Journal of Researches in Mechanics of Agricultural Machinery

Journal of Researches in Mechanics of Agricultural Machinery

Sugarcane Yield Prediction through Integrated Satellite Sentinel-2 Indices and Management Features using Ensemble Machine Learning Algorithms

Document Type : Research Paper

Authors
Feryal Jaderi 1
Nasim Monjezi 2
1 MSc., Biosystems engineering Dept., Faculty of Agriculture, Shahid Chamran University of Ahvaz, Ahvaz, Iran
2 Associate professor, Biosystems engineering Dept., Faculty of Agriculture, Shahid Chamran University of Ahvaz, Ahvaz, Iran
10.22034/jrmam.2026.14989.762
Abstract
Accurate prediction of sugarcane yield plays a crucial role in improving farm management and supply chain sustainability. In this research, a precise framework for predicting sugarcane yield in the Dakht-e-Dehkhoda Sugarcane Agro-Industry (Khuzestan Province) has been presented, based on the combination of satellite data and agricultural information. The data used included 2417 records from the agricultural years 1396 to 1403, gathered from farm management records and Sentinel-2 satellite imagery, including standard vegetation indices such as NDVI and EVI. In the first step, farms were categorized into four distinct groups using the K-means clustering algorithm, based on their management and yield characteristics. Subsequently, to enhance model accuracy, engineered features like water use efficiency and fertilizer use efficiency were defined. Following this, two machine learning models of the Random Forest and Gradient Boosting types were trained for yield prediction. Model evaluation was performed by allocating 80% of the data for training and the remaining 20% to an independent test set. To ensure model stability and generalizability, 5-fold cross-validation was employed during the training phase. The results indicated that the Gradient Boosting model achieved the best performance, reaching a coefficient of determination of 0.9924 and a root mean square error of 1.88 tons per hectare. Furthermore, feature importance analysis revealed that water use efficiency, with a share of 87%, was the most effective factor in yield prediction. In conclusion, the findings of this research confirm that combining management data with satellite information and employing feature engineering can serve as a precise tool to support spatial decision-making and resource management in precision agriculture.
Keywords
Crop yield prediction
Remote sensing
K-means clustering
Ensemble machine learning
Precision agriculture
Subjects
Afsharnia, F., & Marzban, A. (2019). Application of integrated FMEA-ANP approach in prioritizing the risk of sugarcane transport delays to the factory. Journal of Agricultural Machinery, 9(2), 455-467. (In Persian). https://doi.org/10.22067/jam.v9i2.69447
 
Akbarian, S., Jamnani, M. R., Xu, C., Wang, W., & Lim, S. (2024). Plot level sugarcane yield estimation by machine learning on multi-spectral images: A case study of Bundaberg, Australia. Information Processing in Agriculture, 11(4),476-487. https://doi.org/10/1016/j.inpa.2023.06.004
 
Barbosa, L. A. F., Pedronette, D. C. G., & Guilherme, I. R. (2023). A Meta-Feature Model for Exploiting Different Regressors to Estimate Sugarcane Crop Yiel d. IGARSS 2023-2023 IEEE International Geoscience and Remote Sensing Symposium, https://doi.org/10.1109/IGARSS52108.2023.10283309
 
Canata, T. F., Wei, M. C. F., Maldaner, L. F., & Molin, J. P. (2021). Sugarcane Yield Mapping Using High-Resolution Imagery Data and Machine Learning Technique. Remote Sens. 2021, 13, 232.
 
Bhatt, R., Hossain, A., Majumder, D., Chandra, M. S., Ghimire, R., Shahzad, M. F., Verma, K. K., Riar, A. S., Rajput, V. D., & Oliveira, M. W. (2024). Prospects of artificial intelligence for the sustainability of sugarcane production in the modern era of climate change: An overview of related global findings. Journal of Agriculture and Food Research, 18, 101519. https://doi.org/10.1016/j.jafr.2024.101519
 
Charoen-Ung, P., & Mittrapiyanuruk, P. (2018). Sugarcane yield grade prediction using random forest with forward feature selection and hyper-parameter tuning. International Conference on Computing and Information Technology, https://doi.org/10.1007/978-3-319-93692-5_4
 
Das, A., Kumar, M., Kushwaha, A., Dave, R., Dakhore, K. K., Chaudhari, K., & Bhattacharya, B. K. (2023). Machine learning model ensemble for predicting sugarcane yield through synergy of optical and SAR remote sensing. Remote Sensing Applications: Society and Environment, 30, 100962. https://doi.org/10.1016/j.rsase.2023.100962
 
de França e Silva, N. R., Chaves, M. E. D., Luciano, A. C. d. S., Sanches, I. D. A., de Almeida, C. M., & Adami, M. (2024). Sugarcane yield estimation using satellite remote sensing data in empirical or mechanistic modeling: A systematic review. Remote Sensing, 16(5), 863. https://doi.org/10.3390/rs16050863
 
de Oliveira Maia, F. C., Bufon, V. B., & Leão, T. P. (2023). Vegetation indices as a tool for mapping sugarcane management zones. Precision Agriculture, 24(1), 213-234. https://doi.org/10.1007/s11119-022-09939-7.
 
Li, H., Wang, Z., Sun, L., Zhao, L., Zhao, Y., Li, X., Han, Y., Liang, S., & Chen, J. (2024). Parcel-Based Sugarcane Mapping Using Smoothed Sentinel-1 Time Series Data. Remote Sensing, 16(15), 2785. https://doi.org/10.3390/rs16152785
 
Karami, P., & Esmaili-Rineh, S. (2020). Using Maximum Entropy (MaxEnt) modeling and K-mean clustering to analyze the underground habitats of Niphargus genus in Iran. Journal of Animal Research (Iranian Journal of Biology), 33, 310-323, (In Persian).
 
Kaydani, M., Hooshmand, A., & Hamzeh, S. (2025). Sugarcane yield estimation using Landsat and Sentinel satellite imagery (Case study: Haft Tappeh Sugarcane Agro-Industry). Iranian Journal of Irrigation and Drainage, 18(6), 1023-1033. (In Persian).
 
Mariadass, D. A., Moung, E. G., Sufian, M. M., & Farzamnia, A. (2022, November). EXtreme gradient boosting (XGBoost) regressor and shapley additive explanation for crop yield prediction in agriculture. In 2022 12th International Conference on Computer and Knowledge Engineering (ICCKE) 219-224. https://doi.org/10/1109/ICCKE57176.2022.9960069
 
Mirzaei, M., Marofi, S., Solgi, E., Abbasi, M., & Karimi, R. (2021) .Non-destructive estimation of chlorophyll and nitrogen in grape leaves using ground-based hyperspectral data and support vector machine method. Journal of Plant Research (Iranian Journal of Biology), 34(1), 191-204. (In Persian). https://doi.org/20.1001.1.23832592.1400.34.1.12.9
 
Nakhaeinejad, M., Abbasi, M., ZareMehrjerdy, Y., & Asadi Zarch, A. (2022). Greenhouse gas emission reduction model: an integrated approach of linear programming and system dynamics: The case of Iranian power plants. Research in Production and Operations Management, 13(1), 51-77.‌ https://doi.org/10.22108/jpom.2022.129313.1382
 
Parashar, N., Johri, P., Khan, A. A., Gaur, N., & Kadry, S. (2024). An Integrated Analysis of Yield Prediction Models: A Comprehensive Review of Advancements and Challenges. Computers, Materials & Continua, 80. http://dx.doi.org/10.32604/cmc.2024.050240
 
Poudyal, C., Costa, L. F., Sandhu, H., Ampatzidis, Y., Odero, D. C., Arbelo, O. C., & Cherry, R. H. (2022). Sugarcane yield prediction and genotype selection using unmanned aerial vehicle‐based hyperspectral imaging and machine learning. Agronomy Journal, 114(4), 2320–2333. https://doi.org/10.1016/j.fcr.2020.107984
 
Parchami-Araghi, F. & Sadeghi-Lari, A. (2021). Uncertainty analysis of distributed and sub-daily agro-hydrological modeling of a sugarcane cropping system under combined free/controlled subsurface drainage management. Iran Water Research Journal, 15(3), 37-49. (In Persian).
 
Shahhosseini, M., Hu, G., Huber, I., & Archontoulis, S. V. (2021). Coupling machine learning and crop modeling improves crop yield prediction in the US Corn Belt. Scientific reports, 11(1), 1606. https://doi.org/10.1038/s41598-020-80820-1
 
Shendryk, Y., Davy, R., & Thorburn, P. (2021). Integrating satellite imagery and environmental data to predict field-level cane and sugar yields in Australia using machine learning. Field Crops Research, 260, 107984. https://doi.org/10.1016/j.fcr.2020.107984
 
Seyed Jalali, S. M., Navidi, M. N., & Zeinadini Maymand, M. (2021). Estimating sugarcane production potential with different models in the lands of southern Khuzestan province. Journal of Soil Research, 35(1), 59-74. (In Persian) https://doi.org/10.22092/ijsr.2021.351600.548
 
Singla, S. K., Garg, R. D., & Dubey, O. P. (2021). Ensemble machine learning methods for spatio-temporal data analysis of plant and ratoon sugarcane. Intelligent Data Analysis, 25(5), 1291-1322.‌
 
Soltani-Kazemi, M., Minaei, S., Shafi-Zadeh-Moghadam, M., & Mahdavian, A. (2024). Comparison of four algorithms PLSR, RF, GRNN, and SVR for estimating sugarcane canopy moisture during the growth period using Sentinel-2 satellite imagery. Iranian Journal of Remote Sensing and GIS, 16(3), 47-68. (In Persian). https://doi.org/10.48308/gisj.2023.103163
 
Taravat, A., Abebe, G., Gessesse, B., & Tadesse, T. (2024). Estimation of Sugarcane Yield Using Multi-Temporal Sentinel 2 Satellite Imagery and Random Forest Regression. http://dx.doi.org/10.5194/isprs-archives-XLVIII-4-W9-2024-357-2024
 
Van Klompenburg, T., Kassahun, A., & Catal, C. (2020). Crop yield prediction using machine learning: A systematic literature review. Computers and electronics in agriculture, 177, 105709. https://doi.org/10.1016/j.compag.2020.105709
 
 Zhang, S., Qin, H., Li, X., Zhang, M., Yao, W., Lyu, X., & Jiang, H. (2025). Sensitive Multi-spectral Variable Screening Method and Yield Prediction Models for Sugarcane Based on Gray Relational Analysis and Correlation Analysis. Remote Sensing, 17(12), 2055. https://doi.org/10.3390/rs17122055