Ribana works at the intersection of remote sensing, agricultural and environmental sciences, and data science, where she endeavors to create data-driven models capable of efficiently, accurately, and comprehensively analyzing plant structure and processes on all scales.
Her research is guided by various directions and objectives. Foremost among them is her commitment to advancing our comprehension of plant science processes through the utilization of advanced machine learning techniques. This involves addressing challenges like handling data gathered under variable field conditions where environmental factors may be unmeasurable or unknown and dealing with intricate and often complex datasets. Furthermore, Ribana is dedicated to developing novel methods tailored specifically to agricultural and environmental sciences, aiming to solve the distinctive challenges encountered in these fields. A significant portion of her work involves utilizing machine learning-based analysis methods to merge the capabilities of machine learning with agricultural sciences. This integration is intended to contribute to the expansion of knowledge and the creation of sustainable solutions in this domain.