Stacking ensemble-based hybrid algorithms for discharge computation in sharp-crested labyrinth weirs

Labyrinth weirs are utilized to transport a greater discharge during floods in contrast conventional due their increased weir crest length. Nevertheless, the geometric complexity of labyrinth weirs, determination accurate coefficients and accordingly, head-discharge ratings quite essential issues practical application. Hence, as first step present study proposes following eight standalone algorithms: decision table (DT), Kstar, least median square (LMS), M5 prime (M5P), rule (M5R), pace regression (PR), random forest (RF) sequential minimal optimization (SMO). Then, applying stacking (ST) algorithm, these models were hybridized predict coefficient (Cd) for sharp-crested weirs. Potential/effective variables constructed form several independent dimensionless parameters (i.e., θ, h/W, L/B, L/h, Froude number (Fr), B/W L/W) Cd an output. The accuracy developed was examined terms different statistical visually based quantitative-based error measurement criteria. results illustrate that h/W have highest lowest effect on prediction, respectively. According NSE, all algorithms provided performances, while ST-Kstar had prediction power.