Fast multi-output relevance vector regression for joint groundwater and lake water depth modeling

Fast multi-output relevance vector regression (FMRVR) algorithm is developed for simultaneous estimation of groundwater and lake water depth the first time in this study. The FMRVR a analysis technique which can simultaneously predict multiple outputs multi-dimensional input. data used study collected from 34 stations located Urmia basin over 40-year period. performance model examined contrast to support (SVR) multi-linear (MLR) benchmarks. Results reveal that able generate more accurate with coefficient determination (R2) 0.856 0.992 root mean square error (RMSE) 0.857 0.083, respectively. outperformance be linked its capability joint relevant by taking into account possible correlations among outputs.