Long-term SPI drought forecasting in the Awash River Basin in Ethiopia using wavelet neural network and wavelet support vector regression models

Drought is a damaging natural hazard due to the lack of precipitation from the expected amount for a period of time. Mitigations are required to reduced its impact. Due to the difficulty in determining the onset and offset of droughts, accurate drought forecasting approaches are required for drought risk management. Given the growing use of machine learning in the field, Wavelet-Boosting Support Vector Regression (W-BS-SVR) was proposed for drought forecasting at Langat River Basin, Malaysia. Monthly rainfall, mean temperature and evapotranspiration for years 1976 - 2015 were used to compute Standardized Precipitation Evapotranspiration Index (SPEI) in this study, producing SPEI-1, SPEI-3 and SPEI-6. The 1-month lead time SPEIs forecasting capability of W-BS-SVR model was compared with the Support Vector Regression (SVR) and Boosting-Support Vector Regression (BS-SVR) models using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), coefficient of determination (R2) and Adjusted R2. The results demonstrated that W-BS-SVR provides higher accuracy for drought prediction in Langat River Basin.

Download Full-text

Drought forecasting using new machine learning methods / Prognozowanie suszy z wykorzystaniem automatycznych samouczących się metod

Journal of Water and Land Development ◽

10.2478/jwld-2013-0001 ◽

2013 ◽

Vol 18 (9) ◽

pp. 3-12 ◽

Cited By ~ 39

Author(s):

Anteneh Belayneh ◽

Jan Adamowski

Keyword(s):

Machine Learning ◽

River Basin ◽

Standardized Precipitation Index ◽

Machine Learning Techniques ◽

Support Vector ◽

Lead Times ◽

Drought Forecasting ◽

Awash River Basin ◽

Ann Models ◽

The Standardized Precipitation Index

Abstract In order to have effective agricultural production the impacts of drought must be mitigated. An important aspect of mitigating the impacts of drought is an effective method of forecasting future drought events. In this study, three methods of forecasting short-term drought for short lead times are explored in the Awash River Basin of Ethiopia. The Standardized Precipitation Index (SPI) was the drought index chosen to represent drought in the basin. The following machine learning techniques were explored in this study: artificial neural networks (ANNs), support vector regression (SVR), and coupled wavelet-ANNs, which pre-process input data using wavelet analysis (WA). The forecast results of all three methods were compared using two performance measures (RMSE and R2). The forecast results of this study indicate that the coupled wavelet neural network (WA-ANN) models were the most accurate models for forecasting SPI 3 (3-month SPI) and SPI 6 (6-month SPI) values over lead times of 1 and 3 months in the Awash River Basin in Ethiopia.

Download Full-text

Standard Precipitation Index Drought Forecasting Using Neural Networks, Wavelet Neural Networks, and Support Vector Regression

Applied Computational Intelligence and Soft Computing ◽

10.1155/2012/794061 ◽

2012 ◽

Vol 2012 ◽

pp. 1-13 ◽

Cited By ~ 50

Author(s):

A. Belayneh ◽

J. Adamowski

Keyword(s):

Neural Networks ◽

Support Vector Regression ◽

River Basin ◽

Precipitation Index ◽

Data Driven ◽

Support Vector ◽

Lead Times ◽

Wavelet Neural Networks ◽

Standard Precipitation Index ◽

Awash River Basin

Drought forecasts can be an effective tool for mitigating some of the more adverse consequences of drought. Data-driven models are suitable forecasting tools due to their rapid development times, as well as minimal information requirements compared to the information required for physically based models. This study compares the effectiveness of three data-driven models for forecasting drought conditions in the Awash River Basin of Ethiopia. The Standard Precipitation Index (SPI) is forecast and compared using artificial neural networks (ANNs), support vector regression (SVR), and wavelet neural networks (WN). SPI 3 and SPI 12 were the SPI values that were forecasted. These SPI values were forecast over lead times of 1 and 6 months. The performance of all the models was compared using RMSE, MAE, andR2. The forecast results indicate that the coupled wavelet neural network (WN) models were the best models for forecasting SPI values over multiple lead times in the Awash River Basin in Ethiopia.

Download Full-text

Optimal Kernel and Wavelet Coefficients to Support Vector Regression Model and Wavelet Neural Network for Time Series Rainfall Prediction

International Journal of Applied Evolutionary Computation ◽

10.4018/ijaec.2014100101 ◽

2014 ◽

Vol 5 (4) ◽

pp. 1-21

Author(s):

B. Kavitha Rani ◽

A. Govardhan

Keyword(s):

Neural Network ◽

Time Series ◽

Support Vector Regression ◽

Hybrid Model ◽

Wavelet Neural Network ◽

Natural Phenomenon ◽

Support Vector ◽

Wavelet Coefficients ◽

Rainfall Prediction ◽

Optimal Kernel

Rainfall prediction is an active topic recently since people want to make decisions about crop and irrigation cycles to understand weather and climate patterns. Due to need of predicting this natural phenomenon, various research works has been carried out previously with different type of techniques using historical data. In this paper, a hybrid model based on support vector regression (SVR) model and wavelet neural network (WNN) for rainfall prediction is proposed. In hybridized SVR-WNN, optimal kernel and wavelet coefficients are generated using hybrid algorithm. Here, artificial bee colony (ABC) and genetic algorithm (GA) are hybridized and used to this purpose. These optimal kernel functions and wavelet coefficients are supplied to hybrid model to predict the rainfall. In hybrid model, wavelet neural network with ARX modeling and support vector regression (SVR) model is effectively hybridized to time series rainfall prediction. The performance of the hybrid model is analyzed with the help of real datasets taken from Assam, Chhattisgarh, East Rajasthan, Gangetic West Bengal, Gujarath, Haryana, Telangana, Rajalaseema regions. From the results, it can be concluded that proposed rainfall prediction model have shown the MAPE performance of 20, the RMSE performance of 2, MAD performance of 12, but existing model show the MAPE performance of 61, the RMSE performance of 3, MAD performance of 27 for Telangana dataset.

Download Full-text