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 (R2) 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; R2=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.

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.

Missing value in hydrological studies is an unexceptional riddle that has long been discussed by researchers. There are various patterns and mechanisms of “missingness” that can occur and this may have an impact on how the researcher should treat the missingness before analyzing the data. Supposing the consequence of missing value is disregarded, the outcomes of the statistical analysis will be influenced and the range of variability in the data will not be appropriately projected. The aim of this paper is to brief the patterns and mechanism of missing data, reviews several infilling techniques that are convenient to time series analyses in streamflow and deliberates some advantages and drawback of these approaches practically. Simplest infilling approaches along with more developed techniques, such as model-based deterministic imputation method and machine learning method, were discussed. We conclude that attention should be given to the method chosen to handle the gaps in hydrological aspects since missing data always result in misinterpretation of the resulting statistics.