Year Established: 2020 Start Date: 2020-02-25 End Date: 2021-02-23
Total Federal Funds: $5,000 Total Non-Federal Funds: $10,000
Principal Investigators: Yusuf Sermet
Abstract: The growing availability of smart devices with advanced sensors has increased opportunities for the Internet of Things (IoT) applications in environmental monitoring. Accurate and widespread monitoring of river stage is vital for modeling water resources. Reliable data points are required for model calibration and validation in forecast studies. While current embedded monitoring systems provide accurate measurements, the cost to replicate these systems on a large domain is prohibitively expensive, limiting the quantity of data available. This project proposes a novel methodology for water level measurement by introducing geometric solutions that utilize prevalent smartphone sensors. The introduced approach creates a distinct opportunity for a low-cost camera-based embedded system that will measure water levels and share surveys to power environmental research and decision making. The framework includes communication protocols on the embedded systems as well as a web application as a centralized information system to view and analyze the vast amount of measurements. In addition to the water level measurement, the presence of the camera enables further usage scenarios such as recognizing objects (e.g. debris, tree, human, boat) on the water surface using deep learning, and supplying annotated data for hydrological processes including surface water modeling, and streamflow estimation.