The performance of the bio-inspired adaptive neuro-fuzzy inference system (ANFIS) models are proposed for forecasting highly non-linear streamflow of Pahang River, located in a tropical climatic region of Peninsular Malaysia. Three different bio-inspired optimization algorithms namely particle swarm optimization (PSO), genetic algorithm (GA), and differential evolution (DE) were individually used to tune the membership function of ANFIS model in order to improve the capability of streamflow forecasting. Different combination of antecedent streamflow was used to develop the forecasting models. The performance of the models was evaluated using a number of metrics including mean absolute error (MAE), root mean square error (RMSE), coefficient of determination (R 2), and Willmott's Index (WI) statistics. The results revealed that increasing number of inputs has a positive impact on the forecasting ability of both ANFIS and hybrid ANFIS models. The comparison of the performance of three optimization methods indicated PSO improved the capability of ANFIS model (RMSE = 7.96; MAE = 2.34; R 2 = 0.998 and WI = 0.994) more compared to GA and DE in forecasting streamflow. The uncertainty band of ANFIS-PSO forecast was also found the lowest (±0.217), which indicates that ANFIS-PSO model can be used for reliable forecasting of highly stochastic river flow in tropical environment. INDEX TERMS Streamflow forecasting, fuzzy logic, evolutionary algorithm, uncertainty analysis, tropical environment.
The frequency and severity of global drought-induced impacts have led to raising awareness of the need for improved river management. Although academic publications on drought have proliferated, a systematic review of literature has not yet been conducted to identify trends, themes, key topics, and authorships. This study aims to evaluate the scientific evidence for the hydrological drought characteristics and the methodologies by performing as a framework. This systematic review performed three-stage screening of literature review for current applicable hydrological drought studies that have been conducted since the year of 2000 concerning methodologies, literature research gaps, and trends, and contribute to future studies. The analysis shows the increasing trends of research and publications in the hydrological drought assessment. The primary research themes are hydrological drought is drought severity, drought vulnerability, and drought forecast. Despite the current research findings, spatial and temporal variability, low flow analysis and regional modelling are the most important to encourage a holistic approach and international collaborations. The finding identified the shortcomings of most research, which are the use of non-standardized methodological and distinct sample sizes, resulting in data summary challenges and unrealistic comparisons.
In recent decades, Malaysia has become one of the world’s most urbanized nations, causing severe flash flooding. Urbanization should meet the population’s needs by increasing the development of paved areas, which has significantly changed the catchment’s hydrological and hydraulic characteristics. Therefore, the frequency of flash flooding in Malaysia’s urban areas has grown year after year. Numerous techniques have been used, including the statistical approach, modeling, and storm design methods, in flood simulation. This research integrated hydrology and hydraulic models to simulate the urban flood events in the Aur River catchment. The primary objective is to determine water level and forecast peak flow based on hydrological assessment in the drainage system using XPSWMM software. The rainfall data for 60 min was used for this study in the hydrological analysis by obtaining an intensity-duration-frequency curve and peak flow value (Q peak). XPSWMM is used to simulate the response of a catchment to rainfall events in which runoff, water depth profile, and outflow hydrograph are obtained. Peak runoff is also obtained from the modified rational method for validation purposes. The proposed method was verified by comparing the result with the standard method. This is essential to identify flash flooding, which can lead to efficient flood mitigation planning and management in the urban catchment. The increase in residential areas results in the alteration of time of concentration, water quantity, and flow rate. Thus, to mitigate present and future problems, the effects of urbanization on water resources and flood should be analyzed.
Reference evapotranspiration ET o is one of the most significant factors in the hydrological cycle since it has a great influence on water resource planning and management, agriculture and irrigation management, and other processes in the hydrological sector. In this study, an efficient and local predictive model was established to forecast the monthly mean ET o t over Turkey based on the data collected from 35 locations. For this purpose, twenty input combinations including hydrological and geographical parameters were introduced to three different approaches called multiple linear regression MLR , random forest RF , and extreme learning machine ELM . Moreover, in this study, large investigation was done, involving the establishment of 60 models and their assessment using ten statistical measures. The outcome of this study revealed that the ELM approach achieved high accurate estimation in accordance with the Penman–Monteith formula as compared to other models such as MLR and RF . Moreover, among the 10 statistical measures, the uncertainty at 95% U 95 indicator showed an excellent ability to select the best and most efficient forecast model. The superiority of ELM in the prediction of mean monthly ET o over MLR and RF approaches is illustrated in the reduction of the U 95 parameter to 49.02% and 34.07% for RF and MLR models, respectively. Furthermore, it is possible to develop a local predictive model with the help of computer to estimate the ET o using the simplest and cheapest meteorological and geographical variables with acceptable accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.