Short abstract. Real-time control may enable stormwater networks to manage stormwater pollution and create optimal conditions for aquatic life. The limited number of real-world case studies has hindered the acceptance and adoption of these autonomous solutions. In particular, no studies have explored the in-situ, real-time control of water quality directly. To that end, we present a novel dissolved oxygen monitoring and control system deployed in a municipal stormwater wetland in Ann Arbor, Michigan, US. This study shows how dissolved oxygen levels are influenced by real-time control, and we discuss the implications of the results to future system-level control studies.

Creating understandable rainfall-runoff models anywhere with a sensor

Published: May 24, 2023

Abstract. We present a software framework that automatically sources forcing data and trains a predictive model for rainfall-runoff given only a sensor’s readings timeseries and location.

Automatically discovering interpretable rainfall-runoff models

Published: June 13, 2023

Short abstract. Hydrologic sensor networks are expanding rapidly and generating more data every day. As the volume and resolution of these data sets grow, manual analysis, model calibration and quality control become infeasible. Few existing approaches can transform raw data into interpretable results. Process-based models are not designed to consume large amounts of real-time data, while machine learning models are typically uninterpretable, limiting insight and trust. To address this gap of automation and interpretability, we present a scalable approach that discovers differential equations and latent state estimations in water systems using only rainfall and runoff measurements. This method generates approximations of watersheds as nonlinear, time invariant dynamical systems automatically from measurements. We capture rainfall-runoff relations for catchments and combined sewers of all scales using between five and thirty parameters. We also demonstrate the method’s potential for surrogate modeling by replicating the dynamics of a large process-based model at a small fraction of the computational complexity. This parsimonious representation of watershed dynamics provides theoretical insight and the computational efficiency to enable automated predictions across large sensor networks.

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.

Travis Adrian Dantzer

Posts by Collection

portfolio

publications

talks

teaching