Improved Crop Yield Forecasting using Wavelet-Based Denoising and Artificial Neural Networks Framework
50 / 27
Authors
-
Md Yeasin
ICAR-Indian Agricultural Statistics Research Institute, New Delhi
-
Ranjit Kumar Paul
ICAR-Indian Agricultural Statistics Research Institute, New Delhi
-
Pushkar Bora
ICAR-Indian Agricultural Statistics Research Institute, New Delhi
-
Himadri Shekhar Roy
ICAR-Indian Agricultural Statistics Research Institute, New Delhi
-
Prakash Kumar
ICAR-Indian Agricultural Statistics Research Institute, New Delhi
-
A.K. Paul
ICAR-Indian Agricultural Statistics Research Institute, New Delhi
Keywords:
Hybrid model; Neural network; Pulse yield;Wavelets and volatility.Abstract
Agricultural crop yields are often non-stationary, noisy and influenced by multiple environmental factors, which limits the effectiveness of traditional
statistical models. Advanced hybrid approaches that can capture both linear and non-linear patterns, along with multi-scale characteristics, are required
for reliable forecasting. This study aimed to develop and evaluate a hybrid wavelet-based forecasting framework by integrating the Maximal Overlap
Discrete Wavelet Transform (MODWT) with Artificial Neural Network (ANN) and Autoregressive Integrated Moving Average (ARIMA) models
for predicting crop yield series of Total Pulses, Gram, and Tur in India. Annual yield data from 1950 to 2023 were analysed using a hybrid modelling
framework. The MODWT was applied to decompose the original time series into multi-resolution components, followed by denoising through
thresholding techniques. The decomposed components were then modelled using ANN and ARIMA. Optimal wavelet filters and decomposition
levels were obtained based on predictive performance. The results showed that hybrid wavelet-based models significantly outperformed standalone
ARIMA and ANN models. This study contributes to the literature by systematically optimizing wavelet filters and decomposition levels within a
hybrid modelling framework and demonstrates the effectiveness of combining wavelet-based denoising with machine learning and statistical models
for non-stationary agricultural time series data.
Downloads
References
Alhnaity, B., Kollias, S., Leontidis, G., Jiang, S., Schamp, B. and
Pearson, S. (2021). An autoencoder wavelet based deep neural
network with attention mechanism for multi-step prediction of
plant growth. Information Sciences, 560, 35-50
Anjoy, P., Paul, R.K., Sinha, K., Paul, A.K. and Ray, M. (2017). A hybrid
wavelet based neural networks model for predicting monthly WPI
of pulses in India. Indian Journal of Agricultural Sciences, 87(6),
834-839.
Bakulin, D.V., Beletskaya, N.V., Gorshkov, N.N., Djioeva, M.I.,
Mokhnatkina, U.S., Petrusevich, D.A. and Polyakov, A.A. (2025).
Hybrid Models of Time Series Using Wavelet Transform. Journal
of Communications Technology and Electronics, 70(7), 309-318
Burrus S., Gopinath R., and Guo H. (1998). Introduction to Wavelets
and Wavelet Transforms: A Primer. Recherche, 67.
Das, P., Jha, G.K., Lama, A., and Parsad, R. (2023). Crop yield
prediction using hybrid machine learning approach: a case study
of lentil (Lens culinaris Medik.). Agriculture, 13(3), 596.
Daubechies, I. (1992) Ten lectures on wavelets. Society for industrial
and applied mathematics.
Hounmenou, C.G., Gneyou, K.E. and Kakai, R.G. (2021). A Formalism
of the General Mathematical Expression of Multilayer Perceptron
Neural Networks.
Huang, W., Huang, Z., Matei, M. and Wang, T. (2012). Price volatility
forecast for agricultural commodity futures: the role of high
frequency data. Romanian Journal of Economic Forecasting.
Khosravi, S., Nikoo, M.R., Zamani, M.G., Barzegar, R., Najafipour, P.
and Gandomi, A.H., (2026). Enhancing long-term water quality
forecasting with a hybrid deep-learning approach integrating
MODWT, CNN, and GRU. Hydrological Sciences Journal, 71(2),
270-293.
Lindfield, G. and Penny, J. (2019). Analysing data using discrete
transforms. Numerical Methods, 383-431
Lionel, B.M., Musabe, R., Gatera, O. and Twizere, C., (2025). A
comparative study of machine learning models in predicting crop
yield. Discover Agriculture, 3(1),151.
Mila, F.A. and Parvin, M.T., (2019). Forecasting area, production and
yield of onion in Bangladesh by using ARIMA model. Asian
Journal of Agricultural Extension, Economics & Sociology,
37(4),1-12.
Mitra, D. and Paul, R.K. (2017). Hybrid time-series models for
forecasting agricultural commodity prices. Model Assisted
Statistics and Applications, 12,255–264
Musunuru, N., Yu, M. and Larson, A. (2013). Forecasting volatility
of returns for corn using GARCH Models. Texas Journal of
Agriculture and Natural Resources, 26:42-55.
148
Md Yeasin et al. / Journal of the Indian Society of Agricultural Statistics 135–148
Naik, R.T. (2025). Comparative Study of Wavelet–ANN and Wavelet
ARIMA Models for Groundwater Level Forecasting. International
Journal on Science and Technology, 16(4).
Oikonomidis, A., Catal, C. and Kassahun, A. (2022). Hybrid deep
learning-based models for crop yield prediction. Applied artificial
intelligence, 36(1), 2031822.
Paidipati, K. and Banik, A. (2020). Forecasting of rice cultivation
in India–a comparative analysis with ARIMA and LSTM-NN
models. EAI Endorsed Transactions on Scalable Information
Systems, 7(24).
Paul, R. K., Prajneshu, and Ghosh, H. (2009). GARCH Nonlinear Time
Series Analysis for Modeling and Forecasting of India’s Volatile
Spices Export Data. Journal of the Indian Society of Agricultural
Statistics, 63(2), 123-131.
Paul, R.K., Ghosh, H. and Prajneshu (2014). Development of out
of-sample forecast formulae for ARIMAX-GARCH model and
their application. Journal of the Indian Society of Agricultural
Statistics, 68(1), 85-92.
Paul, R.K., Paul, A.K., and Bhar, L.M. (2019). Wavelet-based
combination approach for modelling sub-divisional rainfall in
India. Theoretical and Applied Climatology, 139(3-4), 949-964.
Paul, R.K. and Garai, S. (2021). Performance comparison of wavelets
based machine learning technique for forecasting agricultural
commodity prices. Soft Computing, 25(20), 12857-12873
Paul, R.K. and Garai, S. (2022). Wavelets based artificial neural network
technique for forecasting agricultural prices. Journal of the Indian
Society for Probability and Statistics, 23(1), 47-61.
Paul, R.K., Garai, S., and Yeasin, M. (2025). Wavelet-SVR: A novel
wavelet-based support vector regression algorithm for time series
forecasting. International Journal of Agricultural Sustainability,
23(1), 1-18.
Paul, R.K., Yeasin, M. and Manjunatha, B. (2025). WaveDeepCrop:
wavelet enhanced deep learning framework for noise-resilient
crop yield forecasting. Proceedings of the Indian National Science
Academy, 91(4), 1310-1323.
Rakshit, D. and Paul, R.K. (2024). Hybrid ARFIMA-LRNN Model for
Forecasting Commodity Prices. Journal of the Indian Society of
Agricultural Statistics, 78(3), 221–229.
Rani M. (2025). Application of wavelet transform in agricultural
sciences. International Journal of Statistics and Applied
Mathematics,10(8), 33-36.
Shao, Z., Chao, F., Yang, S.L. and Zhou, K.L. (2017). A review of
the decomposition methodology for extracting and identifying
the fluctuation characteristics in electricity demand forecasting.
Renewable and Sustainable Energy Reviews, 75, 123-136.
Sharif, I. and Khare, S. (2014). Comparative analysis of Haar and
Daubechies wavelet for hyper spectral image classification. The
International Archives of the Photogrammetry, Remote Sensing
and Spatial Information Sciences, 40, 937-941.
Shawon, S.M., Ema, F.B., Mahi, A.K., Niha, F.L. and Zubair, H.T.
(2025). Crop yield prediction using machine learning: An
extensive and systematic literature review. Smart Agricultural
Technology, 10, 100718
Downloads
Submitted
Published
Issue
Section
How to Cite
