Meteorological drought analysis using data-driven models for the Lakes District,Turkey

Abstract

Droughts may be classified as meteorological, hydrological or agricultural. When meteorological drought appears in a region, agricultural and hydrological droughts follow. In this study, the standardized precipitation index (SPI) was applied for meteorological drought analysis at nine stations located around the Lakes District, Turkey. Analyses were performed on 3-, 6-, 9- and 12-month-long data sets. The SPI drought classifications were modelled by Adaptive Neural-Based Fuzzy Inference System (ANFIS) and Fuzzy Logic, which has the advantage that, in contrast to most of the time series modelling techniques, it does not require the model structure to be known a priori. Comparison of the observed values and the modelling results shows a better agreement with SPI-12 and ANFIS models than with fuzzy logic models.     

Hydrological time‐series modelling using an adaptive neuro‐fuzzy inference system

Accurate forecasting of hydrological time‐series is a quite important issue for a wise and sustainable use of water resources. In this study, an adaptive neuro‐fuzzy inference system (ANFIS) approach is used to construct a time‐series forecasting system. In particular, the applicability of an ANFIS to the forecasting of the time‐series is investigated. To illustrate the applicability and capability of an ANFIS, the River Great Menderes, located in western Turkey, is chosen as a case study area. The advantage of this method is that it uses the input–output data sets. A total of 5844 daily data sets collected from 1985 to 2000 are used for the time‐series forecasting. Models having various input structures were constructed and the best structure was investigated. In addition, four various training/testing data sets were built by cross‐validation methods and the best data set was obtained. The performance of the ANFIS models in training and testing sets was compared with observations and also evaluated. In order to get an accurate and reliable comparison, the best‐fit model structure was also trained and tested by artificial neural networks and traditional time‐series analysis techniques and the results compared. The results indicate that the ANFIS can be applied successfully and provide high accuracy and reliability for time‐series modelling. Copyright © 2007 John Wiley & Sons, Ltd.     

Probabilistic forecasting of drought: a hidden Markov model aggregated with the RCP 8.5 precipitation projection

The creeping characteristics of drought make it possible to mitigate drought’s effects with accurate forecasting models. Drought forecasts are inevitably plagued by uncertainties, making it necessary to derive forecasts in a probabilistic framework. In this study, we proposed a new probabilistic scheme to forecast droughts that used a discrete-time finite state-space hidden Markov model (HMM) aggregated with the Representative Concentration Pathway 8.5 (RCP) precipitation projection (HMM-RCP). The standardized precipitation index (SPI) with a 3-month time scale was employed to represent the drought status over the selected stations in South Korea. The new scheme used a reversible jump Markov chain Monte Carlo algorithm for inference on the model parameters and performed an RCP precipitation projection transformed SPI (RCP-SPI) weight-corrected post-processing for the HMM-based drought forecasting to perform a probabilistic forecast of SPI at the 3-month time scale that considered uncertainties. The point forecasts which were derived as the HMM-RCP forecast mean values, as measured by forecasting skill scores, were much more accurate than those from conventional models and a climatology reference model at various lead times. We also used probabilistic forecast verification and found that the HMM-RCP provided a probabilistic forecast with satisfactory evaluation for different drought categories, even at long lead times. In a drought event analysis, the HMM-RCP accurately predicted about 71.19 % of drought events during the validation period and forecasted the mean duration with an error of less than 1.8 months and a mean severity error of <0.57. The results showed that the HMM-RCP had good potential in probabilistic drought forecasting.     

The strategy of building a flood forecast model by neuro‐fuzzy network

A methodology is proposed for constructing a flood forecast model using the adaptive neuro‐fuzzy inference system (ANFIS). This is based on a self‐organizing rule‐base generator, a feedforward network, and fuzzy control arithmetic. Given the rainfall‐runoff patterns, ANFIS could systematically and effectively construct flood forecast models. The precipitation and flow data sets of the Choshui River in central Taiwan are analysed to identify the useful input variables and then the forecasting model can be self‐constructed through ANFIS. The analysis results suggest that the persistent effect and upstream flow information are the key effects for modelling the flood forecast, and the watershed's average rainfall provides further information and enhances the accuracy of the model performance. For the purpose of comparison, the commonly used back‐propagation neural network (BPNN) is also examined. The forecast results demonstrate that ANFIS is superior to the BPNN, and ANFIS can effectively and reliably construct an accurate flood forecast model. Copyright © 2005 John Wiley & Sons, Ltd.     

Monthly total sediment forecasting using adaptive neuro fuzzy inference system

Accurate forecasting of sediment is an important issue for reservoir design and water pollution control in rivers and reservoirs. In this study, an adaptive neuro-fuzzy inference system (ANFIS) approach is used to construct monthly sediment forecasting system. To illustrate the applicability of ANFIS method the Great Menderes basin is chosen as the study area. The models with various input structures are constructed for the purpose of identification of the best structure. The performance of the ANFIS models in training and testing sets are compared with the observed data. To get more accurate evaluation of the results ANFIS models, the best fit model structures are also tested by artificial neural networks (ANN) and multiple linear regression (MLR) methods. The results of three methods are compared, and it is observed that the ANFIS is preferable and can be applied successfully because it provides high accuracy and reliability for forecasting of monthly total sediment.     

Temporal trends and spatial characteristics of drought and rainfall in arid and semiarid regions of Iran

Drought, a normal recurrent event in arid and semiarid lands such as Iran, is typically of a temporary nature usually leaving little permanent aftermath. In the current study, the rainfall and drought severity time series were analyzed at 10 stations in the eastern half of Iran for the period 1966–2005. The drought severity was computed using the Standardized Precipitation Index (SPI) for a 12‐month timescale. The trend analyses of the data were also performed using the Kendall and Spearman tests. The results of this study showed that the rainfall and drought severity data had high variations to average values in the study period, and these variations increased with increasing aridity towards the south of the study area. The negative serial correlations found in the seasonal and annual rainfall time series were mostly insignificant. The trend tests detected a significant decreasing trend in the spring rainfall series of Birjand station at the rate of 8.56 mm per season per decade and a significant increasing trend in the summer rainfall series of Torbateheydarieh station at the rate of 0.14 mm per season per decade, whereas the rest of the trends were insignificant. Furthermore, the 12‐month values of the standardized precipitation index decreased at all the stations except Zabol during the past four decades. During the study period, all of the stations experienced at least one extreme drought which mainly occurred in the winter season. Copyright © 2011 John Wiley & Sons, Ltd.     

Multiple linear regression,multi-layer perceptron network and adaptive neuro-fuzzy inference system for forecasting precipitation based on large-scale climate signals

ABSTRACT

Nowadays, mathematical models are widely used to predict climate processes, but little has been done to compare the models. In this study, multiple linear regression (MLR), multi-layer perceptron (MLP) network and adaptive neuro-fuzzy inference system (ANFIS) models were compared for precipitation forecasting. The large-scale climate signals were considered as inputs to the applied models. After selecting the most effective climate indices, the effects of large-scale climate signals on the seasonal standardized precipitation index (SPI) of the Maharlu-Bakhtaran catchment, Iran, simultaneously and with a delay, was analysed using a cross-correlation function. Hence, the SPI time series was forecasted up to four time intervals using MLR, MLP and ANFIS. The results showed that most of the indices were significant with SPI of different lag times. Comparison of the SPI forecast results by MLR, MLP and ANFIS models showed better performance for the MLP network than the other two models (RMSE = 0.86, MAE = 0.74 for the first step ahead of SPI forecasting).

Editor D. Koutsoyiannis; Associate editor F. Pappenberger     

Multi-models for SPI drought forecasting in the north of Haihe River Basin,China

Drought is one of the most devastating climate disasters. Hence, drought forecasting plays an important role in mitigating some of the adverse effects of drought. Data-driven models are widely used for drought forecasting such as ARIMA model, artificial neural network (ANN) model, wavelet neural network (WANN) model, support vector regression model, grey model and so on. Three data-driven models (ARIMA model; ANN model; WANN model) are used in this study for drought forecasting based on standard precipitation index of two time scales (SPI; SPI-6 and SPI-12). The optimal data-driven model and time scale of SPI are then selected for effective drought forecasting in the North of Haihe River Basin. The effectiveness of the three data-models is compared by Kolmogorov–Smirnov (K–S) test, Kendall rank correlation, and the correlation coefficients (R²). The forecast results shows that the WANN model is more suitable and effective for forecasting SPI-6 and SPI-12 values in the north of Haihe River Basin.     

Application of linear stochastic models for drought forecasting in the Büyük Menderes river basin, western Turkey

In the present study, a seasonal and non-seasonal prediction of the Standardized Precipitation Index (SPI) time series is addressed by means of linear stochastic models. The methodology presented here is to develop adequate linear stochastic models known as autoregressive integrated moving average (ARIMA) and multiplicative seasonal autoregressive integrated moving average (SARIMA) to predict drought in the Büyük Menderes river basin using SPI as drought index. Temporal characteristics of droughts based on SPI as an indicator of drought severity indicate that the basin is affected by severe and more or less prolonged periods of drought from 1975 to 2006. Therefore, drought prediction plays an important role for water resources management. ARIMA modeling approach involves the following three steps: model identification, parameter estimation, diagnostic checking. In model identification step, considering the autocorrelation function (ACF) and partial autocorrelation function (PACF) results of the SPI series, different ARIMA models are identified. The model gives the minimum Akaike Information Criterion (AIC) and Schwarz Bayesian Criterion (SBC) is selected as the best fit model. Parameter estimation step indicates that the estimated model parameters are significantly different from zero. Diagnostic check step is applied to the residuals of the selected ARIMA models and the results indicated that the residuals are independent, normally distributed and homoscedastic. For the model validation purposes, the predicted results using the best ARIMA models are compared to the observed data. The predicted data show reasonably good agreement with the actual data. The ARIMA models developed to predict drought found to give acceptable results up to 2 months ahead. The stochastic models developed for the Büyük Menderes river basin can be employed to predict droughts up to 2 months of lead time with reasonably accuracy.     

Adaptive neural-based fuzzy inference system (ANFIS) approach for modelling hydrological time series

Abstract

The main aim of this study is to develop a flow prediction method, based on the adaptive neural-based fuzzy inference system (ANFIS) coupled with stochastic hydrological models. An ANFIS methodology is applied to river flow prediction in Dim Stream in the southern part of Turkey. Application is given for hydrological time series modelling. Synthetic series, generated through autoregressinve moving-average (ARMA) models, are then used for training data sets of the ANFIS. It is seen that the extension of input and output data sets in the training stage improves the accuracy of forecasting by using ANFIS.     

Adaptive neuro-fuzzy inference system for prediction of water level in reservoir

Accurate prediction of the water level in a reservoir is crucial to optimizing the management of water resources. A neuro-fuzzy hybrid approach was used to construct a water level forecasting system during flood periods. In particular, we used the adaptive network-based fuzzy inference system (ANFIS) to build a prediction model for reservoir management. To illustrate the applicability and capability of the ANFIS, the Shihmen reservoir, Taiwan, was used as a case study. A large number (132) of typhoon and heavy rainfall events with 8640 hourly data sets collected in past 31 years were used. To investigate whether this neuro-fuzzy model can be cleverer (accurate) if human knowledge, i.e. current reservoir operation outflow, is provided, we developed two ANFIS models: one with human decision as input, another without. The results demonstrate that the ANFIS can be applied successfully and provide high accuracy and reliability for reservoir water level forecasting in the next three hours. Furthermore, the model with human decision as input variable has consistently superior performance with regard to all used indexes than the model without this input.     

Seasonal drought predictability in Portugal using statistical–dynamical techniques

Atmospheric forecasting and predictability are important to promote adaption and mitigation measures in order to minimize drought impacts. This study estimates hybrid (statistical–dynamical) long-range forecasts of the regional drought index SPI (3-months) over homogeneous regions from mainland Portugal, based on forecasts from the UKMO operational forecasting system, with lead-times up to 6 months. ERA-Interim reanalysis data is used for the purpose of building a set of SPI predictors integrating recent past information prior to the forecast launching. Then, the advantage of combining predictors with both dynamical and statistical background in the prediction of drought conditions at different lags is evaluated. A two-step hybridization procedure is performed, in which both forecasted and observed 500 hPa geopotential height fields are subjected to a PCA in order to use forecasted PCs and persistent PCs as predictors. A second hybridization step consists on a statistical/hybrid downscaling to the regional SPI, based on regression techniques, after the pre-selection of the statistically significant predictors. The SPI forecasts and the added value of combining dynamical and statistical methods are evaluated in cross-validation mode, using the R² and binary event scores. Results are obtained for the four seasons and it was found that winter is the most predictable season, and that most of the predictive power is on the large-scale fields from past observations. The hybridization improves the downscaling based on the forecasted PCs, since they provide complementary information (though modest) beyond that of persistent PCs. These findings provide clues about the predictability of the SPI, particularly in Portugal, and may contribute to the predictability of crops yields and to some guidance on users (such as farmers) decision making process.     

Forecasting effective drought index using a wavelet extreme learning machine (W-ELM) model

A drought forecasting model is a practical tool for drought-risk management. Drought models are used to forecast drought indices (DIs) that quantify drought by its onset, termination, and subsequent properties such as the severity, duration, and peak intensity in order to monitor and evaluate the impacts of future drought. In this study, a wavelet-based drought model using the extreme learning machine (W-ELM) algorithm where the input data are first screened through the wavelet pre-processing technique for better accuracy is developed to forecast the monthly effective DI (EDI). The EDI is an intensive index that considers water accumulation with a weighting function applied to rainfall data with the passage of time in order to analyze the drought-risk. Determined by the autocorrelation function (ACF) and partial ACFs, the lagged EDI signals for the current and past months are used as significant inputs for 1 month lead-time EDI forecasting. For drought model development, 97 years of data for three hydrological stations (Bathurst Agricultural, Wilsons Promontory and Merredin in Australia) are partitioned in approximately 90:5:5 ratios for training, cross-validation and test purposes, respectively. The discrete wavelet transformation (DWT) is applied to the predictor datasets to decompose inputs into their time–frequency components that capture important information on periodicities. DWT sub-series are used to develop new EDI sub-series as inputs for the W-ELM model. The forecasting capability of W-ELM is benchmarked with ELM, artificial neural network (ANN), least squares support vector regression (LSSVR) and their wavelet-equivalent (W-ANN, W-LSSVR) models. Statistical metrics based on agreement between the forecasted and observed EDI, including the coefficient of determination, Willmott’s index, Nash–Sutcliffe coefficient, percentage peak deviation, root-mean-square error, mean absolute error, and model execution time are used to assess the effectiveness of the models. The results demonstrate enhanced forecast skill of the drought models that use wavelet pre-processing of the predictor dataset. Based on statistical measures, W-ELM outperformed traditional ELM, LSSVR, ANN and their wavelet-equivalent counterparts (W-ANN, W-LSSVR). It is found that the W-ELM model is computationally efficient as shown by a faster running time with the majority of forecasting errors in lower frequency bands. The results demonstrate the usefulness of W-ELM over W-ANN and W-LSSVR models and the benefits of wavelet transformation of input data to improve the performance of drought forecasting models.     

Ensemble prediction of regional droughts using climate inputs and the SVM–copula approach

In this study, the climate teleconnections with meteorological droughts are analysed and used to develop ensemble drought prediction models using a support vector machine (SVM)–copula approach over Western Rajasthan (India). The meteorological droughts are identified using the Standardized Precipitation Index (SPI). In the analysis of large‐scale climate forcing represented by climate indices such as El Niño Southern Oscillation, Indian Ocean Dipole Mode and Atlantic Multidecadal Oscillation on regional droughts, it is found that regional droughts exhibits interannual as well as interdecadal variability. On the basis of potential teleconnections between regional droughts and climate indices, SPI‐based drought forecasting models are developed with up to 3 months' lead time. As traditional statistical forecast models are unable to capture nonlinearity and nonstationarity associated with drought forecasts, a machine learning technique, namely, support vector regression (SVR), is adopted to forecast the drought index, and the copula method is used to model the joint distribution of observed and predicted drought index. The copula‐based conditional distribution of an observed drought index conditioned on predicted drought index is utilized to simulate ensembles of drought forecasts. Two variants of drought forecast models are developed, namely a single model for all the periods in a year and separate models for each of the four seasons in a year. The performance of developed models is validated for predicting drought time series for 10 years' data. Improvement in ensemble prediction of drought indices is observed for combined seasonal model over the single model without seasonal partitions. The results show that the proposed SVM–copula approach improves the drought prediction capability and provides estimation of uncertainty associated with drought predictions. Copyright © 2013 John Wiley & Sons, Ltd.     

The spatial–temporal variation of dry and wet periods in Iran based on comparing SPI and RDI indices

Drought is a natural hazard which can cause harmful effects on water resources. To monitor drought, the use of an indicator and determination of wet and dry period trend seem to have an important role in quantifying the drought analysis. In this paper, in addition to the comparison of Reconnaissance Drought Index (RDI) and Standardized Precipitation Index (SPI), based on the most appropriate probability distribution function, it was tried to examine the trends of dry and wet periods based on the mentioned indices. Accordingly, the meteorological data of 30 synoptic stations in Iran (1960–2014) was used and the trend was analyzed using the Mann–Kendall test by eliminating the effect of any significant autocorrelation coefficients at 95% confidence level (modified Mann–Kendall). Comparing results between the time series of RDI and SPI drought indices based on statistical indicators (RMSE?<?0.434, R²?>?0.819 and T-statistic?<?0.419) in all studied stations revealed that the behavior of the two indices was roughly the same and the difference between them was not significant. The trend analysis results of RDI and SPI indices based on modified Mann–Kendall test showed that the variation of dry and wet periods was decreasing in most of the studied stations (five cases were significant). In addition, the results of the trend line slope of dry and wet periods related to the drought indices in the studied area indicated that the slope was negative for SPI and RDI indices in 70% and 50% of stations, respectively.     

Assessing homogeneous regions relative to drought class transitions using an ANOVA-like inference. Application to Alentejo, Portugal

In the present study, an ANOVA-like inference technique is used aiming at to assess if Alentejo, southern Portugal, could be considered a homogeneous region for drought management purposes. First, Alentejo was divided into four sub-regions according to latitude (north and south), and longitude (west and east). Inside each sub-region, 10 weather stations were considered. The time series of the Standardized Precipitation Index (SPI) were obtained for these stations using precipitation data for the period 1932–1999 (67 years). Contingency tables for the transitions between SPI drought classes were obtained for these time series. Loglinear models were fitted to these contingency tables to estimate the probabilities for drought class transitions. An ANOVA-like inference was applied considering the four sub-regions like treatments of a two way layout with two factors, latitude and longitude, each one with two levels, north and south, and west and east respectively. The weather stations of each sub-region were treated as replicates. Significant differences between west and east were found, that allowed to consider that Alentejo could be composed by two sub-regions.     

The survey of climatic drought trend in Iran

Drought is one of the most important natural hazards in Iran. Therefore, drought monitoring has become a point of concern for most of the researchers. In the present study, the changes and trend of drought was surveyed, under the current global climate changes, by non parametric Mann–Kendall statistical test for 42 synoptic stations at different places of Iran. Standardized Precipitation Index (SPI) was calculated to recognize the drought condition at different time scales (3, 6, 9, 12, 18 and 24 months’ time series) for analyzing the drought trend in the recent 30 years. The obtained results have indicated a significant negative trend of drought in many parts of Iran, especially the South-East, West and South-West regions of the country. According to the results, although some parts of Iran such as North (around the Caspian Sea) and Northeast show no significant trend but in other parts of country, the severity of drought has increased during the last 30 years.     

Hybrid denoising-jittering data pre-processing approach to enhance multi-step-ahead rainfall–runoff modeling

Successful modeling of stochastic hydro-environmental processes widely relies on quantity and quality of accessible data and noisy data might effect on the functioning of the modeling. On the other hand in training phase of any Artificial Intelligence based model, each training data set is usually a limited sample of possible patterns of the process and hence, might not show the behavior of whole population. Accordingly in the present article first, wavelet-based denoising method was used in order to smooth hydrological time series and then small normally distributed noises with the mean of zero and various standard deviations were generated and added to the smoothed time series to form different denoised-jittered training data sets, for Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) modeling of daily and multi-step-ahead rainfall–runoff process of the Milledgeville station of the Oconee River and the Pole Saheb station of the Jighatu River watersheds, respectively located in USA and Iran. The proposed hybrid data pre-processing approach in the present study is used for the first time in modeling of time series and especially in modeling of hydrological processes. Furthermore, the impacts of denoising (smoothing) and noise injection (jittering) have been simultaneously investigated neither in hydrology nor in any other engineering fields. To evaluate the modeling performance, the outcomes were compared with the results of multi linear regression and Auto Regressive Integrated Moving Average models. Comparing the achieved results via the trained ANN and ANFIS models using denoised-jittered data showed that the proposed data pre-processing approach which serves both denoising and jittering techniques could improve performance of the ANN and ANFIS based single-step-ahead rainfall–runoff modeling of the Milledgeville station up to 14 and 12% and of the Pole Saheb station up to 22 and 16% in the verification phase. Also the results of multi-step-ahead modeling using the proposed data pre-processing approach showed improvement of modeling for both watersheds.     

One-minute rain rate distribution in Nigeria derived from TRMM satellite data

Data from the Tropical Rainfall Measuring Mission (TRMM) satellite sensors, the Microwave Imager (TMI, 3A12 V6) and other satellite sources (3B43 V6) have been used to derive the thunderstorm ratio β, total rain accumulation M, and 1-min rainfall rates, R1min, for 37 stations in Nigeria, for 0.001–1% of an average year, for the period 1998–2006. Results of the rain accumulations from the TRMM satellite (1998–2006) were compared with the data collected from 14 ground stations in Nigeria for the period 1991–2000. The two data sets are reasonably positively correlated, with correlation coefficients varying from 0.64 to 0.99. Deduced 1-min rainfall rates compared fairly well with the previous ground data of Ajayi and Ezekpo (1988. Development of climatic maps of rainfall rate and attenuation for microwave applications in Nigeria. The Nigerian Engineering 23(4), 13–30) with correlation coefficients varying from 0.17 to 0.97 in all 37 stations. The agreement was much better when compared with the International Telecommunications Union Radio communication Study group 3 digital maps with correlation coefficients varying from 0.84 to 0.98 in 23 locations; however there were negative correlation coefficient (of 0.2 in 7 stations) in the Middle Belt and a weak positive coefficient (of 0.09 in 6 stations) in the South South. Regionally the inferred mean annual 1-min rainfall rates are the highest in the South-East region with values between 111 and 125 mm/h throughout the 9 years, followed by the South-South region (105–124 mm/h). The lowest rainfall rate and rainfall accumulation occur in the North-West region (60–86 mm/h) followed, in ascending order, by the North-East (66–95 mm/h) region, the Middle-Belt region (76–102 mm/h) and the South-West region (77–110 mm/h). The present results were also compared with 9 tropical stations around the world and there was positive correlation between the results. The present results will be very useful for satellite rain attenuation modeling in the tropics and subtropical stations around the world.It is useful to note that one country, particularly one as large as Nigeria, can have significant variations in its rainfall characteristics for a variety of reasons, and this is borne out by the results presented.     

Evaluation of multi-sensor satellite data for monitoring different drought impacts

Drought is a natural disaster that significantly affects human life; therefore, precise monitoring and prediction is necessary to minimize drought damage. Conventional drought monitoring is based predominantly on ground observation stations; however, satellite imagery can be used to overcome the disadvantages of existing monitoring methods and has the advantage of monitoring wide areas. In this research, we assess the applicability of drought monitoring based on satellite imagery, focusing on historic droughts in 2001 and 2014, which caused major agricultural and hydrological issues in South Korea. To assess the applicability and accuracy of the drought index, drought impact areas in the study years were investigated, and spatiotemporal comparative analyses between the calculated drought index and previously affected areas were conducted. For drought monitoring based on satellite imagery, we used hydro-meteorological factors such as precipitation, land surface temperature, vegetation, and evapotranspiration, and applied remote sensing data from various sensors. We verified the effectiveness of using precipitation data for meteorological drought monitoring, vegetation and land surface temperature data for agricultural drought monitoring, and evapotranspiration data for hydrological drought monitoring. Moreover, we confirmed that the Standard Precipitation Index (SPI) can be indirectly applied to agricultural or hydrological drought monitoring by determining the temporal correlation between SPI, calculated for various time scales, and satellite-based drought indices.