an unseen dataset. Among the DL models, one-dimensional (1-D) CNN achieved the highest overall accuracy (OA) 0. 87 and kappa (<italic>k</italic>) 0.84, 2% higher than the best results attained by 2-D CNN, 3-D CNN, and U-net models. However, 1-D CNN is outperformed by RF which achieved 0.89 (OA) and 0.87 (k). Achieving the best and the second-best results using RF and 1-D CNN models, respectively, indicates the superiority of the pixel-based method and the insignificance of spatial information in coarse-resolution image classification. Furthermore, although the DL models can yield high accuracy, especially 1-D CNN, they are less feasible than RF classifiers for coarse-resolution satellite image classification in extensive area land cover mapping.https://ieeexplore.ieee.org/document/10696947/Convolutional neural networks (CNNs)coarse resolutiondeep learningland coversematic segmentationU-net |
| spellingShingle | Tesfaye Adugna Wenbo Xu Jinlong Fan Haitao Jia Xin Luo Assessing CNN and Semantic Segmentation Models for Coarse Resolution Satellite Image Classification in Subcontinental Scale Land Cover Mapping IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Convolutional neural networks (CNNs) coarse resolution deep learning land cover sematic segmentation U-net |
| title | Assessing CNN and Semantic Segmentation Models for Coarse Resolution Satellite Image Classification in Subcontinental Scale Land Cover Mapping |
| title_full | Assessing CNN and Semantic Segmentation Models for Coarse Resolution Satellite Image Classification in Subcontinental Scale Land Cover Mapping |
| title_fullStr | Assessing CNN and Semantic Segmentation Models for Coarse Resolution Satellite Image Classification in Subcontinental Scale Land Cover Mapping |
| title_full_unstemmed | Assessing CNN and Semantic Segmentation Models for Coarse Resolution Satellite Image Classification in Subcontinental Scale Land Cover Mapping |
| title_short | Assessing CNN and Semantic Segmentation Models for Coarse Resolution Satellite Image Classification in Subcontinental Scale Land Cover Mapping |
| title_sort | assessing cnn and semantic segmentation models for coarse resolution satellite image classification in subcontinental scale land cover mapping |
| topic | Convolutional neural networks (CNNs) coarse resolution deep learning land cover sematic segmentation U-net |
| url | https://ieeexplore.ieee.org/document/10696947/ |
| work_keys_str_mv | AT tesfayeadugna assessingcnnandsemanticsegmentationmodelsforcoarseresolutionsatelliteimageclassificationinsubcontinentalscalelandcovermapping AT wenboxu assessingcnnandsemanticsegmentationmodelsforcoarseresolutionsatelliteimageclassificationinsubcontinentalscalelandcovermapping AT jinlongfan assessingcnnandsemanticsegmentationmodelsforcoarseresolutionsatelliteimageclassificationinsubcontinentalscalelandcovermapping AT haitaojia assessingcnnandsemanticsegmentationmodelsforcoarseresolutionsatelliteimageclassificationinsubcontinentalscalelandcovermapping AT xinluo assessingcnnandsemanticsegmentationmodelsforcoarseresolutionsatelliteimageclassificationinsubcontinentalscalelandcovermapping |