Comparative Analysis of Machine Learning Models for Prediction of Reference Evapotranspiration

XVII International Conference on Systems, Automatic Control and Measurements, SAUM 2024 (pp. 165-168)

АУТОР(И) / AUTHOR(S): Miljana Milić , Miljan Jeremić, Jelena Milojković , Duško Lukač

Download Full Pdf  

DOI:  10.46793/SAUM24.165M

САЖЕТАК / ABSTRACT:

Research described in this paper gives a comparative analysis of two different machine learning models, notably RNN (Recurrent Neural Network) and SARIMA (Seasonal Auto Regressive Integrated Moving Average), in order to determine the most effective tool for predicting reference evapotranspiration (ET0) in a specific scenario. The study uses historical evapotranspiration data collected over an extended timeframe. To quantify the accuracy and reliability of the forecasts, metrics like Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) are employed. Through this analysis, the study highlights the strengths and weaknesses of both SARIMA and RNN models, which are useful tools in the field of environmental science.

КЉУЧНЕ РЕЧИ / KEYWORDS:

recurrent neural networks, seasonal auto regressive integrated moving average modelling, reference evapotranspiration, prediction, accuracy

ПРОЈЕКАТ/ ACKNOWLEDGEMENT:

This work has been supported by the Ministry of Education, Science and Technological Development of the Republic of Serbia.

ЛИТЕРАТУРА / REFERENCES

  1. Hu, Z., Bashir, R.N., Rehman, A.U., Iqbal, S.I., Shahid, M.M.A. and Xu, T., “Machine learning based prediction of reference evapotranspiration (ET 0) using iot”. IEEE Access, vol.10, pp.70526-70540, 2022.
  2. Milić, M., Jeremić, M., Milojković, J., Stanojlović Mirković, M., „Prediction of Reference EvapotranspirationUsing Neural Networks, 11th International Conference on Electrical, Electronics and Computer Engineering (IcETRAN)“, Nis, 3-6 June, 2024.
  3. Sattari, M.T., Apaydin, H., Band, S.S., Mosavi, A. and Prasad, R., “Comparative analysis of kernel-based versus ANN and deep learning methods in monthly reference evapotranspiration estimation”. Hydrology and Earth System Sciences, Vol. 25, No. 2, pp.603-618, 2021.
  4. Trajkovic, S., Todorovic, B., Stankovic, M., ”Forecasting of Reference Evapotranspiration by Artificial Neural Networks”, J. Irrig. Drain. Eng., Vol. 129, pp. 454–457, 2003.
  5. Kalyan, B., Reddy, S.P., Kumari, K.K. and Jain, M., “Comparative Analysis of Stock Price Prediction Accuracy: A Machine Learning Approach with ARIMA, LSTM, And Random Forest Models”. International Research Journal on Advanced Engineering Hub (IRJAEH), vol. 2, No. 05, pp.1141-1151, 2024.
  6. Kulkarni, M.A., Patil, S., Rama, G.V. and Sen, P.N., “Wind speed prediction using statistical regression and neural network”. Journal of Earth System Science, vol. 117, pp.457-463, 2008.
  7. Raschka, S. and Mirjalili, V., 2019. Python machine learning: Machine learning and deep learning with Python, scikit-learn, and TensorFlow 2. Packt publishing ltd.
  8. Jeremić, M., Milić, M., Milojković, J. and Gocić, M., “Development of geo-da based android application for spatial and statistical analysis of Serbian long-term precipitation data”. Facta Universitatis, Series: Automatic Control and Robotics, vol. 1, No. 3, pp.131-145, 2022.
  9. Nokeri, T.C., 2021. Forecasting using arima, sarima, and the additive model. In Implementing Machine Learning for Finance: A Systematic Approach to Predictive Risk and Performance Analysis for Investment Portfolios (pp. 21-50). Berkeley, CA: Apress.
  10. Dabral, P.P. and Murry, M.Z., Modelling and forecasting of rainfall time series using SARIMA. Environmental Processes, vol. 4, No. 2, pp.399-419, 2017.
  11. Rami, K., Rajput, A., Shripathi, N., Patel, J. and Patel, R., 2024. Comparative Analysis of ML Models for Currency Exchange Rate Prediction.