In the area of ​​prediction of reshaped profile of slopes, Popov (1960) [13] studied stable slopes in the coastal area using physical models. The stability of the reshaped profile in rubble pile breakwaters with cubic rock or concrete reinforcement was studied by Priest et al. (1964) [14]. Van der Meer (1992) released the first version of his computer software, called "BREAKWAT [15]", to predict the reshaped profile in breakwater berms. According to studies conducted by Lykke Anderson (2006), the Van der Meer (1992) method predicts the reshaped profile of dynamically stable breakwater berms (H0T0>70) with acceptable accuracy. But for statically stable breakwaters (H0T0>70) the "BREAKWAT" software predicts an overestimated damage for the breakwater. Furthermore, in this method, the cross-sectional area of ​​the eroded and accumulated parts is assumed to be equivalent, while according to the experimental results, due to the phenomenon of material compression, these two areas are not necessarily equal. Ezabad et al. (2005) [16] presented a computer software called “IB” in which the reshaped profile of a rubble mound structure can be estimated using some equations based on statistical models.2. Experimental data A total of 412 test results are used in the present study, obtained from the experiments conducted by Moghim (2009) [17] and Shekari (2013) [18]. The ranges of these effective parameters covered in the tests are listed in Table 2. The material properties related to the different armor and filter layers are listed in Table 3.3. Model TreeModel tree is one of the machine learning approaches that makes the complex configuration of some modeling topics insoluble by dividing them into simple...... middle of the paper...... an error is given for these estimates in Table 12.6. ConclusionsIn this study with a total of 412 tests and implementing the machine learning approach of M5, seven new formulas for seven key remodeling parameters are driven. Using these seven equations, a geometric algorithm is written in a computer program that predicts the reshaped profile in the seaward slope of the breakwater berm. The following results can be drawn from the present study: - The predictive accuracy of the model trees, although building linear regression models, was observed sufficiently high in estimating the equations to reshape the parameters - According to Figures 7 to 14 and Table 11 , the new program introduced in this study shows better results for validation indices than those of BREAKWAT3 in the parameter range governed by existing datasets.