Amirhosein Aghakhani Afshar; Yousef Hassanzadeh; Ali Asghar Besalatpour; Mohsen Pourreza Bilondi
Abstract
Introduction: Hydrology cycle of river basins and water resources availability in arid and semi-arid regions are highly affected by climate changes, so that recently the increase of temperature due to the increase of greenhouse gases have led to anomaly in the Earth’ climate system. At present, General ...
Read More
Introduction: Hydrology cycle of river basins and water resources availability in arid and semi-arid regions are highly affected by climate changes, so that recently the increase of temperature due to the increase of greenhouse gases have led to anomaly in the Earth’ climate system. At present, General Circulation Models (GCMs) are the most frequently used models for projection of different climatic change scenarios. Up to now, IPCC has released four different versions of GCM models, including First Assessment Report models (FAR) in 1990, Second Assessment Report models (SAR) in 1996, Third Assessment Report models (TAR) in 2001 and Fourth Assessment Report models (AR4) in 2007. In 2011, new generation of GCM, known as phase five of the Coupled Model Intercomparison Project (CMIP5) released which it has been actively participated in the preparation of Intergovernmental Panel on Climate Change (IPCC) fifth Assessment report (AR5). A set of experiments such as simulations of 20th and projections of 21st century climate under the new emission scenarios (so called Representative Concentration Pathways (RCPs)) are included in CMIP5. Iran is a country that located in arid and semi-arid climates mostly characterized by low rainfall and high temperature. Anomalies in precipitation and temperature in Iran play a significant role in this agricultural and quickly developing country. Growing population, extensive urbanization and rapid economic development shows that Iran faces intensive challenges in available water resources at present and especially in the future. The first purpose of this study is to analyze the seasonal trends of future climate components over the Kashafrood Watershed Basin (KWB) located in the northeastern part of Iran and in the Khorsan-e Razavi province using fifth report of Intergovernmental Panel on climate change (IPCC) under new emission scenarios with Mann-Kendall (MK) test. Mann-Kendall is one of the most commonly used nonparametric tests to detect climatic changes in time series and trend analysis. The second purpose of this study is to compare CMIP5 models with each other and determine the changes in rainfall and temperature in the future periods in compare with base period on seasonal scale in all parts of this basin.
Materials and Methods: In this research, keeping in view the importance of precipitation and temperature parameters, fourteen models obtained from the General Circulation Models (GCMs) of the newest generation in the Coupled Model Intercomparison Project Phase 5 (CMIP5) were used to forecast the future climate changes in the study area. In historical time (1992-2005), simulated data of these models were compared with observed data (34 rainfall and 12 temperature stations) using four evaluation criteria for goodness-of-fit including Nash-Sutcliffe (NS), Percent of Bias (PBIAS), coefficient of determination (R2) and the ratio of the root mean square error to the standard deviation of measured data (RSR). Furthermore, all models have a very good rating performance for all of the evaluation criteria and therefore investigation is done for precipitation data as an important component in survey of climate subject to select the optimum models in kashafrood watershed basin.
Results and Discussion: By comparing four evaluation criteria for fourteen models of CMIP5 during historical time, finally, four climate models, including GFDL-ESM2G, IPSL-CM5A-MR, MIROC-ESM and NorESM1-M which indicated more agreement with observed data according to the evaluation criteria were selected. Furthermore, four Representative Concentration Pathways (RCPs) of new emission scenario, namely RCP2.6, RCP4.5, RCP6.0 and RCP8.5 were extracted, interpolated and then under three future periods, including near-century (2006-2037), mid-century (2037-2070) and late-century (2070-2100) were investigated and compered.
Conclusions: The results of Mann-Kendall test which was applied to examine the trend, revealed that the precipitation have variable positive and negative trends which were statistically significant. In addition, mean temperature have a significant positive trend with 90, 99 and 99.9% confidence level. In seasonal scale, survey of climatic variable (rainfall and mean temperature) showed that the maximum and minimum of precipitations occur during spring and summer and mean temperature in all seasons is higher than historical baseline, respectively. Maximum and minimum of mean temperature occur in summer and winter, and the amount of seasonal precipitation in these seasons will be reduced. Finally, across all parts of kashafrood watershed basin, rainfall and mean temperature will be reduced and increased, respectively. In conclusion, models of CMIP5 can simulate the future climate change in this region and four models of CMIP5 can be used for this region.
Reza Hajiabadi; S. Farzin; Y. Hassanzadeh
Abstract
Introduction One reason for the complexity of hydrological phenomena prediction, especially time series is existence of features such as trend, noise and high-frequency oscillations. These complex features, especially noise, can be detected or removed by preprocessing. Appropriate preprocessing causes ...
Read More
Introduction One reason for the complexity of hydrological phenomena prediction, especially time series is existence of features such as trend, noise and high-frequency oscillations. These complex features, especially noise, can be detected or removed by preprocessing. Appropriate preprocessing causes estimation of these phenomena become easier. Preprocessing in the data driven models such as artificial neural network, gene expression programming, support vector machine, is more effective because the quality of data in these models is important. Present study, by considering diagnosing and data transformation as two different preprocessing, tries to improve the results of intelligent models. In this study two different intelligent models, Artificial Neural Network and Gene Expression Programming, are applied to estimation of daily suspended sediment load. Wavelet transforms and logarithmic transformation is used for diagnosing and data transformation, respectively. Finally, the impacts of preprocessing on the results of intelligent models are evaluated.
Materials and Methods In this study, Gene Expression Programming and Artificial Neural Network are used as intelligent models for suspended sediment load estimation, then the impacts of diagnosing and logarithmic transformations approaches as data preprocessor are evaluated and compared to the result improvement. Two different logarithmic transforms are considered in this research, LN and LOG. Wavelet transformation is used to time series denoising. In order to denoising by wavelet transforms, first, time series can be decomposed at one level (Approximation part and detail part) and second, high-frequency part (detail) will be removed as noise. According to the ability of gene expression programming and artificial neural network to analysis nonlinear systems; daily values of suspended sediment load of the Skunk River in USA, during a 5-year period, are investigated and then estimated.4 years of data are applied to models training and one year is estimated by each model. Accuracy of models is evaluated by three indexes. These three indexes are mean absolute error (MAE), root mean squared error (RMSE) and Nash-Sutcliffecoefficient (NS).
Results and Discussion In order to suspended sediment load estimation by intelligent models, different input combination for model training evaluated. Then the best combination of input for each intelligent model is determined and preprocessing is done only for the best combination. Two logarithmic transforms, LN and LOG, considered to data transformation. Daubechies wavelet family is used as wavelet transforms. Results indicate that diagnosing causes Nash Sutcliffe criteria in ANN and GEPincreases 0.15 and 0.14, respectively. Furthermore, RMSE value has been reduced from 199.24 to 141.17 (mg/lit) in ANN and from 234.84 to 193.89 (mg/lit) in GEP. The impact of the logarithmic transformation approach on the ANN result improvement is similar to diagnosing approach. While the logarithmic transformation approach has an adverse impact on GEP. Nash Sutcliffe criteria, after Ln and Log transformations as preprocessing in GEP model, has been reduced from 0.57 to 0.31 and 0.21, respectively, and RMSE value increases from 234.84 to 298.41 (mg/lit) and 318.72 (mg/lit) respectively. Results show that data denoising by wavelet transform is effective for improvement of two intelligent model accuracy, while data transformation by logarithmic transformation causes improvement only in artificial neural network. Results of the ANN model reveal that data transformation by LN transfer is better than LOG transfer, however both transfer function cause improvement in ANN results. Also denoising by different wavelet transforms (Daubechies family) indicates that in ANN models the wavelet function Db2 is more effective and causes more improvement while on GEP models the wavelet function Db1 (Harr) is better.
Conclusions: In the present study, two different intelligent models, Gene Expression Programming and Artificial Neural Network, have been considered to estimation of daily suspended sediment load in the Skunk river in the USA. Also, two different procedures, denoising and data transformation have been used as preprocessing to improve results of intelligent models. Wavelet transforms are used for diagnosing and logarithmic transformations are used for data transformation. The results of this research indicate that data denoising by wavelet transforms is effective for improvement of two intelligent model accuracy, while data transformation by logarithmic transformation causes improvement only in artificial neural network. Data transformation by logarithmic transforms not only does not improve results of GEP model, but also reduces GEP accuracy.