Knights' research interests are in developing and applying data mining and machine learning methods for feature extraction and predictive modeling with high-dimensional, noisy, and incomplete data. Much of his research has focused on using computational genomics to study the role of the microbiome in human health, including understanding the effects of industrialization on the human microbiome. This work continues, alongside more recent work focused on modeling sustainability of various practices in human civilization. In sustainability, Knights is interested in using predictive models to track greenhouse gas emissions and consumption of natural resources at the global level. The long-term goal of this work is to use data mining to identify changes that will make civilization more sustainable, and to share that information in ways that empower people and organizations to change their behavior.