Evaluation of Machine Learning Algorithms for Estimating NDVI in Time Series of Multispectral Images for Precision Agriculture
DOI:
https://doi.org/10.61467/2007.1558.2026.v17i2.597Keywords:
NDVI, Machine Learning, Time Series, LSTM, Precision Agriculture, Sentinel-2Abstract
Accurate estimation of the Normalized Difference Vegetation Index (NDVI) is crucial for precision agriculture and environmental monitoring. This study compares five machine learning algorithms LSTM, CNN-LSTM, XGBoost, Random Forest, and Gradient Boosting to predict NDVI using time series of multispectral Sentinel-2 data in a maize crop in Guasave, Sinaloa, Mexico. After data preprocessing, the models were evaluated using cross-validation and metrics such as MSE, MAE, RMSE, MAPE, and R2. The results showed that the LSTM model achieved the best performance in accuracy, while tree-based models struggled to predict extreme values. Recurrent neural networks demonstrated a greater capacity to capture complex temporal dependencies, although they still require improvements to optimize their robustness and precision.
Smart citations: https://scite.ai/reports/10.61467/2007.1558.2026.v17i2.597
Dimensions.
Open Alex.
References
Agrawal, R., Mohite, J. D., Sawant, S. A., Pandit, A., & Pappula, S. (2022). Estimation of NDVI for cloudy pixels using machine learning. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIII-B3-2022, 813–818. https://doi.org/10.5194/isprs-archives-XLIII-B3-2022-813-2022
Bollas, N., Kokinou, E., & Polychronos, V. (2021). Comparison of Sentinel-2 and UAV multispectral data for use in precision agriculture: An application from Northern Greece. Drones, 5(2), 35. https://doi.org/10.3390/drones5020035
Castrillo, D., Blanco, P., & Vélez, S. (2023). Can satellite remote sensing assist in the characterization of yeasts related to biogeographical origin? Sensors, 23(4), 2059. https://doi.org/10.3390/s23042059
Gao, P., Du, W., Lei, Q., Li, J., Zhang, S., & Li, N. (2023). NDVI forecasting model based on the combination of time series decomposition and CNN–LSTM. Water Resources Management, 37(4), 1481–1497. https://doi.org/10.1007/s11269-022-03419-3
Hou, H., Li, R., Zheng, H., Tong, C., Wang, J., Lu, H., Wang, G., Qin, Z., & Wang, W. (2023). Regional NDVI attribution analysis and trend prediction based on the Informer model: A case study of the Maowusu Sandland. Agronomy, 13(12), 2882. https://doi.org/10.3390/agronomy13122882
Khodadadi, N., Towfek, S. K., Zaki, A. M., Alharbi, A. H., Khodadadi, E., Khafaga, D. S., Abualigah, L., Ibrahim, A., Abdelhamid, A. A., & Eid, M. M. (2024). Predicting normalized difference vegetation index using a deep attention network with bidirectional GRU: A hybrid parametric optimization approach. International Journal of Data Science and Analytics. https://doi.org/10.1007/s41060-024-00640-8
Kolecka, N., Ginzler, C., Pazur, R., Price, B., & Verburg, P. H. (2018). Regional scale mapping of grassland mowing frequency with Sentinel-2 time series. Remote Sensing, 10(8), 1221. https://doi.org/10.3390/rs10081221
Meng, Z., Lu, Y., & Wang, H. (2024). Correlation change analysis and NDVI prediction in the Yellow River Basin of China using complex networks and GRNN-PSRLSTM. Environmental Monitoring and Assessment, 196. https://doi.org/10.1007/s10661-024-13168-y
Mohanty, V., Behera, D. K., Panda, A. R., & Swetanisha, S. (2025). Comparative study of ARIMA and deep learning for NDVI forecasting using Landsat 8 data. Indian Journal of Science and Technology, 18(11), 922–936. https://doi.org/10.17485/ijst/v18i11.18
Pellegrini, P., Cossani, C. M., Bella, C. M. D., Piñeiro, G., Sadras, V. O., & Oesterheld, M. (2020). Simple regression models to estimate light interception in wheat crops with Sentinel-2 and a handheld sensor. Crop Science, 60(3), 1607–1616. https://doi.org/10.1002/csc2.20129
Roßberg, T., & Schmitt, M. (2023). A globally applicable method for NDVI estimation from Sentinel-1 SAR backscatter using a deep neural network and the SEN12TP dataset. PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science, 91(3), 171–188. https://doi.org/10.1007/s41064-023-00238-y
Ryu, J.-H., Na, S.-I., & Cho, J. (2020). Inter-comparison of normalized difference vegetation index measured from different footprint sizes in cropland. Remote Sensing, 12(18), 2980. https://doi.org/10.3390/rs12182980
West, H., Quinn, N., Horswell, M., & White, P. (2018). Assessing vegetation response to soil moisture fluctuation under extreme drought using Sentinel-2. Water, 10(7), 838. https://doi.org/10.3390/w10070838
Xu, D., An, D., & Guo, X. (2020). The impact of non-photosynthetic vegetation on LAI estimation by NDVI in mixed grassland. Remote Sensing, 12(12), 1979. https://doi.org/10.3390/rs12121979
Zhao, F., Yang, G., Yang, H., Zhu, Y., Meng, Y., Han, S., & Bu, X. (2021). Short and medium-term prediction of winter wheat NDVI based on the DTW–LSTM combination method and MODIS time series data. Remote Sensing, 13(22), 4660. https://doi.org/10.3390/rs13224660
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Combinatorial Optimization Problems and Informatics
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
