A NEW method that is capable of accurately predicting droughts is now available.
This is the successful outcome of a research conducted by INTI International University Faculty of Engineering & Quantity Surveying senior lecturer Dr Md Munir Hayet Khan.
Together with two other researchers, Md Munir achieved the research objective of presenting a new hybrid technique known as the W-2A model.
“We combined the wavelet transform, the autoregressive integrated moving average (ARIMA), and the artificial neural network (ANN) to create the hybrid model to accurately predict droughts,” he said in a press release.
He added that the Standardised Precipitation Index (SPI) and the Standard Index of Annual Precipitation (SIAP) drought indices were used to compute historical drought events in the study.
Apart from providing a more robust drought prediction in a novel way, the model can be used for flood prediction since the drought indices are able to classify wet conditions of selected areas, the press release read.
In conducting the study to test the W-2A model’s ability to accurately predict droughts, the team analysed 30 years’ worth of rainfall data collected from rainfall stations located around the Langat River Basin in Selangor from 1986 to 2016.
Md Munir: Drought prediction has a key role in risk management, and drought readiness and alleviation.
Drought prediction, said Md Munir, is an important topic and has a key role in risk management, and drought readiness and alleviation.
“If we could provide accurate forecasts of meteorological droughts, it would allow the authorities and the public to plan and prepare for the dry conditions,” he added.
According to Md Munir, while various forecasting models had been developed over the years to predict droughts, the team’s latest research discovered that combining two or more separate models could be an effective approach to improving the accuracy of drought predictions.
In addition, it found that the wavelet-based hybrid ANN-ARIMA models offered better predictions and could be used for drought early warning systems.
Wavelet is a way to analyse time series data and can be used to see how different variables change over time.
The ANN is often used in drought forecasting because it can manage large amounts of data and can also model complex relationships between precipitation, temperature and other meteorological variables.
ARIMA models, on the other hand, are a type of statistical model commonly used in time series forecasting; they are particularly useful for modelling trends and patterns in historical data, and can also be used to account for the effects of seasonality and other cyclical patterns.
Md Munir said that in order to keep track of drought events, accurate indices and reliable hydrometeorological data are required, while adding that no single index can accurately depict the onset and severity of such an event.He also said there are different indices for different classes of droughts, namely, meteorological, hydrological, agricultural, and socio-economic, and each index has its limitations.
“The SPI is a well-known, globally accepted drought index which requires a parameter estimation. Meanwhile, the SIAP is quite simple and does not require parameter estimation,” he said.
“I believe that this new hybrid model can be used to help the agriculture sector and water resource management, and the authorities make the right decisions and planning for the long-term impact of drought,” he added.
