Kevin Brandt

Title

Assistant Vice President for Research Cyberinfrastructure

Office Building

Morrill Hall

Office

208A

Mailing Address

Morrill Hall 208A
IT Research Computing-Box 2201
University Station
Brookings, SD 57007

Social Media Links

• LinkedIn
• X

Education

• Ph.D. in agricultural, biosystems and mechanical engineering | South Dakota State University
  • Dissertation Research: Modeling Algal Bloom Risk in Fresh Water Lakes Using Artificial Intelligence Deep Learning Networks (May 2024)
  • Dissertation Abstract: South Dakota has a wide diversity of freshwater lakes used for many purposes, including water consumption and recreational activities. Many of these lakes are threatened in the summer months with harmful blue-green algal bloom conditions that are adversely affecting use. This impairment increases oxygen depletion within the water body which is needed to sustain aquatic organisms and is also responsible for the further proliferation of harmful algal bloom conditions (HABs) that make a lake toxic for recreational use. Economic impacts can be devastating due to the loss of revenue resulting from the lack of lake use as a drinking water source and for recreational purposes. Early algal bloom prediction could provide critical information for water resources managers, state and federal agencies to aid in early detection for planning, potential pollution mitigation activities, and for enacting state and federal water quality standards associated with point and nonpoint sources of pollution.
  • This study aims to determine the factors contributing to the growth of hazardous algal blooms in freshwater lakes, including human activities, environmental conditions, and characteristics of the lake and surrounding land. To achieve this, the study will use historical spectral data and critical factors that increase the growth of HABs to develop deep neural network prediction models. These models will attempt to predict/forecast algal bloom risk zones in several freshwater lakes in eastern South Dakota. The accuracy of the models will be evaluated by comparing predicted chlorophyll-a measurements to actual measurements collected from the lakes through statistical analysis.
• M.S. in Agricultural and Biosystems Engineering | South Dakota State University
  • Research Thesis: Modeling of Sugarbeet Quality Using Vegetative Index, Statistical and Artificial Neural Networks
    2009, Activities and Societies: IEEE, ASABE
  • Scope: Five years of Landsat 5 and 7 multispectral data from over 1000 sugar beet fields.
  • Tested different vegetative index approaches and investigated the potential statistical link between remote sensing canopy and sucrose concentration.
    • Developed artificial neural network and conventional multiple linear regression models, and applied them to new data sets for whole-field sucrose concentration prediction analysis.
    • Examined the correlation of the artificial neural network and conventional multiple linear regression sucrose model prediction results with measured sucrose concentration, assessing model performance over multiple site-years.
    • Compared the effectiveness of multiple linear regression models to artificial neural network models for sucrose predictions.
• B.S. in agricultural and biosystems engineering | South Dakota State University

Academic Interests

• High performance computing
• Remote sensing, image processing and machine vision
• Methods: GIS, systems modeling and integration, spatial analysis, big data

Committees and Professional Memberships

Committees:

• University Strategic Planning Committee
• Northern Tier Network Consortium (NTNC) State Representative, Steering and Program Committee Member
• Great Plains Network (GPN): Cyberinfrastructure Program, University Representative
• XSEDE Campus Champion Coordinator, Region 3 Lead (North Dakota, South Dakota, Minnesota, Wisconsin, Iowa, Illinois)
• SDSU IT Committee

Professional Memberships:

• ASABE
• IEEE
• ACM
• Alpha Epsilon
• Order of the Engineer

Grants

Active Funded Initiatives:  

1. RCN:CIP: A Connect.CI-based Community-Wide Mentorship Network (CCMNet) for the Advancement of Science and Engineering Research and Education. (Role: Project PI)
   1. Award Number: 2227656; Principal Investigator: Kevin Brandt; Co-principal investigator: Laura Christopherson, Marisa Brazil, Torey Battelle, Vikram Gazula.
   2. Organization: South Dakota State University; NSF Organization: OAC Start Date: 1/01/2023; Award Amount: $999,797.
2. CC* Team: Great Plains Regional CyberTeam (Role: Local PI, CyberTeam Project Lead)
   1. Award Number: 1925681; Principal Investigator: Grant Scott; Co-Principal Investigator: Douglas Jennewein, Daniel Andresen, Derek Weitzel, Carrie Brown, David Swanson, James Deaton, Bradley Spitzbart, George Louthan, Henry Neeman, Kevin Brandt.
      1. Organization: University of Missouri-Columbia; NSF Organization: OAC Start Date: 7/01/2019; Award Amount: $1,399,479.00
3. CC* Regional: SD-REDI: The South Dakota Research and Education Data Interchange (Role: Local PI)
   1. Award Number: 2201822; Principal Investigator: Liza Clark; Co-Principal Investigator: Alyssa Kiesow, Debbi Bumpous, Kevin Brandt, Ryan Johnson.
   2. Organization: South Dakota Board of Regents; NSF Organization: OAC Start Date: 7/01/2022; Award Amount: $998,750.

Areas of Research

• Machine learning
• Remote sensing
• Precision agriculture

Publications

Products

1. “Cyberinfrastructure Facilitation Skills Training via the Virtual Residency Program | Practice and Experience in Advanced Research Computing.” Acm.org, 2020, DOI:10.1145/3311790.3396629
2. “Great Plains CyberTeam: A Regional Mentor Approach to Cyberinfrastructure Workforce Development and Advancement.” Aptaracorp.com, 2020. Accessed Jan. 12, 2021
3. Brandt, Kevin L. “Predictive Modeling of Sugarbeet Quality Using Vegetative Index, Statistical and Artificial Neural Network Methods.” Open PRAIRIE: Open Public Research Access Institutional Repository and Information Exchange, 2016. Accessed Jan. 12, 2021