The proctor compaction test is used to determine the compaction parameters: maximum dry density and optimal moisture content. This test can be labor-intensive and time-consuming particularly when many testing samples are involved. Additionally, the forecast accuracy of the empirical correlations utilized to estimate these compaction parameters is low. Also, artificial intelligence models which are considered black boxes can result in trained models with high prediction accuracy and yet incoherent with physical and engineering principles. This study has thus concentrated on creating interpretable AI-based models for forecasting OMC utilizing liquid limit, plastic limit (PL), gravel fraction, sand fraction (SF), clay fraction (CF), and compaction energy from a broader range of soil data as input data. Artificial neural networks, deep neural networks, support vector regression (SVR), extreme gradient boosting machine, and random forest are the artificial intelligence (AI) algorithms employed in this study. The similarity in prediction accuracy among the five AI models serves as an example of the accuracy and reliability of AI prediction models. The SVR OMC model was determined to be the best utilizing interpretable AI (IAI) since it has a high degree of generalizability and is compatible with engineering and physical concepts. During these IAI analyses, no erratic or irrational OMC estimations occurred. PL and SF or CF have been successfully used in the development of new IAI-based charts for direct OMC predictions since the IAI analysis revealed that these inputs produce reliable forecasts of OMC.