If there is bea significant result to reject the null hypothesis, this network method based on the deep learning algorithms is valid and acceptable to predict the total tree heights located from forest areas. In this study, the dissimilarity ratio in the equivalence test was specified as 10 percent10% of the standard deviation of the difference in observed and predicted means and two one-sided test strategy (TOST) was used to test the equality of slope (b1) to 1±10% and the equality of intercept (b0) to y ̅±10%. The predictions of the confidence intervals for these parameter values waswere obtained by using a nonparametricnon-parametric bootstrap procedure described in Robinson et al. (2005). This equivalence test procedure was performed by using the “TOST” function of the “equivalence” package in the R statistical environment (R development Core Team, 2016).