Using Sensor Data to Dynamically Map Large‐Scale Models to Site‐Scale Forecasts: A Case Study Using the National Water Model

Abstract

There has been an explosive growth in the ability to model large water systems. While these models are effective at routing water across massive scales, they do not yet forecast the street‐level information desired by local decision makers. Simultaneously, the increasing affordability of sensors has made it possible for even small communities to measure the state of their watersheds. However, these real‐time measurements are often not attached to a predictive model, thus making them less useful for applications like flood warnings. In this paper, we ask the question: how can highly localized forecasts be generated by fusing site‐scale sensor measurements with outputs from large‐scale models? Rather than altering the larger physical model, our approach uses the outputs of the unmodified model as the inputs to a dynamical system. To evaluate the approach, a case study is carried out across the U.S. state of Iowa using publicly available measurements from over 180 water level sensors and outputs from the National Water Model. The approach performs well across a third of the studied sites, as quantified by a high normalized root mean squared error. A performance classification is carried out based on Principal Component Analysis and Random Forests. We discuss how these results will enable stakeholders with local measurements to quickly benefit from large‐scale models without needing to run or modify the models themselves. The results are also placed into a broader sensor‐placement context to provide guidance on how investments into local measurements can be made to maximize predictive benefits.

Quantifying the Uncertainty Created by Non‐Transferable Model Calibrations Across Climate and Land Cover Scenarios: A Case Study With SWMM

“…An alternative to relying on historical calibration is to adopt data‐assimilation modeling approaches which can update model parameters in response to observations (Liu & Gupta, 2007; Merz et al., 2011; Pathiraja et al., 2016). Data assimilation is valuable for improving short‐term predictions in response to non‐stationarity or simply in response to more observational data availability (e.g., model “learning”; Fries & Kerkez, 2018; Hutton et al., 2014; Milly et al., 2008)—an approach with strong synergies to “adaptive management” philosophies (Dietze et al., 2018). However, data assimilation is necessarily data‐hungry, limiting its application to well observed systems.…”

The convergence of AI, IoT, and big data for advancing flood analytics research

“…IFIS provides real-time information on streams and weather conditions that incorporates advanced rainfall-runoff models for flood prediction and mapping. Fries and Kerkez (2018) used water level sensors across the state of Iowa and outputs from the National Water Model (NWM) to dynamically map largescale models to site-scale forecasts for flood warnings. In a consequence, Barker and Macleod (2019) developed a prototype as a real-time social geodata pipeline for flood data collection and visualization across Scotland.…”