Fine-scale forest classification with multi-temporal sentinel-1/2 imagery using a temporal convolutional neural network
Monitoring and mapping forest vegetation are crucial for conserving biodiversity and estimating biomass and carbon. However, spectral similarity between different vegetation types and the issue of mixed pixels in medium-resolution satellite imagery remain significant challenges for fine-scale forest...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-12-01
|
| Series: | International Journal of Digital Earth |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/17538947.2025.2457953 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583839452495872 |
|---|---|
| author | Rongfei Duan Chunlin Huang Peng Dou Jinliang Hou Ying Zhang Juan Gu |
| author_facet | Rongfei Duan Chunlin Huang Peng Dou Jinliang Hou Ying Zhang Juan Gu |
| author_sort | Rongfei Duan |
| collection | DOAJ |
| description | Monitoring and mapping forest vegetation are crucial for conserving biodiversity and estimating biomass and carbon. However, spectral similarity between different vegetation types and the issue of mixed pixels in medium-resolution satellite imagery remain significant challenges for fine-scale forest classification. This study focused on the Tao River National Nature Reserve in southern Gansu Province, China, where over 6,000 vegetation samples were collected. A Temporal Convolutional Neural Network (TempCNN), which excels in handling temporal data and adapting to complex patterns, was constructed using TensorFlow with 133.8k parameters. The model was compared with CNN, random forest, XGBoost, and long short-term memory to validate its advantages. The SHAP (SHapley Additive exPlanations) interpreter was employed for feature importance analysis. Spectral, SAR, temporal, and geographic features were extracted from Sentinel-1/2 images to capture spectral differences and phenological characteristics of vegetation. Results show that TempCNN achieves the best performance (overall accuracy = 91.67%, Kappa = 0.895) and is particularly effective at handling complex data and mixed forests. Spring imagery and the short-wave infrared band play key roles in accurate vegetation classification. This study provides a new framework for fine-scale forest classification by combining multisource and multi-temporal data, highlighting the practical value of large-scale forest mapping. |
| format | Article |
| id | doaj-art-38fd2c330021489c8000b9b9a8e21463 |
| institution | Kabale University |
| issn | 1753-8947 1753-8955 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | International Journal of Digital Earth |
| spelling | doaj-art-38fd2c330021489c8000b9b9a8e214632025-01-28T05:09:26ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552025-12-0118110.1080/17538947.2025.2457953Fine-scale forest classification with multi-temporal sentinel-1/2 imagery using a temporal convolutional neural networkRongfei Duan0Chunlin Huang1Peng Dou2Jinliang Hou3Ying Zhang4Juan Gu5Faculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, People’s Republic of ChinaKey Laboratory of Remote Sensing of Gansu Province, Heihe Remote Sensing Experimental Research Station, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou, People’s Republic of ChinaKey Laboratory of Remote Sensing of Gansu Province, Heihe Remote Sensing Experimental Research Station, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou, People’s Republic of ChinaKey Laboratory of Remote Sensing of Gansu Province, Heihe Remote Sensing Experimental Research Station, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou, People’s Republic of ChinaKey Laboratory of Remote Sensing of Gansu Province, Heihe Remote Sensing Experimental Research Station, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou, People’s Republic of ChinaCollege of Earth and Environmental Sciences, Lanzhou University, Lanzhou, People’s Republic of ChinaMonitoring and mapping forest vegetation are crucial for conserving biodiversity and estimating biomass and carbon. However, spectral similarity between different vegetation types and the issue of mixed pixels in medium-resolution satellite imagery remain significant challenges for fine-scale forest classification. This study focused on the Tao River National Nature Reserve in southern Gansu Province, China, where over 6,000 vegetation samples were collected. A Temporal Convolutional Neural Network (TempCNN), which excels in handling temporal data and adapting to complex patterns, was constructed using TensorFlow with 133.8k parameters. The model was compared with CNN, random forest, XGBoost, and long short-term memory to validate its advantages. The SHAP (SHapley Additive exPlanations) interpreter was employed for feature importance analysis. Spectral, SAR, temporal, and geographic features were extracted from Sentinel-1/2 images to capture spectral differences and phenological characteristics of vegetation. Results show that TempCNN achieves the best performance (overall accuracy = 91.67%, Kappa = 0.895) and is particularly effective at handling complex data and mixed forests. Spring imagery and the short-wave infrared band play key roles in accurate vegetation classification. This study provides a new framework for fine-scale forest classification by combining multisource and multi-temporal data, highlighting the practical value of large-scale forest mapping.https://www.tandfonline.com/doi/10.1080/17538947.2025.2457953Deep learningclassificationtemporal informationmultisource data fusionremote sensing |
| spellingShingle | Rongfei Duan Chunlin Huang Peng Dou Jinliang Hou Ying Zhang Juan Gu Fine-scale forest classification with multi-temporal sentinel-1/2 imagery using a temporal convolutional neural network International Journal of Digital Earth Deep learning classification temporal information multisource data fusion remote sensing |
| title | Fine-scale forest classification with multi-temporal sentinel-1/2 imagery using a temporal convolutional neural network |
| title_full | Fine-scale forest classification with multi-temporal sentinel-1/2 imagery using a temporal convolutional neural network |
| title_fullStr | Fine-scale forest classification with multi-temporal sentinel-1/2 imagery using a temporal convolutional neural network |
| title_full_unstemmed | Fine-scale forest classification with multi-temporal sentinel-1/2 imagery using a temporal convolutional neural network |
| title_short | Fine-scale forest classification with multi-temporal sentinel-1/2 imagery using a temporal convolutional neural network |
| title_sort | fine scale forest classification with multi temporal sentinel 1 2 imagery using a temporal convolutional neural network |
| topic | Deep learning classification temporal information multisource data fusion remote sensing |
| url | https://www.tandfonline.com/doi/10.1080/17538947.2025.2457953 |
| work_keys_str_mv | AT rongfeiduan finescaleforestclassificationwithmultitemporalsentinel12imageryusingatemporalconvolutionalneuralnetwork AT chunlinhuang finescaleforestclassificationwithmultitemporalsentinel12imageryusingatemporalconvolutionalneuralnetwork AT pengdou finescaleforestclassificationwithmultitemporalsentinel12imageryusingatemporalconvolutionalneuralnetwork AT jinlianghou finescaleforestclassificationwithmultitemporalsentinel12imageryusingatemporalconvolutionalneuralnetwork AT yingzhang finescaleforestclassificationwithmultitemporalsentinel12imageryusingatemporalconvolutionalneuralnetwork AT juangu finescaleforestclassificationwithmultitemporalsentinel12imageryusingatemporalconvolutionalneuralnetwork |