Standardized Precipitation Index Series Research Articles

Evaluation of Drought in the Ken River Basin in Bundelkhand Region, India

The present study exhibits the analyses of the meteorological drought events in the Ken Basin using various indices viz., Standardized Precipitation Index (SPI) for different time-scale and Rainfall Departure (RD) method. Precipitation data from 1990 to 2020 for six districts falling in the basin have been used to compute SPI and RD values. The computation of SPI series has been carried out for 1-month, 3-month, 6-month, 9-month and 12-month time-scales. The analysis indicated that the most parts of the basin experienced drought events in the years 2007, 2015 and 2017 region during the years. However, the basin was affected partially in the other drought years. The maximum severity of drought has been recorded as -65% and -52% in the year 1997 in Mahoba and Banda districts respectively. However, the up-reach parts of the basin were not affected in the year 1997. The comparative analysis of RD and SPI exhibited a good correlation with 3-month and 6-month SPI time steps. It is found that the SPI-3 identifies the meteorological drought event appropriately followed by SPI-6.

Enhancing drought prediction precision with EEMD-ARIMA modeling based on standardized precipitation index.

This study introduces ensemble empirical mode decomposition (EEMD) coupled with the autoregressive integrated moving average (ARIMA) model for drought prediction. In the realm of drought forecasting, we assess the EEMD-ARIMA model against the traditional ARIMA approach, using monthly precipitation data from January 1970 to December 2019 in Herat province, Afghanistan. Our evaluation spans various timescales of standardized precipitation index (SPI) 3, SPI 6, SPI 9, and SPI 12. Statistical indicators like root-mean-square error, mean absolute error (MAE), mean absolute percentage error (MAPE), and R2 are employed. To comprehend data features thoroughly, each SPI series initially computed from the original monthly precipitation time series. Subsequently, each SPI undergoes decomposition using EEMD, resulting in intrinsic mode functions (IMFs) and one residual series. The next step involves forecasting each IMF component and residual using the corresponding ARIMA model. To create an ensemble forecast for the initial SPI series, the predicted outcomes of the modeled IMFs and residual series are finally added. Results indicate that EEMD-ARIMA significantly enhances drought forecasting accuracy compared to conventional ARIMA model.

Standardized Precipitation Index for Metrological Drought Analysis In Kashmir Valley Of Jammu And Kashmir

Abstract: The term "drought" is multifaceted, with varying interpretations based on personal experiences. It is a natural disaster that is distinguished by a severe and ongoing precipitation deficit. The planning and management of freshwater resources as well as the forecasting of the arrival and intensity of droughts depend heavily on drought monitoring. A number of indices have been put forth over time to track and measure data related to droughts. The Standardized Precipitation index (SPI), which is based on the idea of probability, is the most commonly used index. The current study examines the possibility of analysing the temporal pattern and severity of drought in the Kashmir Valley (Jammu and Kashmir) using precipitation-based SPI. Utilizing the "DrinC" software application, the Indices were calculated. SPI values were calculated using monthly precipitation data for the IMD Srinagar 2003 to 2022. SPI series computations were carried out for short, moderate, and long time scales. Based on the data, the Kashmir region experienced four periods of moderate drought in the years 2007, 2009, 2012, and 2016. Additionally, there was no significant drought from 2003 to 2022. 2007 had the maximum intensity with an SPI value of -1.37 for a moderate drought.

Multifractal analysis of standardized precipitation index in Northeast Brazil

Northeast Brazil (NEB) is one of the world's most densely populous dryland regions most vulnerable to the impacts of climate change. It is expected that the risk of natural disasters related to excess or lack of water (flash floods and severe droughts) will continue increasing in the region until the end of the century. In this work, we study multifractal properties of the Standardized precipitation index (SPI) which is commonly used to evaluate the degree of severity of drought and humid conditions at different time scales and can be compared among regions with distinct climatic conditions. The method Multifractal detrended fluctuation analysis (MFDFA) is used to analyze SPI for 1, 3, 6, and 12-month accumulation periods at 133 locations across the state of Pernambuco, with climate varying from tropical humid in the coastal area to semiarid in the deep inland region. The results show that all SPI series (independently of time scale and climatic conditions) display multifractal dynamics, which can be described by properties of the multifractal spectrum. It was found that SPI series exhibit long-term persistence and multifractality that becomes stronger as accumulation time increases. For all temporal scales, the values of Hurst exponent increase in the west-east direction indicating stronger persistence of dry/wet conditions in the coastal region Zona da Mata, with a tropical humid climate, than in the dry semiarid inland Sertão region. For SPI-1, SPI-3, and SPI-6 which describe short and medium conditions the width of the multifractal spectrum (degree of multifractality) doesn't vary across the studied area, while for SPI-12 which describes long-term conditions the width of the multifractal spectrum decreases in a west-east direction, indicating stronger multifractality and higher complexity in long duration precipitation anomalies in the semiarid Sertão region.

Modeling Various Drought Time Scales via a Merged Artificial Neural Network with a Firefly Algorithm

Drought monitoring and prediction have important roles in various aspects of hydrological studies. In the current research, the standardized precipitation index (SPI) was monitored and predicted in Peru between 1990 and 2015. The current study proposed a hybrid model, called ANN-FA, for SPI prediction in various time scales (SPI3, SPI6, SPI18, and SPI24). A state-of-the-art firefly algorithm (FA) has been documented as a powerful tool to support hydrological modeling issues. The ANN-FA uses an artificial neural network (ANN) which is coupled with FA for Lima SPI prediction via other stations. Through the intelligent utilization of SPI series from neighbors’ stations as model inputs, the suggested approach might be used to forecast SPI at various time scales in a meteorological station with insufficient data. To conduct this, the SPI3, SPI6, SPI18, and SPI24 were modeled in Lima meteorological station using other meteorological stations’ datasets in Peru. Various error criteria were employed to investigate the performance of the ANN-FA model. Results showed that the ANN-FA is an effective and promising approach for drought prediction and also a multi-station strategy is an effective strategy for SPI prediction in the meteorological station with a lack of data. The results of the current study showed that the ANN-FA approach can help to predict drought with the mean absolute error = 0.22, root mean square error = 0.29, the Pearson correlation coefficient = 0.94, and index of agreement = 0.97 at the testing phase of best estimation (SPI3).

Oceanic and terrestrial origin of precipitation over 50 major world river basins: Implications for the occurrence of drought

The terrestrial and oceanic origins of precipitation over 50 major river basins worldwide were investigated for the period 1980–2018. For this purpose, we used a Lagrangian approximation that calculates the humidity that results in precipitation from the entire ocean area (ocean component of the precipitation, PLO) and the entire land area (land component, PLT) as well as the sum of both components (Lagrangian precipitation, PL). PL and its components were highly correlated with precipitation over the basins, where PLT accounted for >50 % of the PL in most of them. This confirmed the importance assigned by previous studies to terrestrial recycling of precipitation and moisture transport within the continents. However, the amount of PLO in almost all North American river basins was highlighted. The assessment of drought conditions through the Standardized Precipitation Index (SPI) at a temporal scale of 1- and 3-months revealed the number of drought episodes that affected each river basin, especially the Amazon, Congo, and Nile, because of the lower number of episodes but higher average severity and duration. A direct relationship between the severity of drought episodes and the respective severity computed on the oceanic and terrestrial SPI series was also found for the majority of basins. This highlights the influence of the severity of the SPI of oceanic origin for most basins in North America. However, for certain basins, we found an inverse relationship between the severity of drought and the associated severity according to the SPI of oceanic or terrestrial origin, thus highlighting the principal drought attribution. Additionally, a copula analysis provided new information that illustrates the estimated conditional probability of drought for each river basin in relation to the occurrence of drought conditions of oceanic or terrestrial origin, which revealed the possible main driver of drought severity in each river basin.

Assessment of drought trends and variabilities over the agriculture-dominated Marathwada Region, India.

Drought is considered among the most perilous events with catastrophic consequences, particularly from the agro-economic point of view. These consequences are expected to exacerbate under the increasing meteorological aberrations due to changing climate, which necessitates investigating drought variabilities. This study presents a thorough spatiotemporal assessment of drought trends and variabilities over the agriculture-dominated Marathwada Region, Maharashtra, India. The precipitation data is extracted from the India Meteorological Department (IMD) gridded product, whereas actual evapotranspiration (ET) and Evaporative Stress Index (ESI) are obtained from Global Land Evaporation Amsterdam Model (GLEAM) datasets. Standardized Precipitation Index (SPI) is used to characterize drought occurrences at multiple time frames, whereas non-parametric tests, i.e., modified Mann-Kendall (MMK) and Sen's slope (SS) tests, are employed to detect trends. The results reveal the region to be prone to droughts, and SPI at a longer time frame (i.e., 12-monthly moving frame) can capture drought occurrences better than the shorter time frames, which can be attributed to the lesser randomness in the time series in the longer frame. A mix of positive/negative trends of SPI series are found for the monsoonal months; however, they are relatively more concentrated towards negative ZMMK. Hence, the Marathwada Region can be inferred to have exhibited a relatively increased tendency towards drought occurrences. The seasonal differences in mean values and trends of rainfall, ET, and ESI are discussed in detail. Since the Marathwada Region has a monsoon-dominated climate with high agricultural importance, the information reported in this study will help in devising water management strategies to minimize the repercussions of droughts.

Trends of Rainfall Variability and Drought Monitoring Using Standardized Precipitation Index in a Scarcely Gauged Basin of Northern Pakistan

This study focused on the trends of rainfall variability and drought monitoring in the northern region of Pakistan (Gilgit-Baltistan). Climate Hazards Group Infrared Precipitation with Stations (CHIRPS) model data were used for the period of 1981 to 2020. The Standardized Precipitation Index (SPI) was applied to assess the dry and wet conditions during the study period. The Mann–Kendall (MK) and Spearman’s rho (SR) trend tests were applied to calculate the trend of drought. A coupled model intercomparison project–global circulation model (CMIP5–GCMs) was used to project the future precipitation in Gilgit-Baltistan (GB) for the 21st century using a multimodel ensemble (MME) technique for representative concentration pathway (RCP) 4.5 and RCP 8.5. From the results, the extreme drought situations were observed in the 12-month SPI series in 1982 in the Diamir, Ghizer, and Gilgit districts, while severe drought in 1982–1983 was observed in Astore, Ghizer, Gilgit, Hunza-Nagar, and Skardu. Similarly, in 2000–2001 severe drought prevailed in Diamir, Ghanche, and Skardu. The results of MK and SR indicate a significant increasing trend of rainfall in the study area, which is showing the conversion of snowfall to rainfall due to climate warming. The future precipitation projections depicted an increase of 4% for the 21st century as compared with the baseline period in the GB region. The results of the midcentury projections depicted an increase in precipitation of about 13%, while future projections for the latter half of the century recorded a decrease in precipitation (about 9%) for both RCPs, which can cause flooding in midcentury and drought in the latter half of the century. The study area is the host of the major glaciers in Pakistan from where the Indus River receives its major tributaries. The area and volume of these glaciers are decreasing due to warming impacts of climate change. Therefore, this study is useful for proper water resource management to cope up with water scarcity in the future.

Meaningful Trend in Climate Time Series: A Discussion Based On Linear and Smoothing Techniques for Drought Analysis in Taiwan

Finding significant trends in hydroclimate time series has been deemed an essential task in numerous studies. Despite the existence of various trend detection methods, statistical significance is mostly examined for linear trends and related to the meaningfulness of the found trends. We wish to draw attention to a more general definition of meaningful trends by cross-referencing not only linear but also smoothing techniques. We apply linear regression (LR) and two smoothing techniques based on regularized minimal-energy tensor-product B-splines (RMTB) to the trend detection of standardized precipitation index (SPI) series over Taiwan. LR and both RMTB-based methods identify an overall upward (wetting) trend in the SPI series across the time scales in Taiwan from 1960 to 2019. However, if dividing the entire time series into the earlier (1960–1989) and later (1990–2019) sub-series, we find that some downward (drying) trends at varied time scales migrate from southcentral–southwestern to eastern regions. Among these significant trends, we have more confidence in the recent drying trend over eastern Taiwan since all the methods show trend patterns in highest similarity. We also argue that LR should be used with great caution, unless linearity in data series and independence and normality in residuals can be assured.

Analysis of spatiotemporal variations of drought and its correlations with remote sensing-based indices via wavelet analysis and clustering methods

Abstract Beside in situ observations, satellite-based products can provide an ideal data source for spatiotemporal monitoring of drought. In this study, the spatiotemporal pattern of drought was investigated for the northwest part of Iran using ground- and satellite-based datasets. First, the Standardized Precipitation Index series were calculated via precipitation data of 29 sites located in the selected area and the CPC Merged Analysis of Precipitation satellite. The Maximal Overlap Discrete Wavelet Transform (MODWT) was used for obtaining the temporal features of time series, and further decomposition was performed using Ensemble Empirical Mode Decomposition (EEMD) to have more stationary time series. Then, multiscale zoning was done based on subseries energy values via two clustering methods, namely the self-organizing map and K-means. The results showed that the MODWT–EEMD–K-means method successfully identified homogenous drought areas. On the other hand, correlation between the satellite sensor data (i.e. the Normalized Difference Vegetation Index, the Vegetation Condition Index, the Vegetation Healthy Index, and the Temperature Condition Index) was evaluated. The possible links between central stations of clusters and satellite-based indices were assessed via the wavelet coherence method. The results revealed that all applied satellite-based indices had significant statistical correlations with the ground-based drought index within a certain period.

Detecting Drought Variability by using Two-Dimensional Correlation Analysis

The Standardized Precipitation Index (SPI) has been recognized as the standard index that should be used for quantifying and reporting meteorological drought. This study aims to present the application of the two-dimensional correlation method for determining the spatial and temporal variability of drought among the SPI series. Heatmaps were used as a new way of visualizing SPI series which enables visual inspection of dry and wet periods. The developed method was applied on 13 meteorological stations in Central Anatolia. Significant variations in drought behaviour were found in the investigated region even for the stations close to each other.

Assessment of drought in SPI series using continuous wavelet analysis for Gediz Basin, Turkey

This study aims to estimate the short and long-term drought periodicities, and trend component using the continuous wavelet transforms. The applied approach introduces a new concept, the maxima line, which defines the most dominant component affecting the trend in Standardized Precipitation Index (SPI) time series. The analysis of the short and long-term drought cycles was performed with data from 15 stations located in Gediz Basin, at western part of Turkey, obtained during the recording period of 1960–2016. The change point in the SPI time series was determined graphically via the continuous wavelet power spectrum, and the obtained results were verified with Pettitt's test. The significant change points, in the northwest, east and southwest part of the basin, occurred by the beginning of 1980s, by the end of 1980s, and by the mid of 1990s, respectively. The most dominating periodicities affecting the trend were varying between 24 and 48 months for the short-term drought cycles, whereas they were varying between 96 and 162 months for the long-term drought cycles.

Analysis of Drought Investigation Using Standard Precipitation Index (SPI) of Historical Rainfall Data (1979-2013) Under Temperate Conditions Over Anand, Gujarat (India)

Drought is a naturally occurring event caused due to deficiency in precipitation over an extended period of time. It is a slow-onset, creeping natural hazard that affects continuously all parts of the world. It occurs in all climatic zones such as high as well as low precipitation areas and causes high economic and social losses around the world. Droughts are generally measured in terms of deficiency in the rainfalls or streams flows below a predefined reference level. The magnitude of departure from the reference level during a drought spell is known as the severity of drought. Droughts are occurring in different regions of the world with increased frequency and severity. In this study, temporal pattern of droughts was analyzed in the Anand Station using SPI approach. Monthly precipitation data from 1979 to 2013 were used to compute Standardized Precipitation Index (SPI) values. The computation of SPI series was done for short as well as intermediate time scales. Analysis of SPI values were done to study the temporal patterns of drought occurrence. The drought severity and duration were also estimated. From the analysis, it was observed that in the years 1980, 1984,1985,1986,1987, 1989, 1991,1992,1993,1995, 1999,2000,2001,2002 and 2009 drought occurred in the area in Anand station. Extreme drought occurred in the year 1987 when the SPI value was -2.27. Also, SPI in the severe and extreme drought years indicate only moderate dryness instead of extreme dryness.

The potential of integrated hybrid pre-post-processing techniques for short- to long-term drought forecasting

Abstract Due to the drought negative impacts, accurate forecasting of drought indices is important. This study focused on the short- to long-term Standardized Precipitation Index (SPI) forecasting in sites with different climates using newly integrated hybrid pre-post-processing techniques. Four sites in Iran's northwest were selected and the SPIs series with time scales of 3, 9, and 24 months were forecasted during the period of 1978–2017. For improving the modeling efficiency, wavelet transform and ensemble empirical mode decomposition (EEMD) pre-processing methods were used. In this regard, temporal features of the SPIs series were decomposed via wavelet transform (WT), then, the obtained sub-series were further broken down into intrinsic mode functions using EEMD. Also, simple linear averaging and nonlinear neural ensemble post-processing methods were applied to ensemble the outputs of hybrid models. The results showed that data pre-processing enhanced the models' capability up to 40%. Also, integrated pre-post-processing models improved the models' efficiency by approximately 50%. The root mean square errors' criteria distribution range decreased from 0.337–1.03 (in raw data) to 0.195–0.714 (in decomposed data). The results proved the capability of applied methods in modeling the SPIs series. In increasing the models' accuracy, data pre-processing was more effective than data post-processing.

Analysis of Precipitation and Streamflow Data for Drought Assessment in an Unregulated Watershed

Predicting drought occurrence accurately still remains a challenging task. To fill research gaps, this study identified and analysed meteorological and hydrological droughts using the Standardized Precipitation Index (SPI) and Streamflow Drought Index (SDI), respectively, in the upper Lam Pao watershed in Thailand. The study also focused on investigating the relationships between both droughts. The SPI and SDI were computed based on observed long-term precipitation and streamflow data during the period of 1988-2017. The drought analysis was carried out by using the R packages. The location, period and severity level of drought events were graphically presented. On the basis of trend analysis, the SPI series showed slightly increasing trends, whereas no trend was found for the SDI series. This implied that the hydrological drought was influenced by not only precipitation but also other factors. The key findings indicated that there was a positive relationship between meteorological and hydrological droughts. In addition, there was a specific lag time, which may depend on physical characteristics of a basin, in drought propagating from meteorological drought to hydrological drought. Overall, the drought indices can help to predict hydrological drought events, which could be valuable information for drought monitoring and early warning systems.

Reassessing long-term drought risk and societal impacts in Shenyang, Liaoning Province, north-east China (1200–2015)

Abstract. The occurrence of two severe droughts in north-east China since 2000 has raised attention in the risk presented by droughts. This paper presents a historic drought series for Shenyang in Liaoning Province, north-east China, from 1200 CE to the present with a reconstructed long precipitation series (1906–2015) augmented with historical documentary accounts. Analysis of the instrumental series using a standardized precipitation index (SPI) and extending it using historical records has produced a combined series spanning over 8 centuries. The combined long series was analysed for patterns in drought frequency, severity and typology. Three droughts comparable to those since 2000 occur in the instrumental series during the early 20th century (i.e. 1907, 1916–1918 and 1920–1921), and coeval archival sources reveal the human impacts of these severe droughts. The archival sources demonstrate how reduced vulnerability resulting from societal and cultural changes in the early 20th century helped prevent the loss of life experienced during comparable severe droughts at the end of the 19th century (1887 and 1891). Incorporating a longer temporal perspective to drought analysis shows that onset is often earlier than is documented explicitly within the archives, and so combined SPI series for a region could provide an early warning of drought development expressed as a water deficit in the previous year. Analysis of archival data provides a rich historical description of impacts and societal responses to severe drought. The archives provide a rich historical description of drought impacts and responses at the personal and community level whilst also detailing the different roles played by communities, state and international organizations in responding to events.

ENN-SA: A novel neuro-annealing model for multi-station drought prediction

This paper presents a new hybrid model, called ENN-SA, for spatiotemporal drought prediction. In ENN-SA, an Elman neural network (ENN) is conjugated with simulated annealing (SA) optimization and support vector machine (SVM) classification algorithms for the standardized precipitation index (SPI) modeling at multiple stations. The proposed model could be applied to predict SPI at different time scales in a meteorology station with lack of data through the intelligent use of SPI series of the nearby stations as the model inputs. The capability of the hybrid model for multi-station prediction of meteorological drought was examined through the cross-validation technique for Kecioren station in Ankara Province, Turkey. To this end, the SPI-3, SPI-6, and SPI-12 at the station were modeled using the same indices of five nearby stations. In the first step, SVM was trained using different kernels in order to generate and classify a set of plausible multi-station prediction scenarios. Then, ENN was used to regress the SPI series at each scenario and finally, the SA component of the integrated model was utilized to improve the ENN efficiency. Various error and complexity measures were used to detect the models’ performance. The results showed the ENN-SA is promising and efficient for multi-station SPI prediction.

Meteorological drought trend analysis by standardized precipitation index (SPI) and reconnaissance drought index (RDI): a case study of Gajapati District

Drought is taken into account as a natural hazard, which might be characterized mainly by its severity, duration, and areal extent. Among the above three dimensions, drought severity is that the main factor through which drought analysis was done. The paper aims at presenting the overall meteorological drought analysis of Gajapati District of Odisha by Reconnaissance Drought Index (RDI)and Standard precipitation Index (SPI), through DrinC software using SPI-3, SPI-6, SPI-9 & SPI-12, and RDI-3, RDI-6, RDI-9 & RDI 12 which were computed at multiple time steps (3, 6,9 and 12-month) for the period 1967-2002. The 12-month SPI and RDI series shows well-defined wet periods and dry periods compared to other months. it has been discussed, for identifying dry/wet periods, SPI 12 and RDI 12 shows greater utility than SPI 3 and RDI 3. The analysis of RDI-12 shows that, there was a Moderate drought was recorded during 1967-68, 1973-74, 1984-85, 1987-88. In the Gajapati region drought index, by SPI & RDI method showed that extremely affected by drought among 35 years was 1972-73 and severe drought occurred in 1979-80. Overall, there was a moderate drought situation within the Gajapati district.

Effects of Gamma-Distribution Variations on SPI-Based Stationary and Nonstationary Drought Analyses

This study aims to analytically explore the effects of changing rainfall distributions in terms of variations in the mean and variance of gamma distributions on the drought analysis based on standardized precipitation index (SPI). Traditional SPI calculation involves the fitting of observed rainfall series to a time-invariant probability distribution; the gamma distribution is commonly used. Fitting a time-varying gamma distribution to a trending rainfall series leads to nonstationary SPI (NSPI) series. The effects of changing gamma distributions on the SPI and NSPI can be systematically summarized by the proposed nine-category distributional-change scheme in terms of variations in the mean and variance of the gamma distributions. The annual wet-season rainfall series at Taipei (1897–2017) and Dawu (1940–2017), which exhibit significantly increasing and insignificantly decreasing trends, respectively, were selected for demonstration. A clearly increasing rainfall trend at Taipei over the last four decades corresponds to less severe droughts in the SPI series and more frequent and more severe droughts in the NSPI series. These contradictory results are attributed to the time-invariant gamma distribution, which causes the trending SPI series to be identical to the rainfall series, and the time-varying gamma distribution, which results in the trend-free NSPI series. The modeling of nonstationarity in rainfall series in the proposed calculation framework depends on the purposes of the analysis since different information is revealed for drought assessments.

Spatio-temporal analysis and forecasting of drought in the plains of northwestern Algeria using the standardized precipitation index

Drought is the most frequent natural disaster in Algeria during the last century, with a severity ranging over the territory and causing enormous damages to agriculture and economy, especially in the north-west region of Algeria. The above issue motivated this study, which is aimed to analyse and predict droughts using the Standardized Precipitation Index (SPI). The analysis is based on monthly rainfall data collected during the period from 1960 to 2010 in seven plains located in the north-western Algeria. While a drought forecast with 2 months lead-time is addressed using an artificial neural network (ANN) model. Based on SPI values at different time scales (3-, 6-, 9-, and 12-months), the seven plains of north-western Algeria are severely affected by drought, conversely of the eastern part of the country, wherein drought phenomena are decreased in both duration and severity. The analysis also shows that the drought frequency changes according to the time scale. Moreover, the temporal analysis, without considering the autocorrelation effect on change point and monotonic trends of SPI series, depicts a negative trend with asynchronous in change-point timing. However, this becomes less significant at 3 and 6 months’ time scales if time series are modelled using the corrected and unbiased trend-free-pre-whitening (TFPWcu) approach. As regards the ANN-based drought forecast in the seven plains with 2 months of lead time, the multi-layer perceptron networks architecture with Levenberg–Marquardt calibration algorithm provides satisfactory results with the adjusted coefficient of determination ( $$ R_{\text{adj}}^{2} $$ ) higher than 0.81 and the root-mean-square-error (RMSE) and the mean absolute error (MAE) less than 0.41 and 0.23, respectively. Therefore, the proposed ANN-based drought forecast model can be conveniently adopted to establish with 2 months ahead adequate irrigation schedules in case of water stress and for optimizing agricultural production.