ERI: an integrated UAV-enabled framework for autonomous sampling and continuous water quality monitoring

The National Science Foundation Division of Chemical, Bioengineering, Environmental, and Transport Systems awarded $200,000 to Texas A&M International University on July 15, 2026, under the Engineering program (CFDA 47.041) to develop an integrated framework for autonomous water quality monitoring using unmanned aerial vehicles.

The project will design and deploy UAV platforms equipped with custom water-sampling payloads to collect samples across strategically selected cross-sections of drinking water sources such as large rivers and reservoirs. Collected data will be integrated with ground-based monitoring networks and analyzed using machine learning models to generate three outputs: real-time water quality estimates, long-term trend indicators, and cumulative pollutant load assessments. These spatially and temporally resolved assessments will provide regulators with decision-relevant intelligence including seasonal nutrient dynamics and annual contaminant budgets.

The project includes student training in automated system design, field experiments, laboratory methods, and data analysis to build workforce capacity in STEM disciplines. Work is performed in Laredo, Texas, with a period of performance extending from the award date through June 30, 2028. This assistance type is a Project Grant.

Abstract

Protecting drinking water sources is essential for public health. However, monitoring water quality across large rivers and reservoirs is difficult. Traditional sampling methods are costly and often provide limited coverage. This project will develop an autonomous monitoring system that uses unmanned aerial vehicles (uavs) to collect water samples across drinking water sources. The collected data will be combined with ground-based monitoring networks and analyzed using artificial intelligence. This approach will create dynamic maps that show current and long-term water quality conditions. In addition, students will receive training in automated system design, field experiments, laboratory methods, and data analysis. These activities will help students build hands-on skills and learn to solve complex engineering problems, supporting stem education and workforce development. This project will establish a next-generation environmental monitoring framework that integrates autonomous UAV-based water sampling, multi-source data fusion, and machine learning analytics to assess water quality dynamics at scale. Equipped with custom water-sampling payloads, UAV platforms will execute systematic multi-point sampling across strategically selected cross-sections of critical water bodies. These flight-derived measurements will be combined with ground-based monitoring datasets including laboratory results, hydrological variables, and contextual drivers to enable quantitative estimation of water quality through machine learning models. These models will generate three decision-relevant outputs: real-time water quality estimates, long-term trend indicators, and cumulative pollutant load assessments. Collectively, these results will provide regulators with spatially and temporally resolved intelligence, such as seasonal nutrient dynamics and annual contaminant budgets, to support evidence-based management decisions. The resulting framework will advance a scalable paradigm for UAV-enabled, data-driven environmental monitoring, with direct implications for the protection and sustainable management of drinking water resources. 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.- subawards are not planned for this award.