A CASE STUDY OF APPLYING HUMAN-AI COLLABORATION TO AQUIFER TEST DESIGN: PLANNING, ANALYSIS, AND INTERPRETATION

Aquifer testing is commonly performed to evaluate hydraulic properties of groundwater systems. However, test design and analysis still heavily relies on direct human involvement and experience. Recent advances in artificial intelligence (AI) enable new opportunities to enhance and streamline elements of the aquifer testing workflow through human-AI collaboration. We explore this potential by partnering an AI assistant with domain expertise in hydrogeology to design and implement an aquifer test in Bell County, Texas working with the Clearwater Underground Water Conservation District. The goal of the aquifer test is to determine the local transmissivity in the Middle Trinity aquifer. The AI assistant was provided with background documents to extract well details, recent water levels, landowner information and aquifer test analysis. These data were used to aid development of a preliminary test plan outlining goals, participants, equipment needs, pre-test measurements and other considerations. The human hydrogeologists leveraged AI functionality for rapid information retrieval and integrated recommendations into an executable field test protocol. Ongoing collaboration during pre-test monitoring, testing operations, and post-test analysis may demonstrate additional areas AI can improve productivity. Initial results indicate the coupling of AI tools with specialized knowledge optimizes and broadens planning. This methodology demonstrates one-way emerging technologies can be harnessed to enhance groundwater characterization and management practices.