Publications

• GaugeCam lab performance study: we evaluated uncertainty in the image-based water level system based on GRIME2 (published in Journal of Hydrology)
• GaugeCam field performance study: we evaluated the performance of GaugeCam relative to traditional measurement methods in the field (published in PLOS Water)
• GaugeCam technical note: we describe the algorithms and GRIME2 software used in the lab, field, and current studies (published open access in Water Resources Research)
• Water quality study: GaugeCam was used to monitor water level in a tidal salt marsh (published in Ecological Engineering)
• Improving streamflow monitoring with machine learning: we are using image analysis and machine learning to fill data gaps in hydrologic records; these workflows are inspiration for several GRIME-AI features
  • Proof of concept focused on modeling stage from scalar image features: this analysis focuses on extraction of scalar image features and uses Platte Basin Timelapse Project images available to University of Nebraska for research and education.
  • Conference paper focused on using image features in machine learning models. This paper was led by Professor Gildardo Sanchez-Ante and collaborators at ITESM.
• Current Manuscripts in prep:
  • GaugeCam stop-sign calibration method; comparison with bowtie target calibration and HOBO transducer performance
  • GRIME-AI technical note and software release