Engineering and Technology Journal 41 (05) (2023) 2 of soil with such simple physical properties as Atterberg limits and particle-sizes. These are obtained through simple index tests [3].The determination of compaction characteristics indirectly considering the physical soil properties has been an ongoing topic of many studies. Several correlations have been developed to estimate the compaction characteristics through individual soil index properties [3 -12] or from considering soil fractions [13,14]. However, other studies indicated that considering one input parameter might not be sufficient to estimate the compaction characteristics. Therefore, multiple linear regression (MLR) models were utilized to predict the compaction characteristics considering different basic soil parameters [15 -17, 14, 2, 18, 19]. Further, machine learning techniques were used in some other studies to develop more accurate correlations [20 -23]. Sinha and Wang [24], as an early study employing artificial neural networks (ANN) for the prediction of soil compaction characteristics, indicated that the ANN technique outperforms the traditional statistical models, and a reliable prediction can be obtained. Sivrikaya [16] used a multilinear regression model (MLR) to predict the compaction characteristics of fine-grained soils from soil index properties and soil particle -sizes. The considered input parameters were the combination of gravel content (G), sand content (S), fine-grained content (F), plasticity index (PI), liquid limit (LL), and plastic limit (PL). The study concluded that the compaction characteristics can correlate with Plastic limit well compared to other index properties. Gunaydin [4] employed different techniques: simple-multiple analysis and artificial neural networks in order to predict the compaction characteristics based on the soil particle -sizes. The study highlights that, from both techniques, reliable correlations (R 2 = 0.70 -0.95) for preliminary design can be achieved.Furthermore, Mujtaba et al. [17] developed multiple regression analysis models for 110 sandy soils to predict the compaction characteristics according to the uniformity coefficient (Cu) and compaction energy (CE). Considering the liquid limit (LL), the plasticity index (PI), and compaction energy (CE), Tenpe and Kaur [25] investigated artificial neural network (ANN) modeling performance for predicting compaction characteristics with respect to the index properties of soil. Moreover, Omar et al. [26] utilized complicated mathematical models and novel approaches to anticipate the compaction characteristics of fine-grained soil from numerous physical properties. In addition, Farooq et al. [2] utilized a multiple regression model to predict OMC. Also, Saika et al. [8] developed a set of regression models for predicting compaction characteristics with respect to consistency limits.Using ANNs and MLR for 728 datasets, Karimpour et al. [27] employed some models to predict the compaction characteristics based on soil type, grain size distribution, l...