Skip to main content

Theory, Data Science and Systems

In recent years, the digital age has transformed chemical engineering—and vice versa—with an increasing use of “big data” and data science. When paired with theoretical principles, such as thermodynamics and transport phenomena, we can use big data and data science to further explore chemical engineering for research and industry applications.

Graphic of computer code

What is big data?

Big data refers to massive and complex data sets that tend to grow rapidly and usually cannot be handled by traditional database systems. Big data sets offer additional insights with large statistical impacts, but it also comes with greater challenges and unique complexity to consider.

What is chemical engineering data science?

Integrate mathematics and computational methods, such as machine learning and artificial intelligence, to analyze and harness data for applications in chemical and systems engineering.

With computational visualizations and actionable, data-driven insights, use data science and chemical engineering theory to:

  • Improve efficiency, safety, and quality in industrial processes.
  • Calculate and predict reaction pathways for sustainable, greener energy.
  • Transform raw data from sensors to improve insights from experimental research.
  • Predict molecular or system properties for material and pharmaceutical development, safety and stabilization checks, separation techniques, and more.

What is chemical systems engineering?

Design, optimize, and manage large and complex systems by combining engineering, business management and practical requirements, like energy or user needs. System application can range from physical systems, such as energy plants or waste management systems, to conceptual systems, like software frameworks or algorithms. At times, it can be simple as helping optimize a factory floor, or weighing cost and risk factors. Other times, it goes beyond a traditional manufacturing system, analyzing what problems need resolving, predicting failures or delays, and finding solutions to all of these problems. 

What will you do in chemical systems engineering?

Systems engineering emphasizes holistic thinking and considered the full lifecycle of a system, including:
Corn field

Generating raw materials

students at the 2019 Collegiate Wind Competition

Product design, testing and creation

Quality control

plastic scrap for recycling

Recycling

Algae blooms

Waste and environmental impact

Company co-founder Jarryd Featherman, Wenjia Wang, Hoya Ihara and co-founder Scott Rankin

Worker training and safety

Cost, shipping and scheduling

Solar panel on blue sky background

Energy requirements and sustainability

A closer look. What are some focus areas?

Computer and information research science is projected to grow 20% through 2034 according to the U.S. Bureau of Labor Statistics. Our researchers and alumni expertly apply computational tools and data science to solve complex challenges in chemical engineering. Learn about some of the methods they utilize below!
Note: One panel is always open. Activating an open panel will advance to the next panel. Use arrow keys to navigate between panels.

A subset of artificial intelligence, machine learning (ML) enables computers to learn from large data sets to make data-driven predictions and decisions, without being explicitly programmed for every scenario. With ML, we can train predictive models to screen for the best solvents for plastics recycling, design nanoparticles for drug delivery systems, detect toxic forever chemicals in water, and find new energy-efficient catalysts for chemical production.

Machine learning

Study and solve complex chemical problems using computer simulations, mathematical modeling and theoretical methods. With computational chemistry, we can predict catalytic and material properties, model reactions turning agriculture waste into hydrogen and fuel, and accelerate the discovery of sustainable electrolytes for batteries.

Graduate student Charles Carroll performing computational tests in the Cersonsky Lab.

Using chemical theories and principles to calculate force, reaction times, and motion of atoms and molecules, a computer can apply statistics, probability, and algorithms to predict and simulate molecular systems. With this information, we can optimize and assess the stability of proteins for drug design, analyze DNA to predict biological functions, study characteristics and properties to fashion new materials, test structure for nanoscale technology, and more.

Modeled protein from Van Len Research Group.

Create data-driven visual or mathematical representations of workflows to identify bottlenecks, inefficiencies and opportunities for improvement. With this information, we can structure processes and workflows to enhance performance, reduce costs, which can save valuable energy resources, make the workplace safer, mitigate environmental harm and waste disposal.

statistical analysis stock photo

Use mathematical principles and algorithms to simulate, analyze and solve complex problems involving fluid mechanics and flow of liquids and gases. Not only does this help us explore innovative applications of fluid mechanics research, it also reduces the need for physical testing which can be more costly and time intensive. For example, we can run simulations showing the dynamics of blood flow or drag reduction in order to study blood diseases or how drag on the molecular level affects polymer development.

supercomputer simulations of blood flow
Machine learning

Median Wage

With a Bachelor’s degree according to the Bureau of Labor Statistics in May 2024
US Dollars121,860
chemical engineering
US Dollars140,910
computer and information researcher
US Dollars109,660
health and safety engineering

Faculty

Our interdisciplinary computational research groups collaborate and work closely with experimentalist groups, targeting data to the needs of experiments and testing theories and data-driven conclusions. 

Styliani Avraamidou
circular economy, energy, multi-level, robust and supply chain optimization

Styliana Avraamidou

Duane H. and Dorothy M. Bluemke Assistant Professor

Rose Cersonsky
molecular modeling and simulation, applied mathematics, ML, self-assembly

Rose Cersonsky

Conway Assistant Professor

Michael Graham
computational dynamics

Mike Graham

Steenbock Professor, Harvey D. Spangler Professor & Vilas Distinguished Achievement Professor

Dan Klingenberg
Computational

Dan Klingenberg

Manos Mavrikakis
computational chemistry, sensors

Manos Mavrikakis

James A. Dumesic Professor Vilas Distinguished Achievement Professor

Joel Paulson
AI & ML, optimization, algorithms, control & experimental design

Joel Paulson

Gerald and Louise Battist Associate Professor

Ross Swaney
process design, modeling and optimization

Ross Swaney

Associate Professor

Reid Van Lehn
molecular simulations, solvent effects

Reid Van Lehn

Sobota Associate Professor

John Yin

John Yin

Vilas Distinguished Achievement Professor

Victor Zavala
Optimization, control, data science, energy and environmental systems

Victor Zavala

Baldovin-DaPra Professor

Affiliate faculty: Raman, Spagnolie

Research Centers and Institutes

Our faculty are leading and participating in a wide variety of interdisciplinary centers and institutes: