Drillstring vibration is a major concern during drilling wellbore, and it can be split into three types: axial, torsional, and lateral. Many problems associate with the high drillstring vibrations as tear and wear in downhole tools, inefficient drilling performance, loss of mechanical energy, and hole wash-out. The high cost for the downhole measurement of the drillstring vibrations encourages machine learning applications toward downhole vibration prediction during drilling. Consequently, the objective of this paper is to develop an artificial neural network (ANN) model for predicting the drillstring vibration while drilling a horizontal section. The ANN model uses the surface drilling parameters as model inputs to predict the three types of drillstring vibrations. These surface drilling parameters are flowrate, mud pumping pressure, surface rotating speed, top drive torque, weight on bit, and rate of penetration. The study utilized a data set of 13,927 measurements from a horizontal well that was used to train the ANN model. In addition, a different data set (9284 measurements) was employed to validate the developed ANN model. Correlation coefficient (R) and average absolute percentage error (AAPE) are statistical metrics that are used to evaluate the model accuracy based on the difference between the actual and predicted values for the axial, torsional, and lateral vibrations. The results of the optimized parameters for the developed model showed a high correlation coefficient between the predicted and the actual drillstring vibrations that showed R higher than 0.95 and AAPE below 3.5% for all phases of model training, testing, and validation. The developed model proposed a model-based equation for real-time estimation for the downhole vibrations.