Powder Bed Fusion (PBF) has become an indispensable technique in manufacturing complex and novel structures across a wide range of industries over the past decade. It facilitates rapid prototyping enabling quick validation of part functionality and serial manufacturing of metal parts more economically. However, tailoring properties of manufactured component by controlling process parameters remains a significant challenge due to the extensive trial-and-error that is required. In addition, various uncertainty sources existing in the PBF process can lead to poor reproducibility due to uncertainty propagation. PBF process assisted by virtual processing based on modeling and simulation can speed up this optimization reducing both time and cost. Nevertheless, the multi-physical and multi-scale nature of the PBF process may result in simulation results that are less robust [1]. Concluding phenomenological laws also suffer from insufficient size of dataset [2]. In this context, the machine learning model trained on dataset from physics-rooted simulation can help greatly reduce time and cost for predicting quantitative correlations between the process parameters and properties. In this work, we perform the multiphysics PBF simulations considering multiple factors that can influence the properties of the manufactured parts, such as temperature dependent effective thermal properties of the powder bed. Uncertainty carried by the input parameters, both material, powder bed and process parameters is considered via random sampling within their physical limits. Data-driven analyses based on the batched parallel simulations are performed to reveal the sensitivity of the input parameters to the output property of interest which is melt pool width which is essential to ascertain the quality of lattice structures manufactured using PBF. The inference of the input parameters under the experimental conditions are then conducted. We further verify the dimensionless scaling law of melt pool control [3] and perform Bayesian uncertainty quantification on the obtained experimental data.