Determination of crop types based on remote sensing data using artificial intelligence methods
DOI:
https://doi.org/10.21638/spbu10.2025.108Abstract
One of the important subtasks for estimating and forecasting yields is crop mapping. In recent years, remote sensing data has been actively used to solve it, which allows us to quickly obtain information about the state of fields, as well as artificial intelligence methods. The purpose of this work was to investigate the possibilities of using neural network methods to determine crops of agricultural plants based on remote sensing data. Two different data sets are taken as a basis: an open dataset of PASTIS satellite images, as well as a mosaic of aerial photographs of the Agrophysical Research Institute obtained in the fields of the Leningrad region using the Geoscan-401 unmanned system. Five segmentation models (U-Net, U-Net 3+, DeepLabV3, FCN, Swin Transformer) were used for training and their performance was evaluated on a set of satellite image data. The results of the experiment showed that the accuracy of the U-Net 3+ and U-Net models significantly exceeds other models. At the same time, the transfer of models trained on low-resolution satellite images to high-resolution aerial photographs for further training has effectively improved the performance of models.
Keywords:
crop mapping, satellite imagery, aerial photography, neural network models
Downloads
References
Kwak G. H., Park N. W. Impact of texture information on crop classification with machine learning and UAV images // Applied Sciences. 2019. Vol. 9. Art. N 643. https://doi.org/10.3390/app9040643
Bure V. M., Mitrofanova O. A., Mitrofanov E. P., Petrushin A. F. Remote sensing data processing for plant production control // Stability and Control Processes. Proceedings of the 4th International Conference dedicated to the memory of professor Vladimir Zubov. Cham: Springer, 2022. P. 753–758. https://doi.org/10.1007/978-3-030-87966-2_86
Weiss M., Jacob F., Duveiller G. Remote sensing for agricultural applications: A meta-review // Remote Sensing of Environment. 2020. Vol. 236. Art. N 111402. https://doi.org/10.1016/j.rse.2019.111402
Митрофанова О. А., Митрофанов Е. П., Буре Н. А. Применение онтологического подхода к проектированию геопространственной базы опытных данных для информационного обеспечения исследований в точном земледелии // Вестник Санкт-Петербургского университета. Прикладная математика. Информатика. Процессы управления. 2022. Т. 18. Вып. 2. С. 253–262. https://doi.org/10.21638/11701/spbu10.2022.206
Молин А. Е., Блеканов И. С., Митрофанов Е. П., Митрофанова О. А. Методы генерации синтетических данных для обучения нейросетей в задаче сегментации уровня азотного режима растений на снимках беспилотных летательных аппаратов на сельскохозяйственном поле // Вестник Санкт-Петербургского университета. Прикладная математика. Информатика. Процессы управления. 2024. Т. 20. Вып. 1. С. 20–33. https://doi.org/10.21638/11701/spbu10.2024.103
Kim Y., Park N.-W., Lee K.-D. Self-learning based land-cover classification using sequential class patterns from past land-cover maps // Remote Sensing. 2017. Vol. 9. Art. N 921. https://doi.org/10.3390/rs9090921
Selea T., Pslaru M.-F. AgriSen — a dataset for crop classification // 22nd International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC). Timisoara, Romania, 2020. P. 259–263. https://doi.org/10.1109/SYNASC51798.2020.00049
Zhou Y., Zhu W., Feng L., Gao J., Chen Y., Zhang X., Luo J. Hierarchical classification for improving parcel-scale crop mapping using time-series Sentinel-1 data // Journal of Environmental Management. 2024. Vol. 369. Art. N 122251. https://doi.org/10.1016/j.jenvman.2024.122251
Iglovikov V., Shvets A. TernausNet: U-Net with VGG11 encoder pre-trained on ImageNet for image segmentation // arXiv: 1801.05746. 2018. https://doi.org/10.48550/arXiv.1801.05746
Huang H., Lin L., Tong R., Hu H., Zhang Q., Iwamoto Y., Han X., Chen Y.-W., Wu J. UNet 3+: A full-scale connected UNet for medical image segmentation // arXiv: 2004.08790. 2020. https://doi.org/10.48550/arXiv.2004.08790
Fu G., Liu C., Zhou R., Sun T., Zhang Q. Classification for high resolution remote sensing imagery using a fully convolutional network // Remote Sensing. 2017. Vol. 9. Art. N 498. https://doi.org/10.3390/rs9050498
Xu X., Zou J., Cai J., Zou D. Multi-scale contextual swin transformer for crop image segmentation // Journal of Physics: Conference Series. 2024. Vol. 2759. Art. N 012012. https://doi.org/10.1088/1742-6596/2759/1/012012
Lu J., Zhou B., Wang B., Zhao Q. Land cover classification of remote sensing images based on improved DeepLabV3+ network // Journal of Physics: Conference Series. 2022. Vol. 2400. Art. N 012035. https://doi.org/10.1088/1742-6596/2400/1/012035
He X., Chen Y., Ghamisi P. Heterogeneous transfer learning for hyperspectral image classification based on convolutional neural network // IEEE Transactions on Geoscience and Remote Sensing. 2020. Vol. 58. N 5. P. 3246–3263. https://doi.org/10.1109/TGRS.2019.2951445
Garnot V. S. F., Landrieu L. Panoptic segmentation of satellite image time series with convolutional temporal attention networks // Proceedings of the IEEE International Conference on Computer Vision. Montreal, Canada: Institute of Electrical and Electronics Engineers Inc., 2021. P. 4852–4861. https://doi.org/10.1109/ICCV48922.2021.00483
Буре В. М., Митрофанов Е. П., Митрофанова О. А., Петрушин А. Ф. Выделение однородных зон сельскохозяйственного поля для закладки опытов с помощью беспилотного летательного аппарата // Вестник Санкт-Петербургского университета. Прикладная математика. Информатика. Процессы управления. 2018. Т. 14. Вып. 2. С. 145–150. https://doi.org/10.21638/11701/spbu10.2018.206
References
Kwak G. H., Park N. W. Impact of texture information on crop classification with machine learning and UAV images. Applied Sciences, 2019, vol. 9, art. no. 643. https://doi.org/10.3390/app9040643
Bure V. M., Mitrofanova O. A., Mitrofanov E. P., Petrushin A. F. Remote sensing data processing for plant production control. Stability and Control Processes. Proceedings of the 4th International Conference dedicated to the memory of professor Vladimir Zubov. Cham, Springer, 2022, pp. 753–758. https://doi.org/10.1007/978-3-030-87966-2_86
Weiss M., Jacob F., Duveiller G. Remote sensing for agricultural applications: A meta-review. Remote Sensing of Environment, 2020, vol. 236, art. no. 111402. https://doi.org/10.1016/j.rse.2019.111402
Mitrofanova O. A., Mitrofanov E. P., Bure N. A. Primenenie ontologicheskogo podkhoda k proektirovaniiu geoprostranstvennoi bazy opytnykh dannykh dlia informatsionnogo obespecheniia issledovanii v tochnom zemledelii [Ontological approach application to the design of a geospatial experimental database for information support of research in precision agriculture]. Vestnik of Saint Petersburg University. Applied Mathematics. Computer Science. Control Processes, 2022, vol. 18, iss. 2, pp. 253–262. https://doi.org/10.21638/11701/spbu10.2022.206 (In Russian)
Molin A. E., Blekanov I. S., Mitrofanov E. P., Mitrofanova O. A. Metody generatsii sinteticheskikh dannykh dlia obucheniia neirosetei v zadache segmentatsii urovnia azotnogo rezhima rastenii na snimkakh bespilotnykh letatel'nykh apparatov na sel'skokhoziaistvennom pole [Synthetic data generation methods for training neural networks in the task of segmenting the level of crop nitrogen status on UAV images of agricultural fields]. Vestnik of Saint Petersburg University. Applied Mathematics. Computer Science. Control Processes, 2024, vol. 20, iss. 1, pp. 20–33. https://doi.org/10.21638/11701/spbu10.2024.103 (In Russian)
Kim Y., Park N.-W., Lee K.-D. Self-learning based land-cover classification using sequential class patterns from past land-cover maps. Remote Sensing, 2017, vol. 9, art. no. 921. https://doi.org/10.3390/rs9090921
Selea T., Pslaru M.-F. AgriSen — a dataset for crop classification. 22nd International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC). Timisoara, Romania, 2020, pp. 259–263. https://doi.org/10.1109/SYNASC51798.2020.00049
Zhou Y., Zhu W., Feng L., Gao J., Chen Y., Zhang X., Luo J. Hierarchical classification for improving parcel-scale crop mapping using time-series Sentinel-1 data. Journal of Environmental Management, 2024, vol. 369, art. no. 122251. https://doi.org/10.1016/j.jenvman.2024.122251
Iglovikov V., Shvets A. TernausNet: U-Net with VGG11 encoder pre-trained on ImageNet for image segmentation. arXiv: 1801.05746, 2018. https://doi.org/10.48550/arXiv.1801.05746
Huang H., Lin L., Tong R., Hu H., Zhang Q., Iwamoto Y., Han X., Chen Y.-W., Wu J. UNet 3+: A full-scale connected UNet for medical image segmentation. arXiv: 2004.08790, 2020. https://doi.org/10.48550/arXiv.2004.08790
Fu G., Liu C., Zhou R., Sun T., Zhang Q. Classification for high resolution remote sensing imagery using a fully convolutional network. Remote Sensing, 2017, vol. 9, art. no. 498. https://doi.org/10.3390/rs9050498
Xu X., Zou J., Cai J., Zou D. Multi-scale contextual swin transformer for crop image segmentation. Journal of Physics: Conference Series, 2024, vol. 2759, art. no. 012012. https://doi.org/10.1088/1742-6596/2759/1/012012
Lu J., Zhou B., Wang B., Zhao Q. Land cover classification of remote sensing images based on improved DeepLabV3+ network. Journal of Physics: Conference Series, 2022, vol. 2400, art. no. 012035. https://doi.org/10.1088/1742-6596/2400/1/012035
He X., Chen Y., Ghamisi P. Heterogeneous transfer learning for hyperspectral image classification based on convolutional neural network. IEEE Transactions on Geoscience and Remote Sensing, 2020, vol. 58, no. 5, pp. 3246–3263. https://doi.org/10.1109/TGRS.2019.2951445
Garnot V. S. F., Landrieu L. Panoptic segmentation of satellite image time series with convolutional temporal attention networks. Proceedings of the IEEE International Conference on Computer Vision. Montreal, Canada, Institute of Electrical and Electronics Engineers Inc. Publ., 2021, pp. 4852–4861. https://doi.org/10.1109/ICCV48922.2021.00483
Bure V. M., Mitrofanov E. P., Mitrofanova O. A., Petrushin A. F. Vydelenie odnorodnykh zon sel'skokhoziaistvennogo polia dlia zakladki opytov s pomoshch'iu bespilotnogo letatel'nogo apparata [Selection of homogeneous zones of agricultural field for laying of experiments using unmanned aerial vehicle]. Vestnik of Saint Petersburg University. Applied Mathematics. Computer Science. Control Processes, 2018, vol. 14, iss. 2, pp. 145–150. https://doi.org/10.21638/11701/spbu10.2018.206 (In Russian)
Downloads
Published
How to Cite
Issue
Section
License
Articles of "Vestnik of Saint Petersburg University. Applied Mathematics. Computer Science. Control Processes" are open access distributed under the terms of the License Agreement with Saint Petersburg State University, which permits to the authors unrestricted distribution and self-archiving free of charge.
