Improving Dryland Urban Land Cover Classification Accuracy Using a Classical Convolution Neural Network
Reliable information of land cover dynamics in dryland cities is crucial for understanding the anthropogenic impacts on fragile environments. However, reduced classification accuracy of dryland cities often occurs in global land cover data. Although many advanced classification techniques (i.e., con...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Land |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-445X/12/8/1616 |
| _version_ | 1797584135835877376 |
|---|---|
| author | Wenfei Luan Ge Li Bo Zhong Jianwei Geng Xin Li Hui Li Shi He |
| author_facet | Wenfei Luan Ge Li Bo Zhong Jianwei Geng Xin Li Hui Li Shi He |
| author_sort | Wenfei Luan |
| collection | DOAJ |
| description | Reliable information of land cover dynamics in dryland cities is crucial for understanding the anthropogenic impacts on fragile environments. However, reduced classification accuracy of dryland cities often occurs in global land cover data. Although many advanced classification techniques (i.e., convolutional neural networks (CNN)) have been intensively applied to classify urban land cover because of their excellent performance, specific classification models focusing on typical dryland cities are still scarce. This is mainly attributed to the similar features between urban and non-urban areas, as well as the insufficient training samples in this specific region. To fill this gap, this study trained a CNN model to improve the urban land classification accuracy for seven dryland cities based on rigorous training sample selection. The assessment showed that our proposed model performed with higher overall accuracy (92.63%) than several emerging land cover products, including Esri 2020 Land Cover (75.55%), GlobeLand30 (73.24%), GLC_FCS30-2020 (69.68%), ESA WorldCover2020 (64.38%), and FROM-GLC 2017v1 (61.13%). In addition, the classification accuracy of the dominant land types in the CNN-classified data exceeded the selected products. This encouraging finding demonstrates that our proposed architecture is a promising solution for improving dryland urban land classification accuracy and compensating the deficiency of large-scale land cover mapping. |
| first_indexed | 2024-03-10T23:49:03Z |
| format | Article |
| id | doaj.art-ed547e71323a4e87b3369a6c612f6477 |
| institution | Directory Open Access Journal |
| issn | 2073-445X |
| language | English |
| last_indexed | 2024-03-10T23:49:03Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Land |
| spelling | doaj.art-ed547e71323a4e87b3369a6c612f64772023-11-19T01:52:25ZengMDPI AGLand2073-445X2023-08-01128161610.3390/land12081616Improving Dryland Urban Land Cover Classification Accuracy Using a Classical Convolution Neural NetworkWenfei Luan0Ge Li1Bo Zhong2Jianwei Geng3Xin Li4Hui Li5Shi He6School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, ChinaKey Laboratory of Watershed Geographic Sciences, Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences, Nanjing 210008, ChinaNational Tibetan Plateau Data Center, State Key Laboratory of Tibetan Plateau Earth System, Environment and Resources, Institute of Tibetan Plateau Research, Chinese Academy of Sciences, Beijing 100101, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaReliable information of land cover dynamics in dryland cities is crucial for understanding the anthropogenic impacts on fragile environments. However, reduced classification accuracy of dryland cities often occurs in global land cover data. Although many advanced classification techniques (i.e., convolutional neural networks (CNN)) have been intensively applied to classify urban land cover because of their excellent performance, specific classification models focusing on typical dryland cities are still scarce. This is mainly attributed to the similar features between urban and non-urban areas, as well as the insufficient training samples in this specific region. To fill this gap, this study trained a CNN model to improve the urban land classification accuracy for seven dryland cities based on rigorous training sample selection. The assessment showed that our proposed model performed with higher overall accuracy (92.63%) than several emerging land cover products, including Esri 2020 Land Cover (75.55%), GlobeLand30 (73.24%), GLC_FCS30-2020 (69.68%), ESA WorldCover2020 (64.38%), and FROM-GLC 2017v1 (61.13%). In addition, the classification accuracy of the dominant land types in the CNN-classified data exceeded the selected products. This encouraging finding demonstrates that our proposed architecture is a promising solution for improving dryland urban land classification accuracy and compensating the deficiency of large-scale land cover mapping.https://www.mdpi.com/2073-445X/12/8/1616dryland regionurban land classificationconvolution neural networktraining sample |
| spellingShingle | Wenfei Luan Ge Li Bo Zhong Jianwei Geng Xin Li Hui Li Shi He Improving Dryland Urban Land Cover Classification Accuracy Using a Classical Convolution Neural Network Land dryland region urban land classification convolution neural network training sample |
| title | Improving Dryland Urban Land Cover Classification Accuracy Using a Classical Convolution Neural Network |
| title_full | Improving Dryland Urban Land Cover Classification Accuracy Using a Classical Convolution Neural Network |
| title_fullStr | Improving Dryland Urban Land Cover Classification Accuracy Using a Classical Convolution Neural Network |
| title_full_unstemmed | Improving Dryland Urban Land Cover Classification Accuracy Using a Classical Convolution Neural Network |
| title_short | Improving Dryland Urban Land Cover Classification Accuracy Using a Classical Convolution Neural Network |
| title_sort | improving dryland urban land cover classification accuracy using a classical convolution neural network |
| topic | dryland region urban land classification convolution neural network training sample |
| url | https://www.mdpi.com/2073-445X/12/8/1616 |
| work_keys_str_mv | AT wenfeiluan improvingdrylandurbanlandcoverclassificationaccuracyusingaclassicalconvolutionneuralnetwork AT geli improvingdrylandurbanlandcoverclassificationaccuracyusingaclassicalconvolutionneuralnetwork AT bozhong improvingdrylandurbanlandcoverclassificationaccuracyusingaclassicalconvolutionneuralnetwork AT jianweigeng improvingdrylandurbanlandcoverclassificationaccuracyusingaclassicalconvolutionneuralnetwork AT xinli improvingdrylandurbanlandcoverclassificationaccuracyusingaclassicalconvolutionneuralnetwork AT huili improvingdrylandurbanlandcoverclassificationaccuracyusingaclassicalconvolutionneuralnetwork AT shihe improvingdrylandurbanlandcoverclassificationaccuracyusingaclassicalconvolutionneuralnetwork |