Abstract
Forecasting extreme hydrological events is critical for drought risk and efficient water resource management in semi-arid environments that are prone to natural hazards. This study aimed at forecasting drought conditions in a semi-arid region in north-eastern South Africa. The Standardized Precipitation Evaporation Index (SPEI) was used as a drought-quantifying parameter. Data for SPEI formulation for eight weather stations were obtained from South Africa Weather Services. Forecasting of the SPEI was achieved by using Generalized Additive Models (GAMs) at 1, 6, and 12 month timescales. Time series decomposition was done to reduce time series complexities, and variable selection was done using Lasso. Mild drought conditions were found to be more prevalent in the study area compared to other drought categories. Four models were developed to forecast drought in the Luvuvhu River Catchment (i.e., GAM, Ensemble Empirical Mode Decomposition (EEMD)-GAM, EEMD-Autoregressive Integrated Moving Average (ARIMA)-GAM, and Forecast Quantile Regression Averaging (fQRA)). At the first two timescales, fQRA forecasted the test data better than the other models, while GAMs were best at the 12 month timescale. Root Mean Square Error values of 0.0599, 0.2609, and 0.1809 were shown by fQRA and GAM at the 1, 6, and 12 month timescales, respectively. The study findings demonstrated the strength of GAMs in short- and medium-term drought forecasting.
Highlights
Rainfall variability is highly significant on several temporal and spatial scales in southern Africa [1,2,3,4], as most rural livelihoods in the region depend on agriculture, which is largely rainfed
The variability shows that Standardized Precipitation Evaporation Index (SPEI) 12 was found to be of greater severity compared to the one- and six-month timescales in the middle reaches, while, in the upper reaches, the 12 month timescale showed the least drought severity compared to the SPEI for one and six months
For medium-term forecasting, this study found that the treatment of a time series did slightly improve the forecast, but an undecomposed Generalized Additive Models (GAMs) showed better performance at this timescale
Summary
Rainfall variability is highly significant on several temporal and spatial scales in southern Africa [1,2,3,4], as most rural livelihoods in the region depend on agriculture, which is largely rainfed. Increasing trends of rainfall have been reported for a few locations over South Africa [5,6,7,8]. The authors of [9] cautioned that whilst this may suggest an increase in water resource availability, an increasing population and land use changes, coupled with intensification of agricultural activities, exert pressure on them. Rainfall trends have been predicted to decrease in the Luvuvhu River Catchment (LRC) in the northeast of South Africa, some stations exhibited increasing trends, which were potentially attributed to the 10 year decadal mean daily fluctuations [10]. The authors of [9] found an increasing trend of annual maximum temperatures in the Limpopo River Basin, which is consistent with several other land areas. Increased temperatures exacerbate drought characteristics (i.e., frequency, duration, and severity) [12], since there exists a positive linear relationship between increased temperature and evapotranspiration
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.