Skip to main content

Computational Informatics

in this section

Section Navigation

In This Section:

cominf

Big data is arguably a major focus in the next round of the transformation of information technology in industry. With the recent development of the Internet of Things, wireless sensors, clouds, mobile devices, e-commerce, and smart manufacturing, the amount of data collected and stored has grown exponentially. Manufacturing process operation databases are massive because of the use of process operation and control computers and information systems. The diversity of process measurement technologies from conventional process sensors to images, videos, and indirect measurement technologies has compounded the variety, volume, and complexity of process big data. The Computer Informatics specialization lies at the interface between process engineering and data science (or informatics). It teaches students data analytics skills to derive knowledge and information from mass process data, as well as decision-support tools for solving real operation problems in the era of big data. Two courses (“CHEME 6800: Computational Optimization” and “CHEME 6880: Industrial Big Data Analytics and Machine Learning”) are specially designed and developed for this specialization and train students with relevant methodologies and skills.

Faculty involved and related projects:
Prof. Paulette Clancy's laboratory is one of the leading groups in the country studying atomic- and molecular-scale modeling of semiconductor materials. Her team focuses on prediction and insight regarding the link between materials design and properties, allowing them to suggest processing conditions and tailored materials to fulfill a desired set of constraints. Her primary current foci are novel materials for (1) photovoltaic applications for solar cells and (2) laser annealing of semiconductors and porous low-k materials. 

Prof. Fernando Escobedo's research group is at the forefront of contributors to novel methods for simulation of both thermodynamic data (like free-energies and microstructure) and kinetic information (like transition mechanisms and rate constants) from molecular-level models of complex materials. His current interests center on establishing structure-property relationships for polymeric and colloidal materials. The ultimate goal of generating such new fundamental knowledge is to improve the engineering of materials of desirable or "super" properties that originate in the creation of special types of structural order or the control of phase transitions. 

Prof. Tobias Hanrath's research efforts focus on the fundamental study of optoelectronic properties of semiconductor nanocrystals. This work is inspired by the potential application of these materials in solar energy conversion and energy storage devices. The semiconductor nanocrystals used in this work provide a diverse set of building blocks whose electronic and optical properties differ from their bulk counterparts due to the spatial wavefunction confinement. 

Prof. Jeffrey Varner's lab studies metabolic and signal transduction pathways that are important in technology and human health using experimental and computational tools. They focus on new technologies for the production of complex therapeutic proteins, pathways associated with trauma, and pathways involved with a variety of human cancers. They work with diverse partners from academics, industry, government, and clinical practice.

Prof. Fengqi You's research on advanced computational models, optimization algorithms, statistical machine learning methods, and systems analysis tools for practically important and fundamental problems on process manufacturing, data science, smart agriculture, energy systems, and sustainability. The research work at Process-Energy-Environmental Systems Engineering (PEESE) lab provides a balance between theory, computation and real world applications.

The specialization in Computational Informatics is designed to train students in data science skills and data analytics in the context of problems of interest to chemical engineering.1,2 This sample curriculum satisfies the chemical engineering M.Eng. requirements and the specialization requirements.

Fall

Spring
CHEME 5500 Software Carpentry or equivalent programming proficiency course3 (core course requirement) 2-3 CHEME 6880         Industrial Big Data Analytics and Machine Learning 2
CHEME 5740 Probability, statistics, and data analysis for physical sciences (core course requirement) or equivalent5 2-3   Required CI focus area elective7 3
CHEME 6800       Computational Optimization or equivalent4 (core course requirement) 3-4   Required CI focus area elective7 3
  Required CI Focus Area Elective7 3   Free Elective8 3
Business Elective  Can be taken fall or spring 2-3 Business Elective Can be taken fall or spring 2-3
CHEME 5650 CI-related M.Eng. Project (can be taken spring semester) 3-6 CHEME 5650 CI-related M.Eng. Project (can be taken spring semester) 3-6
  Total 13-19   Total 14-18
Computational Informatics

1Minimum of 30 total credits

2At least 12 of these credits must be earned in courses listed as chemical engineering courses. This does not include credits earned for the M. Eng. project (more than three credits).

3Approved courses to satisfy the programming proficiency requirement are:

  • Any CS course (but this will not count towards the 30-credit M. Eng. requirement unless the course is at the 4000-or above level)
  • Demonstration of programming proficiency from a prior course. Note that prior courses based on Matlab will not satisfy this requirement. Courses in modern languages (e.g., Python or Julia) will be allowed, as will courses in traditional languages such as Java, C, C++, etc.

4Approved optimization courses include:

  • SYSEN 6800 Computational Optimization (fall) 4 credits
  • ORIE 5300 Optimization I (fall) 4 credits
  • ORIE 5310 Optimization II (spring) 4 credits

5Approved probability and statistics courses include:

  • BIOMG 8340 Quantitative Biology for Molecular Biology & Genetics (spring) 2 credits
  • BTRY 6010 Statistical Methods I (fall) 4 credits
  • CEE 3200 Engineering Computation (spring) 4 credits/or ENGRD 2700 Basic Engineering Probability and Statistics (fall/spring) 3 credits (cannot be counted towards the 30-credit M.Eng. requirement)

6Approved machine learning courses include:

  • CS 4780 Machine Learning for Intelligent Systems (spring) 4 credits
  • CS 4786 Machine Learning for Data Science (fall) 4 credits
  • ORIE 4740 Statistical Data Mining (spring) 4 credits
  • STSC 4740 Data Mining and Machine Learning (fall) 4 credits
  • CHEME 55XX Applied Machine Learning and Process Data Analytics [not offered AY17-18]

7Required CI Focus Area Electives: Students may choose a topic within Computational Informatics (CI) on which to focus their three required electives, or they may choose to take these three electives broadly among categories.  These focus sub-specialization topics are:

  • Computational Biology, Chemistry, or Bioinformatics
  • Process Systems and Data Analytics (i.e., optimization and statistical/machine learning for design, control and operations of chemical/energy processes)
  • Physical Analytics (i.e., high performance computing applications in science and engineering)

  Approved Computational Biology, Chemistry, and Bioinformatics Courses:

  • BEE 4600 Deterministic & Stochastic Modeling in Biological Engineering () 3 credits
  • BIOMG 3340 Computer Graphics and Molecular Biology (fall) 1 credit
  • BIOMG 6300 Math
  • MAE 6210 Adv. Math. Modeling-Biological Fluid Dynamics (spring) 3 credits
  • CHEME 7770 Adv. Biomolecular Engineering (spring) 3 credits
  • BTRY 6840 Computational Genetics and Genomics (fall) 4 credits
  • CHEME 5440 Systems Biology in Biotechnology and Medicine (spring) 3 credits
  • CHEME 7740/CHEME 4810/CHEME 5810 Computational Methods in Chemistry (spring) 4 credits

  Approved Process Systems and Data Analytics:

  • CEE 5970 Risk Analysis and Management (spring) 3 credits
  • CS 6780 Applied Machine Learning (spring) 4 credits
  • CHEME 4700 Process Control Strategies (spring) 3 credits
  • MATH 7740 Statistical Learning Theory (spring) 4 credits
  • ORIE 4740 Statistical Data Mining (spring) 4 credits
  • ORIE 4741 Learning with Big Messy Data (fall) 4 credits
  • ORIE 6127 Computational Issues in Large Scale Data-Driven Models (fall) 3 credits
  • ORIE 6300 Mathematical Programming I (fall) 4 credits
  • ORIE 6741 Bayesian Machine Learning (fall) 4 credits
  • STSCI 4780 Bayesian Data Analysis: Principles and Practice (spring) 4 credits
  • SYSEN 5100 Model Based Systems Engineering (fall) 4 credits
  • SYSEN 5200 Systems Analysis Behavior and Optimization (spring) 3 credits

  Approved Physical Analytics Courses:

  • CEE 6300 Computational Sim. of Flow and Transport in the Environment (spring) 3 credits
  • CHEME 7740/CHEM 4810 Principles of Molecular Simulation (spring) 3 credits
  • MAE 5230 Intermediate Fluid Dynamics with CFD (spring) 4 credits
  • MAE 5700 Finite Element Analysis for Mechanical & Aero. Design (fall) 4 credits
  • MAE 7150 Atomistic modeling of materials (fall) 4 credits
  • MAE 7840 Bayesian Scientific Computing (spring) 4 credits
  • MSE 5715 Engr. Quantum Mechanics (spring) 3 credits
  • MSE 5720 Computational Materials Science (fall) 3 credits
  • MSE 6400 Computational Combustion (spring) 4 credits

8Free elective(s) will be a requirement if the 30-credit criterion is not met.  It can be fulfilled from any other relevant area with the consent of the M.Eng. Director.

9Suitable business requirement courses include:

  • AEM 4120 Comp. Methods for Management and Econ. (fall) 3 credits
  • AEM 4190 Strategic Thinking (spring) 3 credits
  • AEM 4380 Entrepreneurial Strategy for Technology Ventures (spring) 2 credits
  • AEM 6061 Risk, Simulation, and Monte Carlo Methods (spring) 4 credits
  • CHEME 5720 Managing New Business Development (fall) 3 credits
  • CEE 5900 Project Management (spring) 3 credits
  • Any other course with the approval of the M.Eng. Director