In this work, we present our advances to develop and apply digital twins for drilling fluids and associated wellbore phenomena during drilling operations. A drilling fluid digital twin is a series of interconnected models that incorporate the learning from the past historical data in a wide range of operational settings to determine the fluids properties in real-time operations. Our specific focus is on prediction of cuttings bed thickness along the wellbore in hole cleaning and prediction of high-pressure high-temperature (HPHT) rheological properties (in downhole conditions). In both applications, we present procedures to develop accurate digital twins for prediction of drilling fluid properties in real-time drilling operations. In the hole cleaning application, we develop accurate computational fluid dynamics (CFD) models to capture the effects of rotation, eccentricity, and bed height on local fluid velocities above cuttings bed. We then run 55,000 CFD simulations for a wide range of operational settings to generate training data for machine learning. For rheology monitoring, thousands of lab experiment records are collected as training data for machine learning. In this case, the HPHT rheological properties are determined based on rheological measurement in the American Petroleum Institute (API) condition (14.7 psi and 150 °F) together with the fluid type and composition data. We compare the results of the application of several machine learning algorithms to represent CFD simulations (for hole cleaning) and lab experiments (for monitoring HPHT rheological properties). Rotating cross-validation method is applied to ensure accurate and robust results. In both cases, models from the gradient boosting and the artificial neural network algorithms provided the highest accuracy (about 0.95 in terms of R2) for test datasets. With developments presented in this paper, the hole cleaning calculations can be performed in real time, and the HPHT rheological properties of drilling fluids can be estimated at the rig site avoiding the need to wait for the laboratory experimental results.