Heterogeneous computing with graphical processing unit: improvised back-propagation algorithm for water level prediction

<p>A multitude of research has been rising for predicting the behavior different real-world problems through machine learning models. An erratic nature occurs due to augmented and inadequacy prerequisite dataset prediction water level over fundamental models that show flat or low-set accuracy. In this paper, a powerful scaling strategy is proposed improvised back-propagation algorithm using parallel computing groundwater on graphical processing unit (GPU) Faridabad region, Haryana, India. This paper aims propose new streamlined form heterogeneous examine coalescence artificial neural network (ANN) with GPU level. twenty years data set from 2001-2020 taken into consideration three input parameters namely, temperature, rainfall, parallelized backpropagation compute unified device architecture (CUDA). employs be best suited reinforce performance by providing more accurate fast results predictions GPUs as compared sequential ones central units (CPUs) alone.</p>