Data-Driven Modeling

This research area focuses on developing and applying computational models that leverage large datasets to understand and predict complex systems. Researchers investigate methods for data acquisition, preprocessing, and integration, alongside the development of advanced machine learning algorithms, statistical inference techniques, and simulation frameworks. Key areas include building predictive models for physical phenomena, optimizing industrial processes, and analyzing patterns in biological or social data. The work often involves creating open-source software tools to facilitate the application of these data-driven approaches.

In Arkansas, data-driven modeling has significant relevance for optimizing agricultural yields through precision farming, enhancing the efficiency of manufacturing processes, and improving resource management in sectors like forestry and water. Understanding population health trends and predicting disease outbreaks also benefits from these modeling capabilities. The state's diverse economy and natural resources provide rich opportunities for applying and advancing data-driven insights.

This field draws upon expertise in areas such as multiphase transport phenomena, thermal systems modeling, and metal and thin film mechanics. Collaboration extends across institutions, fostering a broad engagement with the scientific and engineering community.