The operational efficiency of continuous casting in steel production is often hindered by the clogging of submerged entry nozzles (SEN), caused due to the agglomeration of nonmetallic inclusions (NMIs). SEN clogging is challenging to monitor and requires probabilistic models for accurate real-time prediction. In this context, data-driven models emerged as a promising tool to be used in the existing industrial settings. Despite frequent occurrence of SEN clogging, collecting large datasets under varied operational conditions remains challenging. The scarcity of data hampers the ability to develop and train traditional data-driven models effectively. To overcome these challenges, physics-informed data-driven models are proposed in this work. The integration of outputs generated from theoretical calculations is sufficient to compensate for the lack of available datasets. To further enhance accuracy, an advanced methodology involving use of ab initio repository is developed. This repository contains material-specific data including high-temperature nonretarded Hamaker constants of NMIs in specific particle size range of 1–10 μm. A novel parameter, “Clogging Factor” is proposed to monitor and integrated into the modeling architecture to track the reduction in the available volume inside SEN due to the accumulation of NMIs. The proposed model has yet to be validated online but has shown potential in reducing SEN clogging.