High-throughput viscometry via machine-learning from videos of inverted vials

Abstract

Although the inverted vial test has been widely used as a qualitative method for estimating fluid viscosity, quantitative rheological characterization has remained limited due to its complex, uncontrolled flow - driven by gravity, surface tension, inertia, and initial conditions. Here, we present a computer vision (CV) viscometer that automates the inverted vial test and enables quantitative viscosity inference across nearly five orders of magnitude (0.01-1000 Pas), without requiring direct velocity field measurements. The system simultaneously inverts multiple vials and records videos of the evolving fluid, which are fed into a neural network that approximates the inverse function from visual features and known fluid density. Despite the complex, multi-regime flow within the vial, our approach achieves relative errors below 25%, improving to 15% for viscosities above 0.1 Pas. When tested on non-Newtonian polymer solutions, the method reliably estimates zero-shear viscosity as long as viscoelastic or shear-thinning behaviors remain negligible within the flow regime. Moreover, high standard deviations in the inferred values may serve as a proxy for identifying fluids with strong non-Newtonian behavior. The CV viscometer requires only one camera and one motor, is contactless and low-cost, and can be easily integrated into high-throughput experimental automated and manual workflows. Transcending traditional characterization paradigms, our method leverages uncontrolled flows and visual features to achieve simplicity and scalability, enabling high-throughput viscosity inference that can meet the growing demand of data-driven material models while remaining accessible to lower resource environments.