Accurate voidage prediction in fluidisation systems for full-scale drinking water pellet softening reactors using data driven models

•A new explicit voidage prediction model for liquid-solid fluidised bed is proposed.•Voidage prediction accuracy is improved from 11 % to 2% by combining Reynolds and Froude.•Specific surface area is of major importance in drinking water treatment processes.•Full-scale pellet softening reactors can be optimised by using superficial space velocity.