Development of a Hybrid Index for Drought Prediction: Case Study

Karamouz, ‪Mohammad; Rasouli, Kabir; Nazif, Sara

doi:10.1061/(asce)he.1943-5584.0000022

Cited by 70 publications

(36 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Unlike physical and conceptual models, data-driven models are not difficult to implement for the purposes of real-time forecasting. Artificial neural networks (ANNs) have been used in several studies as a drought-forecasting tool [10][11][12][13][14][15][16]. The most popular type of ANN used for the purposes of drought forecasting is the multilayer perceptron (MLP) that is usually optimized with a back propagation algorithm.…”

Section: Introductionmentioning

confidence: 99%

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

Belayneh

Adamowski

2012

Applied Computational Intelligence and Soft Computing

125

View full text Add to dashboard Cite

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, and R 2 . 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.

show abstract

Section: Introductionmentioning

confidence: 99%

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

Belayneh

Adamowski

2012

Applied Computational Intelligence and Soft Computing

125

View full text Add to dashboard Cite

show abstract

“…Then, drought indices of the SPI (Standardized Precipitation Index), SWSI (Surface Water Supply Index) and RDI (Reconnaissance Drought Index) are calculated to project the probable drought periods and their intensity in the future. Please see Morid et al (2006), Karamouz et al (2007Karamouz et al ( , 2009), Karamouz and Araghinejad (2008), Clausen and Pearson (1995), Abbaspour and Sabetraftar (2005), Khalili et al (2011), Tabrizi et al (2010, Tsakiris and Vangelis (2005), 1971-2000 1986-2003 1983-2004 Vangelis et al (2010) and Tsakiris et al (2006) for more information on SPI, SWSI and RDI and their applications for drought analysis in Iran and elsewhere. In the last step, the hedging rule is utilized to develop the reservoir operating policies during the projected Fig.…”

Section: Case Studymentioning

confidence: 98%

Development of a Demand Driven Hydro-climatic Model for Drought Planning

Karamouz

Imen

Nazif

2011

Water Resour Manage

Self Cite

View full text Add to dashboard Cite

In recent years, droughts with increasing severity and frequency have been experienced around the world due to climate change effects. Water planning and management during droughts needs to deal with water demand variability, uncertainties in streamflow prediction, conflicts over water resources allocation, and the absence of necessary emergency schemes in drought situations. Reservoirs could play an important role in drought mitigation; therefore, development of an algorithm for operation of reservoirs in drought periods could help to mitigate the drought impacts by reducing the expected water shortages. For this purpose, the probable drought's characteristics and their variations in response to factors such as climate change should be incorporated. This study aims at developing a contingency planning scheme for operation of reservoirs in drought periods using hedging rules with the objective of decreasing the maximum water deficit. The case study for evaluation of the performance of the proposed algorithm is the Sattarkhan reservoir in the Aharchay watershed, located in the northwestern part of Iran. The trend evaluations of the hydro-climatic variables show that the climate change has already affected streamflow in the region and has increased water scarcity and drought severity. To incorporate the climate change study in reservoir planning; streamflow should be simulated under climate change impacts. For this purpose, the climatic variables including temperature and precipitation in the future under climate change impacts are simulated using downscaled GCM (General Circulation Model) outputs to derive scenarios for possible future drought events. Then a hydrological model is developed to simulate the river streamflow, based on the downscaled data. The results show that the proposed Water Resour Manage (2012) 26:329-357 methodology leads to less water deficit and decreases the drought damages in the study area.

show abstract

“…Earlier, indices were developed for characterization of spatial problems like composite hydrological drought index (Karamouz et al ; Waseem et al ) for areas where rainfall is not a primary source of water (Shafer and Dezman ); soil moisture deficit index and evapotranspiration deficit index for soil moisture deficit and ET deficit conditions (Narasimhan and Srinivasan ); multimetric index for river biological conditions (Emery et al ; Pont et al ); groundwater quality index (Saeedi et al ; Kumar and James ) for sea water intrusion in coastal aquifers (Tomaszkiewicz et al ), for lakes (Chow‐Fraser ) and such as developed a watershed sustainability index for a watershed (Chandniha et al ). Most of the earlier developed hydrologic index is based on single essential hydrologic components such as precipitation, water level, ET, sediment yield, and river flow etc.…”

Section: Introductionmentioning

confidence: 99%

Development of a Composite Hydrologic Index for Semi‐Arid Region of India

Jeet¹,

Singh

Sarangi

2019

Groundwater

View full text Add to dashboard Cite

Rainfall is the major source for groundwater recharge in basins areas of central region of India. Now a day, the river basins are experiencing acute shortage of water which has resulted in lowering of groundwater level and drying up of water bodies. In order to maintain water sustainability; a composite hydrologic index was developed in the Betwa basin of Madhya Pradesh and Uttar Pradesh states, India. The index was developed using principal component analysis through hydrologic, topographic as well as geographic parameters derived from the Soil and Water Assessment Tool and MODFLOW model. The geomorphological parameters were categorized, on the basis of groundwater recharge potential and weight ranged from 1 to 4. The geomorphologic parameters, that is, soil type (T), slope (S), runoff ratio (R), and evapotranspiration (ET) were integrated into a single indicator of composite hydrologic index. Soil type and ET were the major factors that directly affected the groundwater recharge. These two parameters together explained 86% of total variability in the data. Based on the analysis of the four parameters that affected groundwater recharge, composite hydrologic index (CHI) was classified into very good, good, moderate, and low grade. The CHI was statistically validated using standardization methods. The index was developed as a water management tool to measure a sustainability state relative to a groundwater recharge potential, which allows for spatial and temporal comparison. This index will be helpful in natural resource management and will improve socioeconomic status of human population inhibiting in the semi‐arid region.

show abstract

Development of a Hybrid Index for Drought Prediction: Case Study

Cited by 70 publications

References 19 publications

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

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

Development of a Demand Driven Hydro-climatic Model for Drought Planning

Development of a Composite Hydrologic Index for Semi‐Arid Region of India

Contact Info

Product

Resources

About