Search

Drought forecasting is a vital task for sustainable development and water resource management. Emerging machine learning techniques could be used to develop precise drought forecasting models. However, they need to be explicit and simple enough to secure their implementation in practice. This article introduces a novel explicit model, called multi-objective multi-gene genetic programming (MOMGGP), for meteorological drought forecasting that addresses both the accuracy and simplicity of the model applied. The proposed model considers two objective functions: (i) root mean square error and (ii) expressional complexity during its evolution. While the former is used to increase the model accuracy at the training phase, the latter is assigned to decrease the model complexity and achieve parsimony conditions. The model evolution and verification procedure were demonstrated using the standardized precipitation index obtained for Burdur City, Turkey. The comparison with benchmark genetic programming (GP) and multi-gene genetic programming (MGGP) models showed that MOMGGP provides the same forecasting accuracy with more parsimony conditions. Thus, it is suggested to utilize the model for practical meteorological drought forecasting. [ABSTRACT FROM AUTHOR]

Accurate and sustainable management of water resources is among the most important circumstances of basin and river engineering. In this study, a hybrid machine learning (ML) model was generated using CatBoost and Genetic Algorithm (GA) for significant impact on river flow prediction. The study was applied to Sakarya Basin, which is located in semi-arid climatic conditions in Turkey. The forecast performance of the models was observed by developing a day-step ahead forecast scenario with the data of Adatepe, Aktaş and Rüstümköy flow measurement stations (FMS). The daily flow data of the specified stations between 2002 and 2012 were used and the performance of the proposed model was tested by comparing with CatBoost, Long-Short Term Memory (LSTM) and the classical estimation method, Linear Regression (LR). The study was also aimed to improve the predictive performance of genetic algorithms combined with the gradient boosting model (GA-CatBoost). The developed hybrid model outperformed the benchmarked models. The results showed that the developed model can be successfully applied in river flow forecasting. [ABSTRACT FROM AUTHOR]

The investigation of the impacts of climate change on the total runoff volume in two different watersheds named Melen and Munzur in Turkey is the main purpose of this study. The dynamically downscaled outputs of GFDL-ESM2M, HadGEM2-ES, and MPI-ESM-MR general circulation models (GCMs) under RCP4.5 and RCP8.5 scenarios were used as climatic forces to drive a hydrological model called WASMOD-D. The parameters of WASMOD-D model were optimized by using the multi-objective genetic algorithm (GA). In order to wane the influences of uncertainties which are rooted in GCMs, in addition to using various models, the biases in climatic parameters (precipitation and temperature) were corrected using the quantile-mapping method, with respect to the observed data during the reference period (1971–2000). Future projections were developed by taking two 30-years periods into the account: (1) mid-period (2041–2070) and (2) late future (2071–2100). The results of this study show that the total water volume will decrease in accord with precipitation diminution and temperature increase during the mid-time and late future in both watersheds. The percentage of the decline in runoff volume by the end of the 21st century were found as 15.42 and 26.65 on average for Melen and Munzur rivers, respectively. However, the monthly distribution of the runoff was found to be not changed during the current century. [ABSTRACT FROM AUTHOR]