An Effective Deep Learning Model for Monitoring Mangroves: A Case Study of the Indus Delta
Rapid and accurate identification of mangroves using remote sensing images is of great significance for assisting ecological conservation efforts in coastal zones. With the rapid development of artificial intelligence, deep learning methods have been successfully applied to a variety of fields. Howe...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/9/2220 |
| _version_ | 1797601790351376384 |
|---|---|
| author | Chen Xu Juanle Wang Yu Sang Kai Li Jingxuan Liu Gang Yang |
| author_facet | Chen Xu Juanle Wang Yu Sang Kai Li Jingxuan Liu Gang Yang |
| author_sort | Chen Xu |
| collection | DOAJ |
| description | Rapid and accurate identification of mangroves using remote sensing images is of great significance for assisting ecological conservation efforts in coastal zones. With the rapid development of artificial intelligence, deep learning methods have been successfully applied to a variety of fields. However, few studies have applied deep learning methods to the automatic detection of mangroves and few scholars have used medium-resolution Landsat images for large-scale mangrove identification. In this study, cloud-free Landsat 8 OLI imagery of the Indus Delta was acquired using the GEE platform, and NDVI and land use data were used to produce integrated labels to reduce the complexity and subjectivity of manually labeled samples. We proposed the use of MSNet, a semantic segmentation model fusing multiple-scale features, for mangrove extraction in the Indus Delta, and compared the performance of the MSNet model with three other semantic segmentation models, FCN-8s, SegNet, and U-Net. The overall performance ranking of the deep learning methods was MSNet > U-Net > SegNet > FCN-8s. The parallel-structured MSNet model was easy to train, had the fewest parameters and the highest validation accuracy, and provided the best results for the extraction of mangrove pixels with weak features. The MSNet model not only maintains the high-resolution features of the image and fully learns the pixels with weak features during the training process but also fuses the multiple-scale underlying features at different scales to enhance the semantic information and improve the accuracy of feature recognition and segmentation localization. Finally, the areas covered by mangroves in the Indus Delta in 2014 and 2022 were extracted using the best-performing MSNet. The statistics show an increase in mangrove-covered areas in the Indus Delta between 2014 and 2022, with a reduction of 44.37 km<sup>2</sup>, an increase of 170.48 km<sup>2</sup>, and a net increase of 126.11 km<sup>2</sup>. |
| first_indexed | 2024-03-11T04:08:51Z |
| format | Article |
| id | doaj.art-1ed129aa701f4b738f62ae0094d38cf1 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T04:08:51Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-1ed129aa701f4b738f62ae0094d38cf12023-11-17T23:37:08ZengMDPI AGRemote Sensing2072-42922023-04-01159222010.3390/rs15092220An Effective Deep Learning Model for Monitoring Mangroves: A Case Study of the Indus DeltaChen Xu0Juanle Wang1Yu Sang2Kai Li3Jingxuan Liu4Gang Yang5School of Marine Technology and Geomatics, Jiangsu Ocean University, Lianyungang 222005, ChinaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaSchool of Marine Technology and Geomatics, Jiangsu Ocean University, Lianyungang 222005, ChinaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaSchool of Marine Technology and Geomatics, Jiangsu Ocean University, Lianyungang 222005, ChinaSchool of Marine Technology and Geomatics, Jiangsu Ocean University, Lianyungang 222005, ChinaRapid and accurate identification of mangroves using remote sensing images is of great significance for assisting ecological conservation efforts in coastal zones. With the rapid development of artificial intelligence, deep learning methods have been successfully applied to a variety of fields. However, few studies have applied deep learning methods to the automatic detection of mangroves and few scholars have used medium-resolution Landsat images for large-scale mangrove identification. In this study, cloud-free Landsat 8 OLI imagery of the Indus Delta was acquired using the GEE platform, and NDVI and land use data were used to produce integrated labels to reduce the complexity and subjectivity of manually labeled samples. We proposed the use of MSNet, a semantic segmentation model fusing multiple-scale features, for mangrove extraction in the Indus Delta, and compared the performance of the MSNet model with three other semantic segmentation models, FCN-8s, SegNet, and U-Net. The overall performance ranking of the deep learning methods was MSNet > U-Net > SegNet > FCN-8s. The parallel-structured MSNet model was easy to train, had the fewest parameters and the highest validation accuracy, and provided the best results for the extraction of mangrove pixels with weak features. The MSNet model not only maintains the high-resolution features of the image and fully learns the pixels with weak features during the training process but also fuses the multiple-scale underlying features at different scales to enhance the semantic information and improve the accuracy of feature recognition and segmentation localization. Finally, the areas covered by mangroves in the Indus Delta in 2014 and 2022 were extracted using the best-performing MSNet. The statistics show an increase in mangrove-covered areas in the Indus Delta between 2014 and 2022, with a reduction of 44.37 km<sup>2</sup>, an increase of 170.48 km<sup>2</sup>, and a net increase of 126.11 km<sup>2</sup>.https://www.mdpi.com/2072-4292/15/9/2220Landsat 8semantic segmentationdeep learningmangrove identificationIndus Delta |
| spellingShingle | Chen Xu Juanle Wang Yu Sang Kai Li Jingxuan Liu Gang Yang An Effective Deep Learning Model for Monitoring Mangroves: A Case Study of the Indus Delta Remote Sensing Landsat 8 semantic segmentation deep learning mangrove identification Indus Delta |
| title | An Effective Deep Learning Model for Monitoring Mangroves: A Case Study of the Indus Delta |
| title_full | An Effective Deep Learning Model for Monitoring Mangroves: A Case Study of the Indus Delta |
| title_fullStr | An Effective Deep Learning Model for Monitoring Mangroves: A Case Study of the Indus Delta |
| title_full_unstemmed | An Effective Deep Learning Model for Monitoring Mangroves: A Case Study of the Indus Delta |
| title_short | An Effective Deep Learning Model for Monitoring Mangroves: A Case Study of the Indus Delta |
| title_sort | effective deep learning model for monitoring mangroves a case study of the indus delta |
| topic | Landsat 8 semantic segmentation deep learning mangrove identification Indus Delta |
| url | https://www.mdpi.com/2072-4292/15/9/2220 |
| work_keys_str_mv | AT chenxu aneffectivedeeplearningmodelformonitoringmangrovesacasestudyoftheindusdelta AT juanlewang aneffectivedeeplearningmodelformonitoringmangrovesacasestudyoftheindusdelta AT yusang aneffectivedeeplearningmodelformonitoringmangrovesacasestudyoftheindusdelta AT kaili aneffectivedeeplearningmodelformonitoringmangrovesacasestudyoftheindusdelta AT jingxuanliu aneffectivedeeplearningmodelformonitoringmangrovesacasestudyoftheindusdelta AT gangyang aneffectivedeeplearningmodelformonitoringmangrovesacasestudyoftheindusdelta AT chenxu effectivedeeplearningmodelformonitoringmangrovesacasestudyoftheindusdelta AT juanlewang effectivedeeplearningmodelformonitoringmangrovesacasestudyoftheindusdelta AT yusang effectivedeeplearningmodelformonitoringmangrovesacasestudyoftheindusdelta AT kaili effectivedeeplearningmodelformonitoringmangrovesacasestudyoftheindusdelta AT jingxuanliu effectivedeeplearningmodelformonitoringmangrovesacasestudyoftheindusdelta AT gangyang effectivedeeplearningmodelformonitoringmangrovesacasestudyoftheindusdelta |