A CNN-RF Hybrid Approach for Rice Paddy Fields Mapping in Indramayu Using Sentinel-1 and Sentinel-2 Data
Rice, cultivated in paddy fields, is one of the staple foods in the world, especially in Asia. In Indonesia, a substantial number of rice paddy fields have been converted into residential or industrial areas, threatening food security. Therefore, it is necessary to monitor the adequacy of rice paddy...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10869467/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823859624930967552 |
|---|---|
| author | Dodi Sudiana Mia Rizkinia Rahmat Arief Tiara De Arifani Anugrah Indah Lestari Dony Kushardono Anton Satria Prabuwono Josaphat Tetuko Sri Sumantyo |
| author_facet | Dodi Sudiana Mia Rizkinia Rahmat Arief Tiara De Arifani Anugrah Indah Lestari Dony Kushardono Anton Satria Prabuwono Josaphat Tetuko Sri Sumantyo |
| author_sort | Dodi Sudiana |
| collection | DOAJ |
| description | Rice, cultivated in paddy fields, is one of the staple foods in the world, especially in Asia. In Indonesia, a substantial number of rice paddy fields have been converted into residential or industrial areas, threatening food security. Therefore, it is necessary to monitor the adequacy of rice paddy field areas. Recently, remote sensing has become the most widely used method for mapping rice paddy fields. This research focuses on developing a classification model for rice paddy field mapping using remote sensing with radar and optical data fusion, including input variations in polarization, texture, and optical derivative indices. This study proposes the CNN-RF method, which combines a convolutional neural network (CNN) as a feature extractor and a random forest (RF) as a classifier. The experiment used combinations of input data, including variations of single and multisource data, to achieve optimal results. Research findings in some districts of Indramayu show that the scheme combining Sentinel-1 features with GLCM (gray-level co-occurrence matrix) and Sentinel-2 features with selected bands provides the best results, with an overall accuracy of 98.23% and a Kappa coefficient of 0.96, using the CNN-RF method. CNN-RF outperforms other classifiers owing to the hybrid learning combination, which improves the accuracy through feature extraction by CNN and handles complex relationships between features while reducing overfitting by RF. This study contributes to the development of accurate and efficient rice paddy field mapping techniques using remote sensing. |
| format | Article |
| id | doaj-art-8fb6d07bc9e24aeea21f012b451a4f63 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-8fb6d07bc9e24aeea21f012b451a4f632025-02-11T00:01:18ZengIEEEIEEE Access2169-35362025-01-0113232342324610.1109/ACCESS.2025.353781810869467A CNN-RF Hybrid Approach for Rice Paddy Fields Mapping in Indramayu Using Sentinel-1 and Sentinel-2 DataDodi Sudiana0https://orcid.org/0000-0001-8062-0901Mia Rizkinia1https://orcid.org/0000-0003-3197-1611Rahmat Arief2https://orcid.org/0000-0002-8567-3225Tiara De Arifani3Anugrah Indah Lestari4https://orcid.org/0009-0005-1047-0879Dony Kushardono5https://orcid.org/0000-0002-8047-1800Anton Satria Prabuwono6https://orcid.org/0000-0003-3337-6605Josaphat Tetuko Sri Sumantyo7https://orcid.org/0000-0002-4036-6854Department of Electrical Engineering, Faculty of Engineering, Universitas Indonesia, Depok, IndonesiaDepartment of Electrical Engineering, Faculty of Engineering, Universitas Indonesia, Depok, IndonesiaResearch Center for Geoinformatics, Research Organization for Electronics and Informatics, National Research and Innovation Agency, Bandung, IndonesiaDepartment of Electrical Engineering, Faculty of Engineering, Universitas Indonesia, Depok, IndonesiaResearch Center for Geoinformatics, Research Organization for Electronics and Informatics, National Research and Innovation Agency, Bandung, IndonesiaResearch Center for Geoinformatics, Research Organization for Electronics and Informatics, National Research and Innovation Agency, Bandung, IndonesiaDepartment of Computer and Information Sciences, Faculty of Science and Information Technology, Universiti Teknologi PETRONAS, Seri Iskandar, Perak, MalaysiaCenter for Environmental Remote Sensing, Chiba University, Chiba, JapanRice, cultivated in paddy fields, is one of the staple foods in the world, especially in Asia. In Indonesia, a substantial number of rice paddy fields have been converted into residential or industrial areas, threatening food security. Therefore, it is necessary to monitor the adequacy of rice paddy field areas. Recently, remote sensing has become the most widely used method for mapping rice paddy fields. This research focuses on developing a classification model for rice paddy field mapping using remote sensing with radar and optical data fusion, including input variations in polarization, texture, and optical derivative indices. This study proposes the CNN-RF method, which combines a convolutional neural network (CNN) as a feature extractor and a random forest (RF) as a classifier. The experiment used combinations of input data, including variations of single and multisource data, to achieve optimal results. Research findings in some districts of Indramayu show that the scheme combining Sentinel-1 features with GLCM (gray-level co-occurrence matrix) and Sentinel-2 features with selected bands provides the best results, with an overall accuracy of 98.23% and a Kappa coefficient of 0.96, using the CNN-RF method. CNN-RF outperforms other classifiers owing to the hybrid learning combination, which improves the accuracy through feature extraction by CNN and handles complex relationships between features while reducing overfitting by RF. This study contributes to the development of accurate and efficient rice paddy field mapping techniques using remote sensing.https://ieeexplore.ieee.org/document/10869467/Rice paddy fieldpaddy mappingCNN-RFGLCMSentinel |
| spellingShingle | Dodi Sudiana Mia Rizkinia Rahmat Arief Tiara De Arifani Anugrah Indah Lestari Dony Kushardono Anton Satria Prabuwono Josaphat Tetuko Sri Sumantyo A CNN-RF Hybrid Approach for Rice Paddy Fields Mapping in Indramayu Using Sentinel-1 and Sentinel-2 Data IEEE Access Rice paddy field paddy mapping CNN-RF GLCM Sentinel |
| title | A CNN-RF Hybrid Approach for Rice Paddy Fields Mapping in Indramayu Using Sentinel-1 and Sentinel-2 Data |
| title_full | A CNN-RF Hybrid Approach for Rice Paddy Fields Mapping in Indramayu Using Sentinel-1 and Sentinel-2 Data |
| title_fullStr | A CNN-RF Hybrid Approach for Rice Paddy Fields Mapping in Indramayu Using Sentinel-1 and Sentinel-2 Data |
| title_full_unstemmed | A CNN-RF Hybrid Approach for Rice Paddy Fields Mapping in Indramayu Using Sentinel-1 and Sentinel-2 Data |
| title_short | A CNN-RF Hybrid Approach for Rice Paddy Fields Mapping in Indramayu Using Sentinel-1 and Sentinel-2 Data |
| title_sort | cnn rf hybrid approach for rice paddy fields mapping in indramayu using sentinel 1 and sentinel 2 data |
| topic | Rice paddy field paddy mapping CNN-RF GLCM Sentinel |
| url | https://ieeexplore.ieee.org/document/10869467/ |
| work_keys_str_mv | AT dodisudiana acnnrfhybridapproachforricepaddyfieldsmappinginindramayuusingsentinel1andsentinel2data AT miarizkinia acnnrfhybridapproachforricepaddyfieldsmappinginindramayuusingsentinel1andsentinel2data AT rahmatarief acnnrfhybridapproachforricepaddyfieldsmappinginindramayuusingsentinel1andsentinel2data AT tiaradearifani acnnrfhybridapproachforricepaddyfieldsmappinginindramayuusingsentinel1andsentinel2data AT anugrahindahlestari acnnrfhybridapproachforricepaddyfieldsmappinginindramayuusingsentinel1andsentinel2data AT donykushardono acnnrfhybridapproachforricepaddyfieldsmappinginindramayuusingsentinel1andsentinel2data AT antonsatriaprabuwono acnnrfhybridapproachforricepaddyfieldsmappinginindramayuusingsentinel1andsentinel2data AT josaphattetukosrisumantyo acnnrfhybridapproachforricepaddyfieldsmappinginindramayuusingsentinel1andsentinel2data AT dodisudiana cnnrfhybridapproachforricepaddyfieldsmappinginindramayuusingsentinel1andsentinel2data AT miarizkinia cnnrfhybridapproachforricepaddyfieldsmappinginindramayuusingsentinel1andsentinel2data AT rahmatarief cnnrfhybridapproachforricepaddyfieldsmappinginindramayuusingsentinel1andsentinel2data AT tiaradearifani cnnrfhybridapproachforricepaddyfieldsmappinginindramayuusingsentinel1andsentinel2data AT anugrahindahlestari cnnrfhybridapproachforricepaddyfieldsmappinginindramayuusingsentinel1andsentinel2data AT donykushardono cnnrfhybridapproachforricepaddyfieldsmappinginindramayuusingsentinel1andsentinel2data AT antonsatriaprabuwono cnnrfhybridapproachforricepaddyfieldsmappinginindramayuusingsentinel1andsentinel2data AT josaphattetukosrisumantyo cnnrfhybridapproachforricepaddyfieldsmappinginindramayuusingsentinel1andsentinel2data |