I-Corps: Translation Potential of Compositional Analyses from Dried Drop Stains

This I-Corps project focuses on exploring the commercial potential of a photographic analysis method that determines chemical composition from patterns left behind by evaporated liquid drops. These stains, which form on common surfaces, contain structural features that reflect underlying chemical properties of the original solution. This solution could address the need for affordable, rapid, and user-friendly chemical testing, particularly in water quality analysis, where existing methods either lack precision or require costly instrumentation. Millions of households and businesses in the United States depend on water testing for health, environmental, or regulatory reasons, yet many do not have access to reliable and convenient options. This project aims to deliver a new solution that uses images captured by conventional smartphone cameras, enabling broad accessibility without the need for specialized training or laboratory resources. By lowering barriers to chemical analysis, the technology serves the national interest in promoting public health, environmental monitoring, and technological innovation. This I-Corps project utilizes experiential learning coupled with a first-hand investigation of the industry ecosystem to assess the translation potential of the technology. This solution is based on the development of machine learning models trained on large libraries of stain images created by evaporating aqueous solutions with known compositions. The method extracts quantitative metrics from these images—such as texture, symmetry, edge complexity, and crystal morphology—and uses statistical learning to correlate them with chemical parameters like ionic strength, salt concentration, and water hardness. Unlike traditional assays, this approach requires no reagents, sensors, or chemical handling, and its accuracy improves with growing datasets and model refinement. If successful, the technology will offer a portable, cost-effective, and scalable platform for composition analysis, with future applications in fields such as beverage quality control, agricultural monitoring, and low-cost diagnostics. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.