Thevar, Elango

Elango is the Founder and CEO of NEER.ai and has spent more than 18 years in the water sector. He founded NEER to bring an affordable digital water...

Joined:

About Thevar, Elango

Elango is the Founder and CEO of NEER.ai and has spent more than 18 years in the water sector. He founded NEER to bring an affordable digital water management platform for 8 billion people. He graduated from the University of Madras in Chemical Engineering and holds a MS in Environmental Engineering from Oklahoma State University. He finished his MBA at the University of Missouri-Kansas City.

Thevar, Elango

Titles from this speaker

Description: Application of Machine Learning in Stormwater Risk Management for the Johnson County...

Application of Machine Learning in Stormwater Risk Management for the Johnson County Stormwater Management Program, Kansas

Abstract

The Stormwater Management Program (SMP) is a Johnson County, Kansas program which partners with the 20 cities in the County to manage stormwater and is funded by a 1/10th of one percent, county-wide sales tax. It administers these funds on behalf of the Cities, historically by providing matching funds to Cities for eligible projects, including study, design, and construction projects. In 2016, SMP as part of new strategic asset management program implemented watershed-based approach to fund projects that incorporate flooding, water quality, and system management. Under 'System Management' program, SMP started funding inspection, rehabilitation, and replacement of stormwater asset projects. As part of this program, SMP developed a risk-based tool to prioritize stormwater assets. This tool is used to assign a prioritization score to all eligible assets contained in County-wide asset database. This prioritization score is calculated using Likelihood of Failure (LoF), Consequence of Failure (CoF), and total risk (Business Risk Score, BRE). The two fundamental building blocks for defining total risk (BRE) are LoF and CoF. LoF describes the chance of an asset failure occurring and CoF measures the severity of the impacts if an asset were to fail. Total Risk or BRE = LoF * CoF Currently, SMP employs a linear age-based degradation model and incorporates an adjustment factor for increased salt load in estimating LoF. to prioritize inspection of stormwater assets (hard assets). For rehab/replacement projects, field verified condition score is used. However, existing field verified condition rating systems like the National Association of Sewer Service Companies' (NASSCO) Pipeline Assessment and Certification Program (PACP) and Water Resource Commission (WRC) were initially developed for wastewater systems. These standard ratings do not capture the environment factors and other variables specific to stormwater pipes. Currently, no standardized methods exist for assessing the condition of stormwater pipes and structures in the U.S. Given these challenges, SMP engaged with NEER to utilize its cloud-based Machine Learning (ML) solution to identify the risk condition of the stormwater assets and implement a proactive data driven asset management program. As a part of this project, NEER developed a Machine Learning (ML) Model that is specific to Johnson County SMP to calculate LoF for all the hard assets such as inlets, junction boxes, bridges, culverts, enclosed gravity. All of these assets are represented either as Links or Nodes. During the ML model creation, all the data obtained from AIMS and local municipalities (physical, functional/operational) were standardized. The NEER team developed micro-ML models to populate several missing parameters for few nodes and links. In addition, several environmental parameters were also superimposed to the existing datasets. After the normalization of the datasets, the original datasets (113,124 links and 122,957 nodes) that had field verified conditions were selected for model training and validation. There were 39,814 links (35% of total links) and 44,600 nodes (36% of total nodes) that had field verified conditions. NEER was able to develop a best performing ML model using 80% of the data (field verified conditions data) for model training and the rest of the 20% of the data (field verified conditions data) for model validation. This ML model is able to predict LoF with an accuracy of 90% & 91% respectively for the existing nodes and links. This SMP specific LoF prediction ML model was configured to continuously train and optimize itself to improve accuracy over time. NEER also adopted the same methodology that is currently being used by SMP to calculate the CoF and Business Risk Exposure (BRE)/Total Risk score. This CoF and BRE/Total Risk score calculation was implemented in the NEER Platform, so that SMP can calculate CoF and BRE/Total Risk for each asset in Watershed Organization 1.

This paper was presented at the WEF Stormwater Summit, June 27-29, 2023.

SpeakerThevar, Elango

Presentation time

14:00:00

14:30:00

Session time

10:45:00

15:00:00

SessionSession 03: Applying Technology to Elevate Stormwater Management

Session number03

Session locationKansas City Convention Center

TopicSmart Solutions, Innovation and Technology in Stormwater Management

Author(s)

Thevar, Elango

Author(s)E. Thevar1; S. Smith2;

Author affiliation(s)NEER1; Johnson County, KS2;

SourceProceedings of the Water Environment Federation

Document typeConference Paper

PublisherWater Environment Federation

Print publication date Jun 2023

DOI10.2175/193864718825158953

Volume / Issue

Content sourceStormwater

Word count17

Description: Leveraging HEC-RAS Models for the Real Time Hydraulic Modeling and Flood Forecasting...

Leveraging HEC-RAS Models for the Real Time Hydraulic Modeling and Flood Forecasting for the Johnson County Stormwater Management Program, Kansas

Abstract

The Stormwater Management Program (SMP) is a Johnson County, Kansas program which partners with the 20 cities in the County to manage stormwater and is funded by a 1/10th of one percent, county-wide sales tax. It administers these funds on behalf of the Cities, historically by providing matching funds to Cities for eligible projects, including study, design, and construction projects. SMP has invested significantly on StormWatch Alert 2 systems (www.stormwatch.com) over the past 30 years to implement real-time early flood warning systems. SMP has funded the installation and maintenance of many of the sites throughout the region and has utilized the data generated from the system for SMP-sponsored studies and projects. SMP also funds a portion of the cost to maintain and improve the website. Johnson County owns 68 of the 108 sites in the system. In addition, City of Overland Park, Kansas Department of Transportation, and City of Kansas City, MO owns several sensors. Currently, SMP with the help of City of Overland Park uses manual process of forecasting flooding conditions and implements emergency management procedures within the county based on existing stream level and National Weather Service's forecasted weather information. However, this process is very tedious, time consuming and not reliable to accurately forecast future flood conditions. Given these challenges, SMP engaged with NEER for the pilot study to utilize its cloud-based Machine Learning (ML) solution to automatically forecast early flood warning system (up to 24 hours) for the Watershed Organization 1 using existing hydraulic models and StormWatch real time datasets. NEER obtained existing HEC-1 and HEC-RAS models from FEMA for Watershed Organization 1. After verifying the integrity of the models, NEER converted existing HEC-1 and HEC-RAS models into EPA-SWMM model. During the conversion process, NEER followed the standard engineering practices to update the existing hydrology (subbasin and storage data) and hydraulic (open channel geometry, culverts, and bridge data) characteristics. After updating all the parameters, the hydraulic model was calibrated using StormWatch gage data collected during 2016 to 2020. There are a variety of statistical measures used to measure the goodness-of-fit between a long term continuous measured and a modeled hydrograph. For this study, statistical measures Integral Square Error (ISE) and Nash'Sutcliffe efficiency (NSE) were used as a single, non-subjective, statistical measure of model calibration (https://www.chijournal.org/C414). Generally, calibration results showed very good to excellent NSE and ISE range for all the gage locations. After the calibration, NEER set up a continuous real time and forecasting stormwater simulation model. In this step, StormWatch gage data (rainfall and stage collected every 5 minute) was obtained and stored in a Time Series Database. In addition, the 24-hour forecasted rainfall data obtained from the National Weather Service was also used in forecasting the stage and water surface elevation along the Brush and Turkey Creek. This real time and forecasting model that is scheduled to run every 6 hours, provides a predicted and forecasted floodplain boundary, depth grid, water surface elevation grid, velocity grid, and flood severity grid. that can be used for operational decisions. The total number of buildings and roads flooded, and operational recommendations (such as closing of roads, and evacuation of buildings) for every 6 hours is stored and displayed in the dashboard.

This paper was presented at the WEF Stormwater Summit, June 27-29, 2023.

SpeakerThevar, Elango

Presentation time

10:45:00

11:15:00

Session time

10:45:00

15:00:00

SessionSession 03: Applying Technology to Elevate Stormwater Management

Session number03

Session locationKansas City Convention Center

TopicSmart Solutions, Innovation and Technology in Stormwater Management

Author(s)

Thevar, Elango

Author(s)E. Thevar1; S. Smith2;

Author affiliation(s)NEER1; Johnson County, KS2;

SourceProceedings of the Water Environment Federation

Document typeConference Paper

PublisherWater Environment Federation

Print publication date Jun 2023

DOI10.2175/193864718825158929

Volume / Issue

Content sourceStormwater

Word count21

Base text size -

Thevar, Elango

About Thevar, Elango

My Recent Activity