International Journal of Web Research

International Journal of Web Research

Transfer Learning for Crop Classification in Data-Scarce Regions Using Satellite Imagery

Document Type : Original Article

Authors
Erfan Shakouri
Saeed Zare
Masomeh Azimzadeh
Parvin Ahmadi
ICT Research Institute, Tehran, Iran;
10.22133/ijwr.2025.537225.1301
Abstract
Satellite imagery provides valuable data to address the growing demand for agricultural production. However, analyzing such vast amounts of data requires advanced artificial intelligence methods, such as deep learning. The primary challenge lies in the scarcity of labeled training data, as its preparation is both costly and time-consuming. To address this issue, this study integrates remote sensing data, deep neural networks, and transfer learning techniques to estimate the cultivated area of strategic crops in Iran. Given the diverse climates and topographies across Iran’s provinces, in addition to Sentinel-1 and Sentinel-2 satellite data, MODIS sensor and SRTM elevation data were also utilized. To compensate for data limitations, transfer learning was employed to enhance model performance in data-deficient regions (Kermanshah and Markazi). This approach resulted in an approximate 10% improvement in Cohen’s Kappa coefficient. Furthermore, the study investigated the minimum data required for fine-tuning the models. The results demonstrated that even with a reduction of over 60% in the target province's training data, transfer learning still achieved model performance comparable to scenarios where it was not applied.
Keywords
Crop Classification
Transformers
CNN
Transfer Learning
Satellite Image Time Series
Data-scarce

Subjects

[1]     Y. Hu et al., "An Interannual Transfer Learning Approach for Crop Classification in the Hetao Irrigation District, China," Remote Sensing, vol. 14, p. 1208, 03/01 2022.
[2]     H.-W. Jo, A. Koukos, V. Sitokonstantinou, W.-K. Lee, and C. Kontoes, "Towards global crop maps with transfer learning," arXiv preprint arXiv:2211.04755, 2022.
[3]     K. K. Gadiraju and R. R. Vatsavai, "Remote Sensing Based Crop Type Classification Via Deep Transfer Learning," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 16, pp. 4699-4712, 2023.
[4]     O. Antonijevic, S. Jelić, B. Bajat, and M. Kilibarda, "Transfer learning approach based on satellite image time series for the crop classification problem," Journal of Big Data, vol. 10, 04/29 2023.
[5]     M. Račič, K. Oštir, A. Zupanc, and L. Čehovin Zajc, "Multi-Year Time Series Transfer Learning: Application of Early Crop Classification," Remote Sensing, vol. 16, p. 270, 01/10 2024.
[6]     V. Barrière, M. Claverie,M. Schneider, G. Lemoine, R. Andrimont, “Boosting Crop Classification by Hierarchically Fusing Satellite Modalities Across Seasons and Regions,” Remote Sensing of Environment, vol. 305,  p.114110., 2024.
[7]     A. Nowakowski et al., "Crop type mapping by using transfer learning," International Journal of Applied Earth Observation and Geoinformation, vol. 98, p. 102313, 06/01 2021.
[8]     P. Hao, L. Di, C. Zhang, and G. Liying, "Transfer Learning for Crop classification with Cropland Data Layer data (CDL) as training samples," Science of The Total Environment, vol. 733, p. 138869, 04/01 2020.
[9]     C. Pelletier, G. I. Webb, and F. Petitjean, "Temporal Convolutional Neural Network for the Classification of Satellite Image Time Series," Remote Sensing, vol. 11, no. 5, p. 523, 2019.
[10]   V. S. F. Garnot, L. Landrieu, S. Giordano, and N. Chehata, "Satellite image time series classification with pixel-set encoders and temporal self-attention," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 12325-12334.
[11]   J. Mai, Q. Feng, Sh. Fu, R. Wang, “Enhancing Crop Type Mapping in Data-Scarce Regions Through Transfer Learning: A Case Study of the Hexi Corridor,” Remote Sensing, vol. 17, no. 9, p. 1494, 2025.
[12]   H. Hoppe et al., “Transferability of Machine Learning Models for Crop Classification,” Remote Sensing, vol. 16, no. 9, p. 1493, 2024.
[13]   X. Guo et al., “Fine Classification of Crops Based on an Inductive Transfer Learning Approach,” GIScience & Remote Sensing, 61, no. 1, p. 2319939, 2024.
[14]   H. Xue, Y. Fan, G. Dong, S. He, Y. Lian, and W. Luan, "Crop classification in the middle reaches of the Hei River based on model transfer," Scientific Reports, vol. 14, no. 1, Art. 28964, Nov. 22, 2024.
[15]   I. Gallo, L. Ranghetti, N. Landro, R. La Grassa, and M. Boschetti, "In-season and dynamic crop mapping using 3D convolution neural networks and sentinel-2 time series," ISPRS Journal of Photogrammetry and Remote Sensing, vol. 195, pp. 335-352, 2023/01/01/ 2023.
[16]   J. Yao, J. Wu, C. Xiao, Z. Zhang, and J. Li, "The Classification Method Study of Crops Remote Sensing with Deep Learning, Machine Learning, and Google Earth Engine," Remote Sensing, vol. 14, no. 12, p. 2758, 2022.
[17]   O. E. Adeyeri et al., "Land surface dynamics and meteorological forcings modulate land surface temperature characteristics," Sustainable Cities and Society, vol. 101, p. 105072, 2024/02/01/ 2024.
[18]   M. O. Román et al., "Continuity between NASA MODIS Collection 6.1 and VIIRS Collection 2 land products," Remote Sensing of Environment, vol. 302, p. 113963, 2024/03/01/ 2024.
[19]   J. Liu, K. Yang, A. Tariq, L. Lu, W. Soufan, and A. El Sabagh, "Interaction of climate, topography and soil properties with cropland and cropping pattern using remote sensing data and machine learning methods," The Egyptian Journal of Remote Sensing and Space Sciences, vol. 26, no. 3, pp. 415-426, 2023/12/01/ 2023.
[20]   Aashish, A. Thakkar, S. Yadav, S. Saini, and K. Lata, "CNN and Autoencoders based Hybrid Deep Learning Model for Crop Disease Detection," in 2022 International Conference on Connected Systems & Intelligence (CSI), 2022, pp. 1-7.
[21]   S. Ofori-Ampofo, C. Pelletier, and S. Lang, "Crop Type Mapping from Optical and Radar Time Series Using Attention-Based Deep Learning," Remote Sensing, vol. 13, no. 22, p. 4668, 2021.
[22]   X. Zhou, J. Wang, B. Shan, and Y. He, "Early-Season Crop Classification Based on Local Window Attention Transformer with Time-Series RCM and Sentinel-1," Remote Sensing, vol. 16, no. 8, p. 1376, 2024.
[23]   D. J. Gallardo-Romero, O. E. Apolo-Apolo, J. Martínez-Guanter, and M. Pérez-Ruiz, "Multilayer Data and Artificial Intelligence for the Delineation of Homogeneous Management Zones in Maize Cultivation," Remote Sensing, vol. 15, no. 12, p. 3131, 2023.
[24]   A. Mirzaei, H. Bagheri, and I. Khosravi, "Enhancing crop classification accuracy by synthetic SAR-optical data generation using deep learning," *arXiv preprint* arXiv:2402.02121, 2024.
[25]   J. Reuss, J. Macdonald, S. Becker, K. Schultka, L. Richter, and M. Körner, "Meta-learning for few-shot time series crop type classification: A benchmark on the EuroCropsML dataset," arXiv preprint arXiv:2504.11022, Apr. 2025. [Online]. Available: https://doi.org/10.48550/arXiv.2504.11022.
[26]   X. Qin, X. Su, and L. Zhang, "SITSMamba for crop classification based on satellite image time series," arXiv preprint arXiv:2409.09673, Sep. 15, 2024. [Online]. Available: https://arxiv.org/abs/2409.09673.
International Journal of Web Research
Volume 9, Issue 1
Winter 2026
Pages 25-37