Deep Learning Application for Crop Classification via Multi-Temporal Remote Sensing Images
The combination of multi-temporal images and deep learning is an efficient way to obtain accurate crop distributions and so has drawn increasing attention. However, few studies have compared deep learning models with different architectures, so it remains unclear how a deep learning model should be...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/13/4/906 |
| _version_ | 1797606758563184640 |
|---|---|
| author | Qianjing Li Jia Tian Qingjiu Tian |
| author_facet | Qianjing Li Jia Tian Qingjiu Tian |
| author_sort | Qianjing Li |
| collection | DOAJ |
| description | The combination of multi-temporal images and deep learning is an efficient way to obtain accurate crop distributions and so has drawn increasing attention. However, few studies have compared deep learning models with different architectures, so it remains unclear how a deep learning model should be selected for multi-temporal crop classification, and the best possible accuracy is. To address this issue, the present work compares and analyzes a crop classification application based on deep learning models and different time-series data to exploit the possibility of improving crop classification accuracy. Using Multi-temporal Sentinel-2 images as source data, time-series classification datasets are constructed based on vegetation indexes (VIs) and spectral stacking, respectively, following which we compare and evaluate the crop classification application based on time-series datasets and five deep learning architectures: (1) one-dimensional convolutional neural networks (1D-CNNs), (2) long short-term memory (LSTM), (3) two-dimensional-CNNs (2D-CNNs), (4) three-dimensional-CNNs (3D-CNNs), and (5) two-dimensional convolutional LSTM (ConvLSTM2D). The results show that the accuracy of both 1D-CNN (92.5%) and LSTM (93.25%) is higher than that of random forest (~ 91%) when using a single temporal feature as input. The 2D-CNN model integrates temporal and spatial information and is slightly more accurate (94.76%), but fails to fully utilize its multi-spectral features. The accuracy of 1D-CNN and LSTM models integrated with temporal and multi-spectral features is 96.94% and 96.84%, respectively. However, neither model can extract spatial information. The accuracy of 3D-CNN and ConvLSTM2D models is 97.43% and 97.25%, respectively. The experimental results show limited accuracy for crop classification based on single temporal features, whereas the combination of temporal features with multi-spectral or spatial information significantly improves classification accuracy. The 3D-CNN and ConvLSTM2D models are thus the best deep learning architectures for multi-temporal crop classification. However, the ConvLSTM architecture combining recurrent neural networks and CNNs should be further developed for multi-temporal image crop classification. |
| first_indexed | 2024-03-11T05:19:36Z |
| format | Article |
| id | doaj.art-1bd732f67a3c4977af94cb8acf715a4c |
| institution | Directory Open Access Journal |
| issn | 2077-0472 |
| language | English |
| last_indexed | 2024-03-11T05:19:36Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj.art-1bd732f67a3c4977af94cb8acf715a4c2023-11-17T17:55:10ZengMDPI AGAgriculture2077-04722023-04-0113490610.3390/agriculture13040906Deep Learning Application for Crop Classification via Multi-Temporal Remote Sensing ImagesQianjing Li0Jia Tian1Qingjiu Tian2International Institute for Earth System Science, Nanjing University, Nanjing 210023, ChinaInternational Institute for Earth System Science, Nanjing University, Nanjing 210023, ChinaInternational Institute for Earth System Science, Nanjing University, Nanjing 210023, ChinaThe combination of multi-temporal images and deep learning is an efficient way to obtain accurate crop distributions and so has drawn increasing attention. However, few studies have compared deep learning models with different architectures, so it remains unclear how a deep learning model should be selected for multi-temporal crop classification, and the best possible accuracy is. To address this issue, the present work compares and analyzes a crop classification application based on deep learning models and different time-series data to exploit the possibility of improving crop classification accuracy. Using Multi-temporal Sentinel-2 images as source data, time-series classification datasets are constructed based on vegetation indexes (VIs) and spectral stacking, respectively, following which we compare and evaluate the crop classification application based on time-series datasets and five deep learning architectures: (1) one-dimensional convolutional neural networks (1D-CNNs), (2) long short-term memory (LSTM), (3) two-dimensional-CNNs (2D-CNNs), (4) three-dimensional-CNNs (3D-CNNs), and (5) two-dimensional convolutional LSTM (ConvLSTM2D). The results show that the accuracy of both 1D-CNN (92.5%) and LSTM (93.25%) is higher than that of random forest (~ 91%) when using a single temporal feature as input. The 2D-CNN model integrates temporal and spatial information and is slightly more accurate (94.76%), but fails to fully utilize its multi-spectral features. The accuracy of 1D-CNN and LSTM models integrated with temporal and multi-spectral features is 96.94% and 96.84%, respectively. However, neither model can extract spatial information. The accuracy of 3D-CNN and ConvLSTM2D models is 97.43% and 97.25%, respectively. The experimental results show limited accuracy for crop classification based on single temporal features, whereas the combination of temporal features with multi-spectral or spatial information significantly improves classification accuracy. The 3D-CNN and ConvLSTM2D models are thus the best deep learning architectures for multi-temporal crop classification. However, the ConvLSTM architecture combining recurrent neural networks and CNNs should be further developed for multi-temporal image crop classification.https://www.mdpi.com/2077-0472/13/4/906crop type classificationdeep learningmulti-temporalremote sensing |
| spellingShingle | Qianjing Li Jia Tian Qingjiu Tian Deep Learning Application for Crop Classification via Multi-Temporal Remote Sensing Images Agriculture crop type classification deep learning multi-temporal remote sensing |
| title | Deep Learning Application for Crop Classification via Multi-Temporal Remote Sensing Images |
| title_full | Deep Learning Application for Crop Classification via Multi-Temporal Remote Sensing Images |
| title_fullStr | Deep Learning Application for Crop Classification via Multi-Temporal Remote Sensing Images |
| title_full_unstemmed | Deep Learning Application for Crop Classification via Multi-Temporal Remote Sensing Images |
| title_short | Deep Learning Application for Crop Classification via Multi-Temporal Remote Sensing Images |
| title_sort | deep learning application for crop classification via multi temporal remote sensing images |
| topic | crop type classification deep learning multi-temporal remote sensing |
| url | https://www.mdpi.com/2077-0472/13/4/906 |
| work_keys_str_mv | AT qianjingli deeplearningapplicationforcropclassificationviamultitemporalremotesensingimages AT jiatian deeplearningapplicationforcropclassificationviamultitemporalremotesensingimages AT qingjiutian deeplearningapplicationforcropclassificationviamultitemporalremotesensingimages |