Jeremiah Johnson

Phone: (603) 641-4127
Office: Applied Engineering & Sciences, 88 Commercial Street, RM 105, Manchester, NH 03101

Jeremiah Johnson is an Assistant Professor of Data Science in the Department of Applied Engineering & Sciences.

Dr. Johnson is a mathematician and machine learning researcher specializing in neural networks and artificial intelligence. Dr. Johnson’s recent research spans a variety of application areas, including Bayesian modeling of water contamination, algorithmic style classification of fine art, automatic nucleus segmentation in microscopy images, and generative modeling techniques for structured prediction in computer vision. Dr. Johnson developed and now co-directs the Bachelor of Science in Analytics & Data Science, an innovative new program that offered on two campuses of the University of New Hampshire.

Dr. Johnson is an alumnus of the University of New Hampshire, earning his Ph.D in mathematics in 2010.


  • Ph.D., University of New Hampshire
  • M.S., University of New Hampshire
  • B.S., University of New Hampshire

Research Interests

  • Algebra
  • Artificial Intelligence/Cybernetics
  • Computational Mathematics
  • Deep Learning
  • Electronic Neural Networks
  • Topology

Courses Taught

  • COMP/DATA 750/850/750: Neural Networks
  • COMP/GRAD 899/900: Master's Thesis
  • DATA 557: Introduction to Analytics
  • DATA 674: Predictive Analytics I
  • DATA 675: Predictive Analytics II
  • DATA 790: Capstone Project
  • GRAD 900: Master's Continuing Research
  • MATH 420: Finite Mathematics
  • MATH 425: Calculus I
  • MATH 426: Calculus II
  • MATH 645: Linear Algebra for Application
  • UMIS 599: IndStdy/Capstone Project

Selected Publications

Johnson, J. W. (2022). A Diophantine Equation with an Elementary Solution. The College Mathematics Journal, 53(5), 361-363. doi:10.1080/07468342.2022.2118993

Halpin, P. A., Johnson, J., & Badoer, E. (2021). Students from a large Australian university use Twitter to identify difficult course concepts to review during face-to-face lectorial sessions. ADVANCES IN PHYSIOLOGY EDUCATION, 45(1), 10-17. doi:10.1152/advan.00147.2020

Johnson, J. W., Hari, S., Hampton, D., Connor, H. K., & Keesee, A. (2021). A Contrastive Learning Approach to Auroral Identification and Classification. 20TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2021), 772-777. doi:10.1109/ICMLA52953.2021.00128

Johnson, J. W. (2020). Benefits and Pitfalls of Jupyter Notebooks in the Classroom. In Proceedings of the 21st Annual Conference on Information Technology Education. ACM. doi:10.1145/3368308.3415397

Johnson, J., & Jin, K. (2020). Jupyter Notebooks in Education. In B. Lu (Ed.), The Journal of computing Sciences in Colleges Vol. 35. virtual: Association for Computing Machinery.

Mahmood, F., Xu, W., Durr, N. J., Johnson, J. W., & Yuille, A. (2019). Structured Prediction using cGANs with Fusion Discriminator. In Workshop on Deep Generative Models for Structured Prediction at
ICLR 2019
. Retrieved from

Mahmood, F., Johnson, J., Yang, Z., & Durr, N. J. (2019). Fusing attributes predicted via conditional GANs for improved skin lesion classification (Conference Presentation). In Unknown Conference (pp. 65). doi:10.1117/12.2513139

Johnson, J. W. (2018). Adapting Mask-RCNN for Automatic Nucleus Segmentation. In Proceedings of the 2019 Computer Vision Conference, Vol. 2. Retrieved from

Johnson, J. (2012). The Number of Group Homomorphisms from $D_m$ into $D_n$. The College Mathematics Journal, 44, 3. Retrieved from

Johnson, J., Hari, S., Pinto, V., Coughlan, M., Keesee, A., & Connor, H. (2020, December 1). Predicting Ground Magnetic Field Fluctuations from Geomagnetic Storm Data Using a Novel Transformer-Based Model. In American Geophysical Union Fall Meeting. Virtual.

Johnson, J., Coughlan, M., Keesee, A., Pinto, V., & Connor, H. (2020, December 1). Using Machine Learning and Geomagnetic Storm Data to Determine the Risk of GIC Occurrence. In American Geophysical Union Fall Meeting 2020.

Johnson, J. (n.d.). Teaching Neural Networks in the Deep Learning Era.

Johnson, J., Pinto, V., Keesee, A., Coughlan, M., Gadbois, M., & Connor, H. (2020, December 1). A Deep Learning Approach to the Forecasting of Ground Magnetic Field Perturbations at High and Mid Latitudes. In American Geophysical Union Fall Meeting 2020. Virtual.

Johnson, J., Coughlan, M., Keesee, A., Pinto, V., & Connor, H. (2020, July 20). Training a Neural Network Using Geomagnetic Storm Data to Predict Ground Magnetic Field Fluctuations. In Geospace Environment Modeling Workshop. Virtual.