Forecasting of stage-discharge in a non-perennial river using machine learning with gamma test.

Knowledge of the stage-discharge rating curve is useful in designing and planning flood warnings; thus, developing a reliable stage-discharge rating curve is a fundamental and crucial component of water resource system engineering. Since the continuous measurement is often impossible, the stage-discharge relationship is generally used in natural streams to estimate discharge. This paper aims to optimize the rating curve using a generalized reduced gradient (GRG) solver and the test the accuracy and applicability of the hybridized linear regression (LR) with other machine learning techniques, namely, linear regression-random subspace (LR-RSS), linear regression-reduced error pruning tree (LR-REPTree), linear regression-support vector machine (LR-SVM) and linear regression-M5 pruned (LR-M5P) models. An application of these hybrid models was performed and test to modeling the Gaula Barrage stage-discharge problem. For this, 12-year historical stage-discharge data were collected and analyzed. The 12-year historical daily flow data (m3/s) and stage (m) from during the monsoon season, i.e., June to October only from 03/06/2007 to 31/10/2018, were used for discharge simulation. The best suitable combination of input variables for LR, LR-RSS, LR-REPTree, LR-SVM, and LR-M5P models was identified and decided using the gamma test. GRG-based rating curve equations were found to be as effective and more accurate as conventional rating curve equations. The outcomes from GRG, LR, LR-RSS, LR-REPTree, LR-SVM, and LR-M5P models were compared to observed values of daily discharge based on Nash Sutcliffe model efficiency coefficient (NSE), Willmott Index of Agreement (d), Kling-Gupta efficiency (KGE), mean absolute error (MAE), mean bias error (MBE), relative bias in percent (RE), root mean square error (RMSE) Pearson correlation coefficient (PCC) and coefficient of determination (R2). The LR-REPTree model (combination 1: NSE = 0.993, d = 0.998, KGE = 0.987, PCC(r) = 0.997, and R2 = 0.994 and minimum value of RMSE = 0.109, MAE = 0.041, MBE = -0.010 and RE = -0.1%; combination 2; NSE = 0.941, d = 0.984, KGE = 0. 923, PCC(r) = 0. 973, and R2 = 0. 947 and minimum value of RMSE = 0. 331, MAE = 0.143, MBE = -0.089 and RE = -0.9%) performed superior to the GRG, LR, LR-RSS, LR-SVM, and LR-M5P models in all input combinations during the testing period. It was also noticed that the performance of the alone LR and its hybrid models (i.e., LR-RSS, LR-REPTree, LR-SVM, and LR-M5P) was better than the conventional stage-discharge rating curve, including the GRG method.

Cost-effective management measures for coastal aquifers affected by saltwater intrusion and climate change.

Sustainable management of natural water resources and food security in the face of changing climate conditions is critical to the livelihood of coastal communities. Increasing inundation and saltwater intrusion (SWI) will likely adversely affect agricultural production and the associated beach access for tourism. This study uses an integrated surface-ground water model to introduce a new approach for retardation of SWI that consists of placing aquifer fill materials along the existing shoreline using Coastal Land Reclamation (CLR). The modeling results suggest that the artificial aquifer materials could be designed to decrease SWI by increasing the infiltration area of coastal precipitation, collecting runoffs from the catchment area, and applying treated wastewater or desalinated brackish water-using coastal wave energy to reduce water treatment costs. The SEAWAT model was applied to verify that it correctly addressed Henry's problem and then applied to the Biscayne aquifer, Florida, USA. In this study, to better inform Coastal Aquifer Management (CAM), we developed four modeling scenarios, namely, Physical Surface Barriers (PSB), including the artificial aquifer widths, permeability, and side slopes and recharge. In the base case scenario without artificial aquifer placement, results show that seawater levels would increase aquifer salinity and displace large amounts of presently available fresh groundwater. More specifically, for the Biscayne aquifer, approximately 0.50% of available fresh groundwater will be lost (that is, 41,192 m3) per km of the width of the aquifer considering the increasing seawater level. Furthermore, the results suggest that placing the PSB aquifer with a smaller permeability of <100 m per day at a width of approximately 615 m increases the available fresh groundwater by approximately 45.20 and 43.90% per km of shoreline, respectively. Similarly, decreasing the slope on the aquifer-ocean side and increasing the aquifer recharge will increase freshwater availability by about 43.90 and 44.50% per km of the aquifer. Finally, placing an aquifer fill along the shallow shoreline increases net revenues to the coastal community through increased agricultural production and possibly tourism that offset fill placement and water treatment costs. This study is useful for integrated management of coastal zones by delaying aquifer salinity, protecting fresh groundwater bodies, increasing agricultural lands, supporting surface water supplies by harvesting rainfall and flash flooding, and desalinating saline water using wave energy. Also, the feasibility of freshwater storage and costs for CAM is achieved in this study.