|
Determining the area under rice cultivation using machine learning methods and simultaneous use of optical satellite images and radar with virtual aperture (Case study: Babol city)
|
Ali لخخیشقظ   |
|
|
|
Abstract: (77 Views) |
Rice is one of the key agricultural products in Iran and the world, and accurate monitoring of its cultivated area, especially the separation of monoculture and double-cropping, plays a vital role in water resources management and production planning. Mazandaran province, as the country's rice production hub, requires new methods for monitoring agricultural lands due to the spatial dispersion of farms and diverse environmental conditions. In this study, a new framework based on the combination of deep convolutional networks (CNN) and recurrent networks (RNN) was developed, which identifies rice lands and distinguishes monoculture/double-cropping patterns at two levels. In the first step, the U-Net neural network architecture was used to identify rice lands in Babol County. This model was trained in two scenarios: (1) with Sentinel-2 optical data only and (2) with a combination of optical and radar data (Sentinel-2 and Sentinel-1). The results of the experiments showed that the model based on Sentinel-2 optical data was evaluated with an overall accuracy of 96.35% and an F1 score of 0.957. While it was expected that the combination of optical-radar data would improve the results, in the study area, due to the relatively cloudless conditions, the main advantage of SAR data was not very apparent. This, along with the need for more complex preprocessing of these data, could be the reason for the relative decrease in the accuracy of the combined model with an overall accuracy of 94.32 and an F1 score of 0.93. Three regions were selected to test the generalizability of the model: Sari County as an area close to the main area, Lahijan County as an area with a greater distance and more diverse vegetation, and south Tehran as an area without rice cultivation. The generalizability assessment showed that the model provided stable and accurate results in Sari County, while in Lahijan, the accuracy decreased but was still acceptable with an overall accuracy of over 88%. Testing the model in rice-free lands south of Tehran also showed a very low error rate (14.2%), indicating the high ability of the model to distinguish non-rice fields. In the second step, the GRU recurrent network was used to distinguish monoculture and biculture lands. This model was able to provide a very good performance in distinguishing monoculture and biculture rice fields with an overall accuracy of 98.4%, a kappa coefficient of 0.951, and an F1 score of 0.974. |
|
| Keywords: Rice Crop Area, Deep learning, CNN, RNN, Sentinel1, Sentinel2 |
|
|
Full-Text [PDF 15254 kb]
(19 Downloads)
|
Type of Study: Research |
Subject:
Photo&RS
Received: 2025/10/14 | Accepted: 2026/06/16
|
|
|
|
|
|
|
| References |
1. Elert, E. Rice by the numbers: A good grain. Nature 514, S50-S51 (2014). [ DOI:10.1038/514S50a] 2. Basnet, B. M. S. (2012a). Rice: Water, Food Security and Climate Change in Nepal. Hydro Nepal: Journal of Water, Energy and Environment, 78-80. [ DOI:10.3126/hn.v11i1.7217] 3. FAO Rice Market Monitor (RMM), April 2018, VOLUME XXI ISSUE No. 1 4. Chang, L., Chen, Y.-T., Wang, J.-H., & Chang, Y.-L. (2020). Rice-Field Mapping with Sentinel-1A SAR Time-Series Data. Remote Sensing, 13(1), 103. [ DOI:10.3390/rs13010103] 5. Ferreira, S. S. D., Sanchez, J. M., & Gonçalves, J. M. (2023). A Remote-Sensing-Assisted Estimation of Water Use in Rice Paddy Fields: A Study on Lis Valley, Portugal. Agronomy. [ DOI:10.3390/agronomy13051357] 6. Saadat, M., Hasanlou, M., & Homayouni, S. (2019). RICE CROP MAPPING USING SENTINEL-1 TIME SERIES IMAGES (CASE STUDY: MAZANDARAN, IRAN). ISPRS -International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-4/W18, 897-904.
https://doi.org/10.5194/isprs-archives-XLII-4-W18-897-2019 [ DOI:10.5194/isprs-archives-xlii-4-w18-897-2019] 7. Remote sensing for agriculture and resource management. (2022).
https://doi.org/10.1016/B978-0-12-822976-7.00012-0 [ DOI:10.1016/b978-0-12-822976-7.00012-0] 8. Haj Hussain, M., Abuhani, D. A., Khan, J., ElMohandes, M., Zualkernan, I., & Ali, T. (2023). A light-weight cropland mapping model using satellite imagery. [ DOI:10.3390/s23156729] 9. Ramadhani, F., Pullanagari, R., Kereszturi, G., & Procter, J. (2020). Automatic Mapping of Rice Growth Stages Using the Integration of SENTINEL-2, MOD13Q1, and SENTINEL-1. Remote Sensing, 12(21), 3613. [ DOI:10.3390/rs12213613] 10. Cao, J., Zhang, Z., Tao, F., Zhang, L., Luo, Y., Zhang, J., Han, J., & Xie, J. (2021). Integrating Multi-Source Data for Rice Yield Prediction across China using Machine Learning and Deep Learning Approaches. Agricultural and Forest Meteorology, 297, 108275. [ DOI:10.1016/j.agrformet.2020.108275] 11. Saadat, M., et al. (2022). Multi-stream deep convolutional networks for accurate paddy rice mapping using Sentinel-1 and Sentinel-2 time-series data in Mazandaran Province, Iran. Agriculture, 12(2083), 1-20.
https://doi.org/10.3390/agriculture12122083 [ DOI:10.3390/agriculture12202083] 12. Sudiana, D., Abdurahman, M., Wirahman, A. D., & Farda, N. M. (2025). CNN-Random Forest hybrid method for phenology-based paddy rice mapping using Sentinel-2 and Landsat-8 satellite images. Computers, 14(336), 1-15. [ DOI:10.3390/computers14080336] 13. Marques, A. C., Luís, I. C., Coelho, A. R., Pessoa, C., Daccak, D., Simões, M., Almeida, A. S., Scotti Campos, P., Ramalho, J. C., Semedo, J. M., Kullberg, J. C., Brito, M., Pessoa, M. F., Reboredo, F., Marques, P. A. A. P., Silva, M. M., Legoinha, P., Oliveira, K., Pais, I. P., & Lidon, F. C. (2022, January 14. Tucker, C. J., & Sellers, P. J. (1986). Satellite remote sensing of primary production. International Journal of Remote Sensing, 7(11), 1395-1416. [ DOI:10.1080/01431168608948944] 15. Comparing satellites and vegetation indices for cover crop biomass estimation. (2022). Computers and Electronics in Agriculture. [ DOI:10.1016/j.compag.2022.106900] 16. Ferreira, S. S. D., Sanchez, J. M., & Gonçalves, J. M. (2023). A Remote-Sensing-Assisted Estimation of Water Use in Rice Paddy Fields: A Study on Lis Valley, Portugal. Agronomy. [ DOI:10.3390/agronomy13051357] 17. Arii, M., & Yamada, H. (2017). Rice paddy monitoring by L-band MIMP SAR approach. International Geoscience and Remote Sensing Symposium. [ DOI:10.1109/IGARSS.2017.8127486] 18. Chang, L., Chen, Y.-T., Wang, J.-H., & Chang, Y.-L. (2020). Rice-Field Mapping with Sentinel-1A SAR Time-Series Data. Remote Sensing, 13(1), 103. [ DOI:10.3390/rs13010103] 19. Shao, Y., Liao, J., & Wang, C. (2002). Analysis of temporal radar backscatter of rice: A comparison of SAR observations with modeling results. Canadian Journal of Remote Sensing.
https://doi.org/10.5589/m02-019 [ DOI:10.5589/M02-019] 20. Lalitha, V., & Latha, B. N. (2022). A review on remote sensing imagery augmentation using deep learning. Materials Today: Proceedings. [ DOI:10.1016/j.matpr.2022.03.341] 21. Searching for CNN Architectures for Remote Sensing Scene Classification. (2022). IEEE Transactions on Geoscience and Remote Sensing.
https://doi.org/10.1109/TGRS.2021.3097938 [ DOI:10.1109/tgrs.2021.3097938] 22. Fu, T., et al. (2023). Unet: A Deep Learning Model for Rice Extraction in Rio Grande do Sul. Remote Sensing, 15(16), 4021. [ DOI:10.3390/rs15164021] 23. Qin, J., Hu, T., Yuan, J., Liu, Q., Wang, W., Liu, J., Guo, L., & Song, G.-Z. (2023). Deep-Learning-Based Rice Phenological Stage Recognition. Remote Sensing. [ DOI:10.3390/rs15112891] 24. Crisóstomo de Castro Filho, H., Abílio de Carvalho Júnior, O., Ferreira de Carvalho, O. L., Pozzobon de Bem, P., dos Santos de Moura, R., Olino de Albuquerque, A., Rosa Silva, C., Guimarães Ferreira, P. H., Fontes Guimarães, R., & Trancoso Gomes, R. A. (2020). Rice Crop Detection Using LSTM, Bi-LSTM, and Machine Learning Models from Sentinel-1 Time Series. Remote Sensing, 12(16), 2655. [ DOI:10.3390/rs12162655] 25. Quinlan, J. R. (1994). Book Review : C4 . 5 : Programs for Machine Learning. In Machine Learning (Vol. 240). 26. Breiman, L. (2001). ST4_Method_Random_Forest. Machine Learning, 45(1), 5-32. [ DOI:10.1017/CBO9781107415324.004] |
|
| Add your comments about this article |
|
|
|
|
لخخیشقظ A. Determining the area under rice cultivation using machine learning methods and simultaneous use of optical satellite images and radar with virtual aperture (Case study: Babol city). JGST 2026; 15 (4) :85-102 URL: http://jgst.issgeac.ir/article-1-1241-en.html
|
