<p>Accurate acquisition and prediction of acoustic parameters of seabed sediments are crucial in marine sound propagation research. While the relationship between sound velocity and physical properties of sediment has been extensively studied, there is still no consensus on the correlation between acoustic attenuation coefficient and sediment physical properties. Predicting the acoustic attenuation coefficient remains a challenging issue in sedimentary acoustic research. In this study, we propose a prediction method for the acoustic attenuation coefficient using machine learning algorithms, specifically the random forest (RF), support vector machine (SVR), and convolutional neural network (CNN) algorithms. We utilized the acoustic attenuation coefficient and sediment particle size data from 52 stations as training parameters, with the particle size parameters as the input feature matrix, and measured acoustic attenuation as the training label to validate the attenuation prediction model. Our results indicate that the error of the attenuation prediction model is small. Among the three models, the RF model exhibited the lowest prediction error, with a mean squared error of 0.8232, mean absolute error of 0.6613, and root mean squared error of 0.9073. Additionally, when we applied the models to predict the data collected at different times in the same region, we found that the models developed in this study also demonstrated a certain level of reliability in real prediction scenarios. Our approach demonstrates that constructing a sediment acoustic characteristics model based on machine learning is feasible to a certain extent and offers a novel perspective for studying sediment acoustic properties.</p>