./untitled

Profile Name

Hello, I am అభిరామ్‌ ముళ్ళపూడి (Abhiram Mullapudi). I develop autonomous water systems; think self-driving cars, but for water infrastructure. These autonomous water systems will monitor and operate themselves to mitigate flash floods, ensure access to safe drinking water, and improve the efficiency of water treatment processes. I currently work at Xylem Vue as a Hydraulic Optimization and Control Engineer. At my job, I design machine learning algorithms and develop software for distilling actionable intelligence from data. In addition, I develop firmware and hardware for wireless monitoring of water networks. I have a Ph.D. in civil engineering, specializing in intelligent systems, from the University of Michigan, Ann Arbor, where I was fortunate to have been advised by Prof. Branko Kerkez. I did my bachelor's in civil engineering at Amrita Viswavidhya Peetham, Coimbatore.

I am a design nerd. I enjoy learning about urban systems, graphic design (especially fonts), and architecture. I like typesetting documents in LaTex. I also collect fountain pens and mechanical pencils. I am passionate about open source science and software; I extensively use and contribute to open-source tools. I enjoy tinkering with microcontrollers and sensors. I am obsessed with coffee and all its derivatives. I enjoy traveling, hiking, and exploring different cuisines. I love playing video games and reading fiction and occasionally non-fiction. I am currently learning French and Chess.

Email  /  CV  /  Github  /  Google Scholar  /  LinkedIn


Research

I am interested in optimization, real-time control, and machine learning, and their application for addressing water challenges. I also enjoy building wireless sensor networks: designing backend infrastructure, prototyping sensors, and laying out custom hardware.

Publications

Bayes

Bayesian optimization for shaping the response of stormwater systems


Abhiram Mullapudi, Branko Kerkez

In preparation, 2022

poster


Bayesian optimization is a automated data-driven approach for identifying a control strategy that achieves the desired response from the stormwater network.

pystorms

pystorms : Simulation sandbox for the evaluation and design of stormwater control algorithms


Sara P. Rimer, Abhiram Mullapudi, Sara C. Troutman, Gregory Ewing, Jeffrey M. Sadler, Bryant E. McDonnell, Ruben Kertesz, Jonathan L. Goodall, Jon M. Hathaway, Branko Kerkez

In preparation, 2022

code / manuscript/ webpage


pystorms provides a curated collection of stormwater control scenarios to enable the development and quantitative comparison of stormwater control algorithms.

pyswmm

Improvement of phosphorus removal in bioretention cells using real-time control


Brooke E. Mason, Abhiram Mullapudi, Cyndee L. Gruden, Branko Kerkez

Urban Water Journal, 2022

code/ paper


Real-time control improves the nutrient capture efficiency of bioretention cells, and thus reducing the size of bioretention cells needed for nutrient removal.

pyswmm

StormReactor: An open-source Python package for the integrated modeling of water quality and water balance


Brooke E. Mason, Abhiram Mullapudi, Branko Kerkez

Environmental Modelling and Software, 2021

code/ manuscript


StormReactor is a python package for updating pollutant concentrations in EPA-SWMM durng simulations.

pyswmm

PySWMM : The Python Interface to Stormwater Management Model (SWMM)


Bryant E. McDonnell, Katherine Ratliff, Michael E. Tryby, Jennifer Jia Xin Wu, Abhiram Mullapudi

Journal of Open Source Software, 2020

code / manuscript


pyswmm is a python wrapper for interfacing with US EPA's Stormwater Management Model.

deeprl

Deep Reinforcement Learning for the Real Time Control of Stormwater Systems


Abhiram Mullapudi, Matthew J. Lewis, Cyndee L. Gruden, Branko Kerkez

Advances in Water Resources, 2020

code / manuscript


Reinforcement learning can be used for creating autonomous stormwater systems that can dynamically change their behavior based on the state of the watershed for achieving system scale objectives.

deeprl

rrcf : Implementation of the Robust Random Cut Forest algorithm for anomaly detection on streams


Matt D. Bartos, Abhiram Mullapudi, Sara C. Troutman

Journal of Open Source Software, 2019

code / manuscript


Anomalies in the streaming data can be detected by estimating the shift in the structure of the random forest caused by the addition of a new data point.

deeprl

Shaping streamflow using a real-time stormwater control network


Abhiram Mullapudi, Matt D. Bartos, Brandon P. Wong, Branko Kerkez

Sensors, 2018

manuscript


Response of a stormwater network can be precisely shaped with the data from a wireless sensor network.

deeprl

Building a theory for smart stormwater systems


Abhiram Mullapudi, Brandon P. Wong, Branko Kerkez

Environmental Science: Water Research and Technology, 2017

code / manuscript


By re-imagining physical watersheds as a network of interconnected systems, they can be dynamically reconfigured in real-time to target the removal of specific pollutants.