Designing for Uncertainty in AI: Supporting Decision-Making in the Process Industry - A User-Centered Approach to Communicating AI Uncertainty for Operators in the Process Industry

Sammanfattning

This thesis investigates how uncertainty in artificial intelligence (AI) systems canbe effectively communicated to support decision-making in the process industry. Asmachine learning-based decision support systems are increasingly integrated into industrial environments, operators are required not only to interpret system outputsbut also to assess their reliability. However, current approaches to uncertainty communication are often insufficiently intuitive, limiting trust and appropriate relianceon AI systems.Adopting a human-centered design approach, this study explores how industrialoperators perceive and reason about uncertainty in their everyday work, and howdifferent forms of uncertainty communication influence trust, decision-making, andsystem use. The research is conducted within the context of the pulp and paperindustry, with a particular focus on the bleaching process, a complex and safetycritical operation.The study follows a Double Diamond design process, combining methods such asa literature review, semi-structured interviews, and observations. Based on theseinsights, a set of design guidelines for uncertainty communication is developed, validated through a design workshop, and implemented in a high-fidelity user interfaceprototype. The guidelines are then evaluated through the prototype with domainexperts using think-aloud protocols, interviews, and acceptance measures.The findings show that operators rely heavily on experience-based and rule-basedreasoning when handling uncertainty, and that transparency, contextual explanations, and historical performance data are essential for building trust in AI systems. Furthermore, effective uncertainty communication encourages more reflectivedecision-making and supports appropriate reliance on AI recommendations.This thesis contributes with empirically grounded design guidelines and a validatedprototype that demonstrate how uncertainty can be communicated in a way thataligns with operators’ cognitive processes and work practices.