Digital Twin for Stream Gage (Proxy Stream gage)

Near real-time and accurate water flow information is critical for saving life and property from flood-related disasters. US Govt has deployed 9000 steam gages to provide water flow information. However, these stream gages break often. Moreover, the chances of stream gages breaking is higher during times of storm and flood. These are times when these are needed most.

Waterly Digital Twin use historical water flow data to train a Digital Twin for Watershed.

• The first stage builds a dataset of clustered stream gages and locations.

• Second stage will train the model and will generate a proxy for each stream gage in the watershed.

In an emergency situation when one more gage break, the digital twin will use train model+ data from working gages to generate real time prediction for water gages.

Data set:

https://waterdata.usgs.gov/nwis

Benefit

Monitoring when gage fails

Many of stream gage failure occur due to sudden flood, debris etc. So it is not easy to predict failure few weeks in advance. But if stream gage fails, machine learning based model can take over and predict water flow.

Paper published

Streamflow Hydrology Estimate Using Machine Learning (SHEM) Research paper published in Major Hydrology Journal JAWR

http://onlinelibrary.wiley.com/doi/10.1111/1752-1688.12555/abstract

Slides on Water Shed Digital Twin

Paper published

Abstract

Continuity and accuracy of near real-time streamflow gauge (streamgage) data are critical for flood forecasting, assessing imminent risk, and implementing flood mitigation activities. Without these data, decision makers and first responders are limited in their ability to effectively allocate resources, implement evacuations to save lives, and reduce property losses. The Streamflow Hydrology Estimate using Machine Learning (SHEM) is a new predictive model for providing accurate and timely proxy streamflow data for inoperative streamgages. SHEM relies on machine learning (“training”) to process and interpret large volumes (“big data”) of historic complex hydrologic information. Continually updated with real-time streamflow data, the model constructs a virtual dataset index of correlations and groups (clusters) of relationship correlations between selected streamgages in a watershed and under differing flow conditions. Using these datasets, SHEM interpolates estimated discharge and time data for any indexed streamgage that stops transmitting data. These estimates are continuously tested, scored, and revised using multiple regression analysis processes and methodologies. The SHEM model was tested in Idaho and Washington in four diverse watersheds, and the model's estimates were then compared to the actual recorded data for the same time period. Results from all watersheds revealed a high correlation, validating both the degree of accuracy and reliability of the model.