PREDICTIVE MODELLING FOR SUGARCANE PRODUCTION: A COMPREHENSIVE COMPARISON OF ARIMA AND MACHINE LEARNING ALGORITHMS

Vishwajeet Singh; Med Ram Verma; Subhash Kumar Yadav

doi:10.48165/abr.2024.26.01.23

Authors

Vishwajeet Singh Directorate of Online Education, Manipal Academy of Higher Education, Manipal – 576 104, Karnataka (India)
Med Ram Verma Division of Design of Experiments, ICAR-Indian Agricultural Statistics Research Institute, Library Avenue, New Delhi – 110 012 (India)
Subhash Kumar Yadav Department of Statistics, Babasaheb Bhimrao Ambedkar University, Lucknow - 226 025, Uttar Pradesh (India)

DOI:

https://doi.org/10.48165/abr.2024.26.01.23

Keywords:

ARIMA, gradient boosting machine, machine learning methods, random forest, sugarcane yield prediction, support vector machine

Abstract

Accurate prediction of sugarcane yield is essential for trade, economic planning, and sustainable agriculture in India. This study addressed the challenge of forecasting sugarcane yield by evaluating the effectiveness of time series modelling and machine learning algorithms. Leveraging data spanning from 2001 to 2020, the research focuses on predicting the sugarcane yield for the subsequent years. The problem statement revolves around the need for precise yield predictions to inform decision-making in the agricultural sector. Methods employed included the utilization of Autoregressive Integrated Moving Average (ARIMA) for time series analysis and machine learning algorithms such as Random Forest (RF), Support Vector Machine (SVM), and Gradient Boosting Machine (GBM). The analysis encompassed sugarcane yield data spanning multiple years, with predictions extending for a specified duration. Through analysis of temporal patterns and dependencies within the sugarcane yield time series data using Autocorrelation Function (ACF) and Partial Autocorrelation Function (PACF), the study optimized the predictive models. Results indicated that ARIMA outperformed machine learning algorithms, exhibiting superior performance with a root meansquare error of 36700.68 anda minimumAICvalue of 456.7. The study emphasizes the significance of accurate yield predictions for agricultural planning and decision-making, highlighting the implications for sustainable crop management and the fortification of Indian sugar industry.The study affirms the importance of informed decisions facilitated by accurate yield predictions in resilient agricultural sector. Overall, this study contributes to the advancement of sugarcane yield prediction, offers practical insights for stakeholders and policymakers in India's agricultural landscape.

Downloads

Download data is not yet available.

References

Alpaydin, E. 2010. Introduction to Machine Learning (2nd edn.). The MIT Press Cambridge, Massachusetts, London, England.

Arumugam, P., Chemura, A. and Schauberger, B. 2021. Remote sensing based yield estimation of rice (Oryza sativa L.) using gradient boosted regression in India. Remote Sensing, 13(12): 1-18. Bhatt, R. and Singh, P. 2021. Sugarcane response to irrigation and potassium levels in a soil testing low in available potassium. Agricultural Research Journal, 58(4): 709-715.

Bhatt, R., Majumder, D., Tiwari, A.K., Singh, S.R., Prasad, S. and Palanisamy, G. 2023. Climate smart technologies for improving sugarcane sustainability in India - A review. Sugar Tech, 25(1): 1-14. [https://doi.org/10.1007/s12355-022-01198-0].

Box, G.E. P., Jenkins, G.M., Reinsel, G.C. and Ljung, G.M. 2015. Time Series Analysis: Forecasting and Control (5th edn.). John Wiley & Sons Inc., New Jersey, USA.

Cowpertwait, P.S.P. and Metcalfe, A.V. 2009. Introductory Time Series with R (1st edn.). Springer. [https://doi.org/10.1007/978-0-387-88698-5].

Das, A., Kumar, M., Kushwaha, A., Dave, R., Dakhore, K.K., Chaudhari, K. and 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].

Dos Santos Luciano, A.C., Picoli, M.C.A., Duft, D.G., Rocha, J.V., Leal, M.R.L.V. and Le Maire, G. 2021. Empirical model for forecasting sugarcane yield on a local scale in Brazil using Landsat imagery and random forest algorithm. Computers and Electronics in Agriculture, 184: 106063. [DOI: 10.1016/j.compag.2021.106063].

Everingham, Y., Sexton, J., Skocaj, D. and Inman-Bamber, G. 2016. Accurate prediction of sugarcane yield using a random forest algorithm. Agronomy for Sustainable Development, 36: 27. [https://doi.org/10.1007/s13593-016-0364-z].

Filippi, P., Jones, E.J., Wimalathunge, N.S., Somarathna, P.D.S.N., Pozza, L.E., Ugbaje, S.U. and Bishop, T.F.A. 2019. An approach to forecast grain crop yield using multi-layered, multi-farm data sets and machine learning. Precision Agriculture, 20: 1015-1029.

Guruprasad, R.B., Saurav, K. and Randhawa, S. 2019. Machine learning methodologies for paddy yield estimation in India: A case study. pp. 7254-7257. In: IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium. Agricultural and Food Sciences, Computer Science Yokohama [https://doi.org/10.1109/igarss.2019.8900339].

Ilyas, Q.M., Ahmad, M. and Mehmood, A. 2023. Automated estimation of crop yield using artificial intelligence and remote sensing technologies. Bioengineering, 10: 125. [https://doi.org/10.3390/ bioengineering10020125].

India. NITI Aayog. 2020. Sugarcane and Sugar Industry: Final Report of the Task Force. Niti Aayog. [https://books.google.co.in/books?id=T3mWzgEACAAJ].

Jagtap, S.T., Phasinam, K., Kassanuk, T., Jha, S.S., Ghosh, T. and Thakar, C.M. 2022. Towards application of various machine learning techniques in agriculture. Materials Today Proceedings, 51: 793-797.

Khan, A.B.F., Kamalakannan, K. and Ahmed, N.S.S. 2023. Integrating machine learning and stochastic pattern analysis for the forecasting of time-series data. SN Computer Science, 4: 484. [https://doi.org/10.1007/s42979-023-01981-0].

Liu, S., Wang, X., Liu, M. and Zhu, J. 2017. Towards better analysis of machine learning models: A visual analytics perspective. Visual Informatics, 1(1): 48-56.

Lovesum, J. and Prince, B. 2023. A study on experimental analysis of best fit machine learning approach for smart agriculture. SN Computer Science, 4: 187. [https://doi.org/10.1007/s42979- 022-01612-0].

Mishra, P., Al Khatib, A.M.G., Sardar, I., Mohammed, J., Karakaya, K., Dash, A., Ray, M., Narsimhaiah, L. and Dubey, A. 2021. Modeling and forecasting of sugarcane production in India. Sugar Tech, 23(6): 1317-1324. [https://doi.org/10.1007/s12355-021-01004-3].

Mourão de Almeida, G., Pereira, G.T., Rabelo de Souza Bahia, A.S., Fernandes, K., Marques Júnior, J. 2021. Machine learning in the prediction of sugarcane production environments. Computers and Electronics in Agriculture, 190: 106452. [https://doi.org/10.1016/j.compag.2021.106452].

Neethi, M.V., Kiran, A.G. and Tiwari, H. 2023. Intelligent mango canopies yield estimation using machine vision. SN Computer Science, 4: 171. [https://doi.org/10.1007/s42979-022-01602-2]. Nihar, A., Patel, N.R., Pokhariyal, S. and Danodia, A. 2022. Sugarcane crop type discrimination and area mapping at field scale using Sentinel images and machine learning methods. Journal of the Indian Society of Remote Sensing, 50(2): 217-225.

NITI Aayog, India, 2020. Sugarcane and Sugar Industry: Final Report of the Task Force. Niti Aayog. Government of India, New Delhi [https://books.google.co.in/books?id=T3mWzgEACAAJ]. Pavani, S. and Augusta, S.B.P. 2023. Improved precision crop yield prediction using weighted-feature

hybrid SVM: Analysis of ML algorithms. IETE Journal of Research. [https://doi.org/ 10.1080/03772063.2023.2192000].

Prasad, N.R., Patel, N.R. and Danodia, A. 2021. Crop yield prediction in cotton for regional level using random forest approach. Spatial Information Research, 9(2): 195-206. Saini, P., Nagpal, B., Garg, P. and Kumar, S. 2023. CNN-BI-LSTM-CYP: A deep learning approach for sugarcane yield prediction. Sustainable Energy Technology and Assessments, 57: 103263. [https://doi.org/10.1016/j.seta.2023.103263].

Sneha, V. and Bhavana, V. 2023. Sugarcane yield and price prediction using forecasting models. pp. 1-6. In: 2023 International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent Engineering (ICECONF). [https://doi.org/10.1109/ICECONF57129.2023.10084094].

Vabalas, A., Gowen, E., Poliakoff, E. and Casson, A.J. 2019. Machine learning algorithm validation with a limited sample size. PLoS One, 14(11): e0224365. [https://doi.org/10.1371/journal.pone. 0224365].

Wilson, G.T. 2016. Time series analysis: Forecasting and control. Journal of Time Series Analysis, 37: [https://doi.org/10.1111/jtsa.12194].

Xing, L., Li, L., Gong, J., Ren, C., Liu, J. and Chen, H. 2018. Daily soil temperatures predictions for various climates in United States using data-driven model. Energy, 160: 430-440. Zhu, L., Liu, X., Wang, Z. and Tian, L. 2023. High-precision sugarcane yield prediction by integrating 10-m Sentinel-1 VOD and Sentinel-2 GRVI indexes. European Journal of Agronomy, 149: 126889. [https://doi.org/10.1016/j.eja.2023.126889].