NDVI Forecasting Based on the Integration of Satellite and Meteorological Data for Agricultural Land Monitoring
Abstract
A data processing pipeline is developed, including extraction, synchronization, and preprocessing of satellite and meteorological time series (missing value interpolation, smoothing, and aggregation), enabling the construction of a robust training dataset.
Based on this dataset, forecasting models are implemented and analyzed, including gradient boosting and a recurrent neural network (LSTM). A comparative study shows that when using aggregated time series, ensemble methods provide higher accuracy compared to recurrent models.
It is established that lagged NDVI values contribute most significantly to prediction performance, indicating the dominant role of the autocorrelation structure of the time series and highlighting limitations in interpreting the influence of external factors.
The proposed approach can be applied in the development of intelligent monitoring and decision support systems in agriculture, including those based on IoT infrastructures.
Full Text:
PDF (Russian)References
Truflyak, Evgeny. Osnovnye elementy sistemy tochnogo zemledeliya [Basic Elements of Precision Agriculture System]. Krasnodar: KubGAU, 2016. URL: https://kubsau.ru/upload/foresight/elements.pdf
Shikhov, Alexander, et al. Tematicheskoe deshifrirovanie i interpretatsiya kosmicheskikh snimkov srednego i vysokogo prostranstvennogo razresheniya [Thematic Interpretation of Medium- and High-Resolution Satellite Images]. Perm: Perm State National Research University, 2020. URL: https://elis.psu.ru/node/642172
Vorobyev, Mikhail. "NDVI vs ASF." GlavAgronom. URL: https://glavagronom.ru/articles/ndvi-vs-asf-ili-pochemu-kompanii-razrabatyvayut-svoy-metod-ocenki-posevov
Government of the Russian Federation. "On Approval of the Program of Fundamental Scientific Research in the Russian Federation for the Long-Term Period (2021–2030)." Decree No. 3684-r, 2020. URL: http://government.ru/docs/all/132190/
Rodimtsev, Sergey, et al. "Modeling Vegetation Conditions Using Deviations of Current NDVI Values from Long-Term Averages." Sel'skokhozyaystvennaya biologiya [Agricultural Biology], 57(3), 2022: 591–603. DOI: 10.15389/agrobiology.2022.3.591rus
Shurlaeva, Elena, et al. "Forecasting the Vegetation Index of Agricultural Lands in the Volgograd Region Using Neural Network Methods." Inzhenerny vestnik Dona [Engineering Journal of Don], no. 5 (2022). URL: https://ivdon.ru/ru/magazine/archive/n5y2022/7664
Cui, C., Zhang, W., Hong, Z., Meng, L. Forecasting NDVI in multiple complex areas using neural network techniques combined feature engineering. International Journal of Digital Earth, 2020, 13(12), 1733–1749. https://doi.org/10.1080/17538947.2020.1808718
Yli-Heikkilä, M., Wittke, S., Luotamo, M., Puttonen, E., Sulkava, M., Pellikka, P., Heiskanen, J., Klami, A. Scalable Crop Yield Prediction with Sentinel-2 Time Series and Temporal Convolutional Network. Remote Sensing, 2022, 14, no. 17: 4193. URL: https://www.mdpi.com/2072-4292/14/17/4193
Wittke, S., Fouilloux, A., Lehti, P., Varho, J., Kivimäki, A., Karhu, M., Karjalainen, M., Vaaja, M., Puttonen, E. EODIE — Earth Observation Data Information Extractor. SoftwareX, 2023, vol. 23: 101421. DOI: 10.1016/j.softx.2023.101421
Quinton, F., Landrieu, L. Crop Rotation Modeling for Deep Learning-Based Parcel Classification from Satellite Time Series. Remote Sensing, 2021, 13, no. 22: 4599. https://doi.org/10.3390/rs13224599
Nyborg, J., Pelletier, Ch., Assent, I. Generalized Classification of Satellite Image Time Series with Thermal Positional Encoding. // In proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. https://doi.org/10.48550/arXiv.2203.09175
Wenger, R., Puissant, A., Weber, J., Idoumghar, L., Forestier, G. Multimodal and Multitemporal Land Use/Land Cover Semantic Segmentation on Sentinel-1 and Sentinel-2 Imagery: An Application on a MultiSenGE Dataset. Remote Sensing, 2023, 15, no. 1: 151. https://doi.org/10.3390/rs15010151
Guo, L., Zhao, S., Gao, J., Zhang, H., Zou, Y., Xiao, X. A Novel Workflow for Crop Type Mapping with a Time Series of Synthetic Aperture Radar and Optical Images in the Google Earth Engine. Remote Sensing, 2022, 14, no. 21: 5458. https://doi.org/10.3390/rs14215458
Index DataBase. A database for remote sensing indices. Search indices for “vegetation” URL: https://www.indexdatabase.de/search/i-search.php?s=vegetation
Huang, S., Tang, L., Hupy, J.P. et al. A commentary review on the use of normalized difference vegetation index (NDVI) in the era of popular remote sensing. J. For. Res. 32, 1–6 (2021). https://doi.org/10.1007/s11676-020-01155-1
Xu, L., Skoularidou, M., Cuesta-Infante, A., Veeramachaneni, K. Modeling Tabular Data using Conditional GAN. NeurIPS, 2019. DOI: 10.48550/arXiv.1907.00503
Alabdulwahab S, Kim Y-T, Seo A, Son Y. Generating Synthetic Dataset for ML-Based IDS Using CTGAN and Feature Selection to Protect Smart IoT Environments. Applied Sciences. 2023; 13(19):10951. DOI: 10.3390/app131910951
Copernicus Request Builder URL: https://shapps.dataspace.copernicus.eu/requests-builder
RP5 Weather Archive. "Weather Archive in Tikhoretsk." URL: https://rp5.ru/Weather_archive_in_Tikhoretsk
Zhu X. X. et al. Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources // IEEE Geoscience and Remote Sensing Magazine, vol. 5, no. 4, pp. 8-36, Dec. 2017. DOI: 10.1109/MGRS.2017.2762307
Reichstein, M., Camps-Valls, G., Stevens, B. et al. Deep learning and process understanding for data-driven Earth system science. Nature 566, 195–204 (2019). https://doi.org/10.1038/s41586-019-0912-1
Sepp Hochreiter, Jürgen Schmidhuber; Long Short-Term Memory. Neural Comput 1997; 9 (8): 1735–1780. doi: https://doi.org/10.1162/neco.1997.9.8.1735
Bryan Lim, Stefan Zohren; Time-series forecasting with deep learning: a survey. Philos Trans A Math Phys Eng Sci 5 April 2021; 379 (2194): 20200209. https://doi.org/10.1098/rsta.2020.0209
Chen, T., Guestrin, C. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '16). Association for Computing Machinery, New York, NY, USA, 785–794. 2016. https://doi.org/10.1145/2939672.2939785
Chandola, V., Banerjee, A., Kumar, V. Anomaly detection: A survey. ACM Comput. Surv. 41, 3, Article 15 (July 2009), 58 pages. https://doi.org/10.1145/1541880.1541882
Thamaraiselvi Dr. R. et al. Attack and Anomaly Detection in IoT Networks using Machine Learning. International Journal of Computer Science and Mobile Computing, Vol.9 Issue.10, October- 2020, pg. 95-103. DOI: 10.47760/ijcsmc.2020.v09i10.012
Dai, L.E., Wang, X., Xu, S.B. (2024). A Deep Learning Based Anomaly Detection Model for IoT Networks. In: Dong, J., Zhang, L., Cheng, D. (eds) Proceedings of the 2nd International Conference on Internet of Things, Communication and Intelligent Technology. IoTCIT 2023. Lecture Notes in Electrical Engineering, vol 1197. Springer, Singapore. https://doi.org/10.1007/978-981-97-2757-5_20
Fu A, Li J. Anomaly Behavior Detection Based on Deep Learning in an IoT Environment. Sensors (Basel). 2025 Dec 15;25(24):7605. DOI: 10.3390/s25247605
Singh, A., Singh, S., Alam M. N., Singh, G. Deep Learning for Anomaly Detection in IoT Systems: Techniques, Applications, and Future Directions. International Journal for Multidisciplinary Research (IJFMR), Volume 6, Issue 4, July-August 2024. DOI: https://doi.org/10.36948/ijfmr.2024.v06i04.24601
Gao, P., Du, W., Lei, Q. et al. NDVI Forecasting Model Based on the Combination of Time Series Decomposition and CNN – LSTM. Water Resour Manage 37, 1481–1497 (2023). https://doi.org/10.1007/s11269-022-03419-3
Gaber, Sh. Kh., Azmy, M., Alakkari, Kh., Abotaleb, M. El-kenawy, El-S. M. Deep Learning in IoT: An LSTM Approach for NDVI Forecasting. 2023, 1-7. DOI: 10.1109/ICEEM58740.2023.10319616
Refbacks
- There are currently no refbacks.
Abava Кибербезопасность Monetec 2026 СНЭ
ISSN: 2307-8162