Document Type : Original/Review Paper
Authors
Babol Noshirvani University of Technology
Abstract
Accurate rice mapping is crucial for food security, water management, and long-term agricultural planning. This study proposes a phenology-informed LSTM framework that integrates multi-source Sentinel-1 and Sentinel-2 time-series data for robust rice mapping. Sentinel-2 optical images and Sentinel-1 SAR images were preprocessed using cloud-pixel removal, 10-day temporal compositing, and interpolation of missing observations to generate complete and temporally consistent 18-step time series over a 180-day observation period. Three indices, including Sentinel-2-derived NDVI and LSWI and Sentinel-1-derived CR, were extracted to represent vegetation greenness, surface/vegetation moisture, and radar backscatter dynamics. To incorporate rice phenological prior knowledge, reference rice phenology curves were constructed for these indices, and a sliding-window correlation analysis was applied between each pixel-level index trajectory and the corresponding reference curve. This process generated three correlation-based temporal similarity sequences, C_NDVI, C_LSWI, and C_CR, which describe how closely each pixel follows the characteristic rice growth pattern. The raw indices, correlation-based features, and their combined representation were then evaluated as sequential inputs to an LSTM classifier. The results showed that the correlation-based feature set achieved the best performance, with an overall accuracy of 99.81%, an error rate of 0.19%, and an F1-score of 0.9950. Compared with raw time-series indices and the combined feature set, the correlation-based representation improved the discrimination of rice paddies from spectrally similar classes such as water bodies and weeds. The results demonstrate that integrating phenology-informed correlation features with LSTM-based temporal learning provides an effective framework for accurate rice mapping in fragmented and cloud-prone agricultural landscapes.
Keywords
Main Subjects
[1] N. Kussul, S. Drozd, H. Yailymova, A. Shelestov, G. Lemoine, and K. Deininger, "Assessing damage to agricultural fields from military actions in Ukraine: An integrated approach using statistical indicators and machine learning," International Journal of Applied Earth Observation and Geoinformation, vol. 125, p. 103562, 2023.
[2] M. Singha, J. Dong, G. Zhang, and X. Xiao, "High resolution paddy rice maps in cloud-prone Bangladesh and Northeast India using Sentinel-1 data," Scientific data, vol. 6, no. 1, p. 26, 2019.
[3] J. Dong, X. Xiao, M. A. Menarguez, G. Zhang, Y. Qin, D. Thau, ... & B. Moore III, (2016). Mapping paddy rice planting area in northeastern Asia with Landsat 8 images, phenology-based algorithm and Google Earth Engine. Remote sensing of environment, 185, 142-154.
[4] G. Zhang, X. Xiao, J. Dong, F. Xin, Y. Zhang, Y. Qin, RB. Doughty and B. Moore III., "Fingerprint of rice paddies in spatial–temporal dynamics of atmospheric methane concentration in monsoon Asia," Nature communications, vol. 11, no. 1, p. 554, 2020.
[5] H. Yang, B. Pan, N. Li, W. Wang, J. Zhang, and X. Zhang, "A systematic method for spatio-temporal phenology estimation of paddy rice using time series Sentinel-1 images," Remote Sensing of Environment, vol. 259, p. 112394, 2021.
[6] L. Pan, H. Xia, X. Zhao, Y. Guo, and Y. Qin, "Mapping winter crops using a phenology algorithm, time-series Sentinel-2 and Landsat-7/8 images, and Google Earth Engine," Remote sensing, vol. 13, no. 13, p. 2510, 2021.
[7] Y. He, J. Dong, X. Liao, L. Sun, Z. Wang, N. You, Z. Li and P. Fu, "Examining rice distribution and cropping intensity in a mixed single-and double-cropping region in South China using all available Sentinel 1/2 images," International Journal of Applied Earth Observation and Geoinformation, vol. 101, p. 102351, 2021.
[8] C. Huang, S. You, A. Liu, P. Li, J. Zhang, and J. Deng, "High-Resolution National-Scale Mapping of Paddy Rice Based on Sentinel-1/2 Data," Remote Sensing, vol. 15, no. 16, p. 4055, 2023.
[9] G. Tian, H. Li, Q. Jiang, B. Qiao, N. Li, Z. Guo, J. Zhao and H. Yang, "An Automatic Method for Rice Mapping Based on Phenological Features with Sentinel-1 Time-Series Images," Remote Sensing, vol. 15, no. 11, p. 2785, 2023.
[10] A.-X. Zhu, F.-H. Zhao, H.-B. Pan, and J.-Z. Liu, "Mapping rice paddy distribution using remote sensing by coupling deep learning with phenological characteristics," Remote sensing, vol. 13, no. 7, p. 1360, 2021.
[11] S. Liang, Y. Chen, J. Liu, H. Ma, W. Li, P. Sucharitakul, N. Luo, Z. Chen, H. Fang, F. Zhang and J. Xu, "Mapping paddy rice cropping intensity and calendar in monsoon asia at 20 m resolution between 2018 and 2021 from multi-source satellite data using a sample-free algorithm," Available at SSRN 4948283, 2024.
[12] D. Huang, L. Xu, S. Zou, B. Liu, H. Li, L. Pu and H. Chi, "Mapping Paddy Rice in Rice–Wetland Coexistence Zone by Integrating Sentinel-1 and Sentinel-2 Data," Agriculture, vol. 14, no. 3, p. 345, 2024.
[13] Q. Jiang, Z. Tang, L. Zhou, G. Hu, G. Deng, M. Xu and G. Sang, "Mapping Paddy Rice Planting Area in Dongting Lake Area Combining Time Series Sentinel-1 and Sentinel-2 Images," Remote Sensing, vol. 15, no. 11, p. 2794, 2023.
[14] L. Sun, T. Yang, Y. Lou, Q. Shi, and L. Zhang, "Paddy rice mapping based on phenology matching and cultivation pattern analysis combining multi-source data in Guangdong, China," Journal of Remote Sensing, vol. 4, p. 0152, 2024.
[15] X. Jiang, S. Gao, H. Du, S. Fang, Y. Gong, N. Han and Y. Wang, "An automatic decision-level fusion rice mapping method of optical and SAR images based on cloud coverage," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025.
[16] V. N. Fikriyah, R. Darvishzadeh, A. Laborte, and A. Nelson, "Ratoon rice mapping based on Sentinel-1 and Sentinel-2 imagery," Remote Sensing Applications: Society and Environment, p. 101592, 2025.
[17] V. Tiwari, MG. Tulbure, J. Caineta, MD. Gaines, V. Perin, M. Kamal, TJ. Krupnik and MA. Aziz, "Automated in-season rice crop mapping using Sentinel time-series data and Google Earth Engine: A case study in climate-risk prone Bangladesh," Journal of Environmental Management, vol. 351, p. 119615, 2024.
[18] X. Li, C. Sun, H. Meng, X. Ma, G. Huang, and X. Xu, "A novel efficient method for land cover classification in fragmented agricultural landscapes using sentinel satellite imagery," Remote Sensing, vol. 14, no. 9, p. 2045, 2022.
[19] P. Wei, H. Ye, S. Qiao, R. Liu, C. Nie, B. Zhang, L. Song and S. Huang, "Early crop mapping based on sentinel-2 time-series data and the random forest algorithm," Remote Sensing, vol. 15, no. 13, p. 3212, 2023.
[20] E. Rahimi and C. Jung, "The efficiency of long short-term memory (LSTM) in phenology-based crop classification," Korean Journal of Remote Sensing, vol. 40, no. 1, pp. 57-69, 2024.
[21] Y. Xie, L. Xu, H. Zhang, M. Song, J. Ge, and F. Wu, "Tropical Rice Mapping Using Time-Series SAR Images and ESF-Seg Model in Hainan, China, from 2019 to 2023," Remote Sensing, vol. 17, no. 2, 2025.
[22] X. Shi, Z. Chen, H. Wang, D.-Y. Yeung, W.-K. Wong, and W.-c. Woo, "Convolutional LSTM network: A machine learning approach for precipitation nowcasting," Advances in neural information processing systems, vol. 28, 2015.
[23] L. Liu, X. Xiao, Y. Qin, J. Wang, X. Xu, Y. Hu and Z. Qiao, "Mapping cropping intensity in China using time series Landsat and Sentinel-2 images and Google Earth Engine," Remote Sensing of Environment, vol. 239, p. 111624, 2020.
[24] H. Nie, Y. Lin, W. Luo, and G. Liu, "Rice cropping sequence mapping in the tropical monsoon zone via agronomic knowledge graphs integrating phenology and remote sensing," Ecological Informatics, vol. 87, p. 103075, 2025.
[25] S. Park, J. Im, S. Park, C. Yoo, H. Han, and J. Rhee, "Classification and mapping of paddy rice by combining Landsat and SAR time series data," Remote Sensing, vol. 10, no. 3, p. 447, 2018.
[26] Z. He, S. Li, Y. Wang, L. Dai, and S. Lin, "Monitoring rice phenology based on backscattering characteristics of multi-temporal RADARSAT-2 datasets," Remote Sensing, vol. 10, no. 2, p. 340, 2018.
[27] L. Carrasco, A. W. O’Neil, R. D. Morton, and C. S. Rowland, "Evaluating combinations of temporally aggregated Sentinel-1, Sentinel-2 and Landsat 8 for land cover mapping with Google Earth Engine," Remote Sensing, vol. 11, no. 3, p. 288, 2019.
[28] F. Namazi, M. Ezoji, and E. G. Parmehr, "Paddy Rice mapping in fragmented lands by improved phenology curve and correlation measurements on Sentinel-2 imagery in Google earth engine," Environmental Monitoring and Assessment, vol. 195, no. 10, p. 1220, 2023.
[29] F. Namazi, M. Ezoji, and E. Ghanbari Parmehr, "A Phenology Based Paddy Rice Mapping by Correlation Analysis on Sentinel-1/2 Imagery in Fragmented Lands Using GEE Platform," Journal of AI and Data Mining, 2025.
[30] F. Gascon, C. Bouzinac, O. Thépaut, M. Jung, B. Francesconi, J. Louis, V. Lonjou and B. Lafranc, "Copernicus Sentinel-2A calibration and products validation status," Remote Sensing, vol. 9, no. 6, p. 584, 2017.
[31] C. J. Tucker, "Red and photographic infrared linear combinations for monitoring vegetation," Remote sensing of Environment, vol. 8, no. 2, pp. 127-150, 1979.
[32] X. Xiao, S. Boles, J. Liu, D. Zhuang and S. Frolking, "Mapping paddy rice agriculture in southern China using multi-temporal MODIS images," Remote sensing of environment, vol. 95, no. 4, pp. 480-492, 2005.
[33] Y. Shao, N. Ma, M. Chen, C. Zhang, and Y. Cui, "Machine Learning in Landscape Architecture: A Comprehensive Review of Advancements, Applications, and Future Directions," Buildings, vol. 15, no. 21, p. 3827, 2025.
[34] M. Zhang, H. Lin, G. Wang, H. Sun, and J. Fu, "Mapping paddy rice using a convolutional neural network (CNN) with Landsat 8 datasets in the Dongting Lake Area, China," Remote Sensing, vol. 10, no. 11, p. 1840, 2018.
[35] A. Graves and J. Schmidhuber, "Framewise phoneme classification with bidirectional LSTM and other neural network architectures," Neural networks, vol. 18, no. 5-6, pp. 602-610, 2005.
[36] M. Marjani, M. Mahdianpari, and F. Mohammadimanesh, "CNN-BiLSTM: A novel deep learning model for near-real-time daily wildfire spread prediction," Remote Sensing, vol. 16, no. 8, p. 1467, 2024.
[37] V. Ashish, "Attention is all you need," Advances in neural information processing systems, vol. 30, p. I, 2017.
[38] Y.-L. Chang, TH. Tan, TH. Chen, JH. Chuah, L. Chang, MC. Wu, NB. Tatini, SC. Ma and M. Alkhaleefah, "Spatial-temporal neural network for rice field classification from SAR images," Remote Sensing, vol. 14, no. 8, p. 1929, 2022.
[39] G. Shen and J. Liao, "Paddy Rice Mapping in Hainan Island Using Time-Series Sentinel-1 SAR Data and Deep Learning," Remote Sensing, vol. 17, no. 6, 2025.
[40] X. Guan, C. Huang, G. Liu, X. Meng, and Q. Liu, "Mapping rice cropping systems in Vietnam using an NDVI-based time-series similarity measurement based on DTW distance," Remote Sensing, vol. 8, no. 1, p. 19, 2016.
)