River Channel Microgeomorphic Feature Extraction and Potential Sandstorm Source Identification Method Based on a Convolutional Autoencoder Model
River channel's microgeomorphic features are crucial for identifying potential sandstorm sources and studying sediment source-sink processes. Current deep learning methods are predominantly applied to visible objects, rendering them unsuitable for latent objects with unstable spatiotempor...
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/10812012/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533425313382400 |
|---|---|
| author | Kecong Wu Lirong Chen Yalige Bai Xinhang Wang Danzeng Pingcuo Zhongpeng Han Chengshan Wang |
| author_facet | Kecong Wu Lirong Chen Yalige Bai Xinhang Wang Danzeng Pingcuo Zhongpeng Han Chengshan Wang |
| author_sort | Kecong Wu |
| collection | DOAJ |
| description | River channel's microgeomorphic features are crucial for identifying potential sandstorm sources and studying sediment source-sink processes. Current deep learning methods are predominantly applied to visible objects, rendering them unsuitable for latent objects with unstable spatiotemporal distributions, such as potential sandstorm sources. These latent objects require the analysis of their internal structures using unsupervised methods. Convolutional kernels in convolutional neural networks capture local spatial structures, and their size is essential for accurately analyzing internal structures. A key challenge is determining the appropriate scale for identifying the latent objects. This model uses high-resolution remote sensing imagery and employs a convolutional autoencoder to extract common features from river channels. Determining the optimal convolution kernel size enables the automatic and efficient identification of the morphological boundaries of latent objects, extracts the spatiotemporal common features of river microtopography, and reconstructs the microtopography background. Anomaly detection methods are employed to identify regions with spatial structural anomalies, recognizing areas that are potential and dynamic sandstorm sources. It addresses the challenges of spatiotemporal feature extraction in complex geographical environments, and the identification of potential wind-blown sand sources in river channels. The approach was applied to the Yarlung Zangbo River from Qushui to Zedang using 2013–2018 Landsat 8 remote sensing images. The results show that this method can effectively identify river microtopographic features and potential sandstorm sources. |
| format | Article |
| id | doaj-art-94424c5cfbc34885963f0ffe4a93a78c |
| 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-94424c5cfbc34885963f0ffe4a93a78c2025-01-16T00:00:45ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01182602261710.1109/JSTARS.2024.352103610812012River Channel Microgeomorphic Feature Extraction and Potential Sandstorm Source Identification Method Based on a Convolutional Autoencoder ModelKecong Wu0Lirong Chen1https://orcid.org/0000-0002-7302-5458Yalige Bai2https://orcid.org/0009-0003-3413-6184Xinhang Wang3Danzeng Pingcuo4Zhongpeng Han5https://orcid.org/0000-0003-1121-6483Chengshan Wang6School of Earth Sciences and Resources, China University of Geosciences, Beijing, ChinaInstitute of Marine Big Data and Knowledge Service, China Ocean Press, Beijing, ChinaSchool of Earth Sciences and Resources, China University of Geosciences, Beijing, ChinaSchool of Earth Sciences and Resources, China University of Geosciences, Beijing, ChinaYangcun Hydrometric Station, Hydrology and Water Resources Survey Bureau of Tibet Autonomous Region, Lhasa, ChinaFrontiers Science Center for Deep-time Digital Earth, China University of Geosciences, Beijing, ChinaSchool of Earth Sciences and Resources, China University of Geosciences, Beijing, ChinaRiver channel's microgeomorphic features are crucial for identifying potential sandstorm sources and studying sediment source-sink processes. Current deep learning methods are predominantly applied to visible objects, rendering them unsuitable for latent objects with unstable spatiotemporal distributions, such as potential sandstorm sources. These latent objects require the analysis of their internal structures using unsupervised methods. Convolutional kernels in convolutional neural networks capture local spatial structures, and their size is essential for accurately analyzing internal structures. A key challenge is determining the appropriate scale for identifying the latent objects. This model uses high-resolution remote sensing imagery and employs a convolutional autoencoder to extract common features from river channels. Determining the optimal convolution kernel size enables the automatic and efficient identification of the morphological boundaries of latent objects, extracts the spatiotemporal common features of river microtopography, and reconstructs the microtopography background. Anomaly detection methods are employed to identify regions with spatial structural anomalies, recognizing areas that are potential and dynamic sandstorm sources. It addresses the challenges of spatiotemporal feature extraction in complex geographical environments, and the identification of potential wind-blown sand sources in river channels. The approach was applied to the Yarlung Zangbo River from Qushui to Zedang using 2013–2018 Landsat 8 remote sensing images. The results show that this method can effectively identify river microtopographic features and potential sandstorm sources.https://ieeexplore.ieee.org/document/10812012/Anomaly valuesconvolutional autoencoder (CAE)microgeomorphic featuresandstorm sourcesYarlung Zangbo River |
| spellingShingle | Kecong Wu Lirong Chen Yalige Bai Xinhang Wang Danzeng Pingcuo Zhongpeng Han Chengshan Wang River Channel Microgeomorphic Feature Extraction and Potential Sandstorm Source Identification Method Based on a Convolutional Autoencoder Model IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Anomaly values convolutional autoencoder (CAE) microgeomorphic feature sandstorm sources Yarlung Zangbo River |
| title | River Channel Microgeomorphic Feature Extraction and Potential Sandstorm Source Identification Method Based on a Convolutional Autoencoder Model |
| title_full | River Channel Microgeomorphic Feature Extraction and Potential Sandstorm Source Identification Method Based on a Convolutional Autoencoder Model |
| title_fullStr | River Channel Microgeomorphic Feature Extraction and Potential Sandstorm Source Identification Method Based on a Convolutional Autoencoder Model |
| title_full_unstemmed | River Channel Microgeomorphic Feature Extraction and Potential Sandstorm Source Identification Method Based on a Convolutional Autoencoder Model |
| title_short | River Channel Microgeomorphic Feature Extraction and Potential Sandstorm Source Identification Method Based on a Convolutional Autoencoder Model |
| title_sort | river channel microgeomorphic feature extraction and potential sandstorm source identification method based on a convolutional autoencoder model |
| topic | Anomaly values convolutional autoencoder (CAE) microgeomorphic feature sandstorm sources Yarlung Zangbo River |
| url | https://ieeexplore.ieee.org/document/10812012/ |
| work_keys_str_mv | AT kecongwu riverchannelmicrogeomorphicfeatureextractionandpotentialsandstormsourceidentificationmethodbasedonaconvolutionalautoencodermodel AT lirongchen riverchannelmicrogeomorphicfeatureextractionandpotentialsandstormsourceidentificationmethodbasedonaconvolutionalautoencodermodel AT yaligebai riverchannelmicrogeomorphicfeatureextractionandpotentialsandstormsourceidentificationmethodbasedonaconvolutionalautoencodermodel AT xinhangwang riverchannelmicrogeomorphicfeatureextractionandpotentialsandstormsourceidentificationmethodbasedonaconvolutionalautoencodermodel AT danzengpingcuo riverchannelmicrogeomorphicfeatureextractionandpotentialsandstormsourceidentificationmethodbasedonaconvolutionalautoencodermodel AT zhongpenghan riverchannelmicrogeomorphicfeatureextractionandpotentialsandstormsourceidentificationmethodbasedonaconvolutionalautoencodermodel AT chengshanwang riverchannelmicrogeomorphicfeatureextractionandpotentialsandstormsourceidentificationmethodbasedonaconvolutionalautoencodermodel |