Tadd Bindas

State College, PA taddbindas@gmail.com

I work in large-scale hydrologic modeling, focusing on the intersection of deep learning and physical-based equations. My thesis work is applying a differentiable framework to the Muskingum-Cunge routing equation to learn river parameters and predict streamflow in ungauged areas.

Experience

Ph.D. Candidate

Pennsylvania State University, MHPI Lab
  • Developing graph-based neural networks to predict streamflow.
  • Assisting in managing team server resources.
  • Managing team GitHub repositories.
August 2020 - Present

Summer Institute Fellow

National Oceanic and Atmospheric Administration
June 2023 - July 2023

Hardware Engineer/Software Developer

IBM
  • Project lead on an automation application to improve support responses to customer calls and decrease log debug time.
  • Researched n-gram analysis techniques applied to error code prediction (PFA).
  • Managed a microcode release application that provides machine code to customers worldwide 24/7.
    • Managed a microcode release application that provides machine code to customers worldwide 24/7.
  • Worked as a software development intern from 2017-2019, developing debugging tools (GUI applications and scripts) using Java, Angular JS, Python, and Bash.
June 2017 - September 2020

Publications

Improving large-basin river routing using a differentiable Muskingum-Cunge model and physics-informed machine learning

Tadd Bindas, Wen-Ping Tsai, Jiangtao Liu, Farshid Rahmani, Dapeng Feng, Yuchen Bian, Kathryn Lawson, Chaopeng Shen
Under Review (2023)
In this paper, we explore the applications of a differentiable river routing model that was trained on daily discharge at a gauge downstream of a river network (with pretrained LSTM producing runoff as inputs to the graph) to learn a parameterization scheme for Manningʼs roughness coefficient (n)

Differentiable modelling to unify machine learning and physical models for geosciences

Chaopeng Shen, Alison P Appling, Pierre Gentine, Toshiyuki Bandai, Hoshin Gupta, Alexandre Tartakovsky, Marco Baity-Jesi, Fabrizio Fenicia, Daniel Kifer, Li Li, Xiaofeng Liu, Wei Ren, Yi Zheng, Ciaran J Harman, Martyn Clark, Matthew Farthing, Dapeng Feng, Praveen Kumar, Doaa Aboelyazeed, Farshid Rahmani, Yalan Song, Hylke E Beck, Tadd Bindas, Dipankar Dwivedi, Kuai Fang, Marvin Höge, Chris Rackauckas, Binayak Mohanty, Tirthankar Roy, Chonggang Xu, Kathryn Lawson
Nature Reviews Earth & Environment (2023)

Education

Pennsylvania State University

Doctor of Philosophy
Civil Engineering - Water Resources Engineering
  • Advisor: Dr. Chaopeng Shen
  • Comprehensive Exam Date: December 2022
  • Qualifying Exam Date: August 2021
August 2020 - Present

Marist College

Bachelor of Science
Computer Science - Software Engineering
Mathematics
  • Advisor: P. Zion Klos
  • Minor: Information Systems
  • Minor: Information Technology
  • Honors Program
  • Magna Cum Laude
August 2015 - May 2019

Presentations

Keynote Presentations

Improving large-basin river routing using a differentiable Muskingum-Cunge model and physics-informed machine learning
CIROH 1st annual Developers and Training Conference
Salt Lake City, UT 2023

Oral/Poster Presentations

On numerical methods and differentiable modeling for soil process representations in the NextGen Framework in arid regions (Oral)
2023 National Water Center Summer Institute Capstone
Tucaloosa, Alabama 2023

Improving large-basin river routing using a differentiable Muskingum-Cunge model and physics-informed machine learning (Oral)
The European Geophysical Union General Assembly
Vienna, Austria 2023

Improving Large-Basin Streamflow Simulation Using a Differentiable, Learnable Routing Model (Poster)
The American Geophysical Union Fall Meeting
Chicago, IL 2022

Improving Large-Basin Streamflow Simulation Using a Differentiable, Learnable Routing Model (Poster)
HydroML (Inaugural Symposium)
State College, PA 2022

Discovering Localized River Parameters via Physics-Guided Machine Learning and the Muskingum-Cunge Method (Poster)
The American Geophysical Union Fall Meeting
New Orleans, LA 2021

Routing flood waves through the river network utilizing physics-guided machine learning and the Muskingum-Cunge Method (Oral)
The American Geophysical Union Fall Meeting
Online Meeting 2020

Road Salts, and Faults: Evidence for Preferential Transport of High Salinity Groundwater via Geologic Structures that Connect Highways to Streams (Poster)
The American Geophysical Union Fall Meeting
San Francisco, CA 2020

Skills

Programming Languages & Tools
  • ArcGIS Pro
  • Bash
  • C
  • C++
  • MATLAB
  • PyTorch
  • R
Workflow
  • Experienced using Conda, Venv and Pipenv environments
  • PyCharm IDE Debugging
  • Agile Development

Interests

Outside of work, you'll find me at the gym working out or running/rowing outdoors. I am a Brazilian Jiu Jitsu Purple Belt under Ryan Gruhn. I rowed for the Marist College Crew team during undergrad (2015-2019).

On my rest days I enjoy cooking, sports, and DIY projects. I'm an avid BBQ enthusiast and try to have long cooks whenever they fit into my schedule.

Awards & Certifications

  • National Water Center Summer Institute Fellow National Water Center (2023)
  • 1st Annual Student Developer Awar CIROH Developers Conference (2023)
  • Graduate Scholarship for Excellence in Engineering Pennsylvania State University (2021)
  • University Graduate Fellowship Pennsylvania State University (2020)
  • REU AwardThe National Science Foundation (2018)
  • Eagle Scout (Bronze Palm)The Boy Scouts of America (2013)