contact details

    Dr Benjamin D. Youngman
    Senior Lecturer
    Statistics and Data Science Group
    Department of Mathematics and Statistics
    Faculty of Environment, Science and Economy
    Laver Building
    University of Exeter
    Exeter, UK

    research overview

    I am a Senior Lecturer in the Statistics and Data Science group in the University of Exeter's Department of Mathematics and Statistics. My research has recently been supported by the Willis Research Network and based on statistical methods for extreme values, typically applied to the modelling of natural hazards. In 2016 I won the Lloyd's Science of Risk Prize for a paper on a geostatistical extreme-value framework for fast simulation of natural hazard events.

    news

  • I'm currently advertising a NERC GW4 PhD studentship on 'Improved extreme climate indices for food security risk analysis' with Dan Bebber, Pete Falloon, Lina Mercado and Catherine Bradshaw. See its University of Exeter advert here or its FindAPhD advert here.
  • deform v1.0.0 is now available on CRAN: https://CRAN.R-project.org/package=deform. Read about it in the preprint here: https://arxiv.org/abs/2311.05272
  • The latest version of evgam is available of GitHub here and is easily installed in R with remotes::install_github("byoungman/evgam").

    • phd topics

  • If you're interested in a PhD on any of the topics below, do get in touch.
    • Statistical modelling of extreme values and events
    • Spatial statistics
    • Natural hazards
    • Parametric insurance

    • phd students

  • Michael Gillan with Stefan Siegert on 'Extreme value models for climate risk'.
  • Ayu Shabrina with David Stephenson on 'Extreme value modelling of climate model output'.

    • research projects

  • ADD-TREES. This project, led by Danny Williamson, aims to find solutions for net zero challenges through the development and use of AI. I'm leading work package 2, which focuses on developing statistical methods for downscaling climate data, which will be used to drive the JULES land surface model.
  • FORESEE (FOREcasting Sea statE Extremes). This project, led by Patrik Bohlinger of the Norwegian Meteorological Institute, aims to better understand, use, and communicate seasonal forecasting of extreme sea states.

    • publications

    preprints

  • Youngman, B. D. (2023). deform: An R Package for Nonstationary Spatial Gaussian Process Models by Deformations and Dimension Expansion. arXiv:2311.05272.

    • 2023

  • Chan, S. C., Kendon, E. J., Fowler, H. J., Youngman, B. D., Dale, M., & Short, C. (2023). New extreme rainfall projections for improved climate resilience of urban drainage systems. Climate Services, 30, 100375. DOI: 10.1016/j.cliser.2023.100375

    • 2022

  • Lockwood, J. F., Stringer, N., Thornton, H. E., Scaife, A. A., Bett, P. E., Collier, T., Comer, R., Dunstone, N., Gordon, M., Hermanson, L., Ineson, S., Kettleborough, J., Knight, J., Mancell, J., McLean, P., Smith, D., Wardle, T., Xavier, P., & Youngman, B. (2022). Predictability of European winter 2020/2021: Influence of a mid-winter sudden stratospheric warming. DOI: 10.1002/asl.1126
  • Youngman, B. D. (2022). evgam: An R package for Generalized Additive Extreme Value Models. Journal of Statistical Software. DOI: 10.18637/jss.v103.i03

    • 2021

  • Nothing.

    • 2020

  • Xiong X., Economou T. and Youngman B. D. (2020) Data fusion with Gaussian processes for estimation of environmental hazard events. Environmetrics. 2020;e2660. DOI: 10.1002/env.2660

    • 2019

  • Youngman, B. D. (2019). Generalized additive models for exceedances of high thresholds with an application to return level estimation for US wind gusts. Journal of the American Statistical Association 114(528), 1865–1879 DOI: 10.1080/01621459.2018.1529596.

    • 2018

  • Figueiredo, R., M. L. Martina, D. B. Stephenson, and B. D. Youngman (2018). A probabilistic paradigm for the parametric insurance of natural hazards. Risk Analysis 38(11), 2400–2414. DOI: 10.1111/risa.13122.
  • Khare, S., Z. Chalabi, and B. Youngman (2018). Spatio-temporal distribution of historical extreme winter temperatures in England and Scotland | a non-stationary extreme value analysis. Journal of Extreme Events 05 (01), 1750005. DOI: 10.1142/S2345737617500051.

    • 2017

  • Oakley, J. E. and B. D. Youngman (2017). Calibration of stochastic computer simulators using likelihood emulation. Technometrics 59 (1), 80-92. DOI: 10.1080/00401706.2015.1125391.
  • Youngman, B. D. and T. Economou (2017). Generalised additive point process models for natural hazard occurrence. Environmetrics 28 (4), e2444. DOI: 10.1002/env.2444.
  • Stephenson, D. B., A. Hunter, B. Youngman, and I. Cook (2017). Chapter 3 -towards a more dynamical paradigm for natural catastrophe risk modeling. In G. Michel (Ed.), Risk Modeling for Hazards and Disasters, pp. 63-77. Elsevier. DOI: 10.1016/C2015-0-01065-6.

    • 2016

  • Youngman, B. D. and D. B. Stephenson (2016). A geostatistical extreme-value framework for fast simulation of natural hazard events. Proceedings of the Royal Society of London A: Mathematical, Physical and Engineering Sciences 472 (2189). DOI: 10.1098/rspa.2015.0855

    • 2014

  • Roberts, J., A. Champion, L. Dawkins, K. Hodges, L. Shaffrey, D. Stephenson, M. Stringer, H. Thornton, and B. Youngman (2014). The XWS open access catalogue of extreme European windstorms from 1979 to 2012. Nat. Hazards Earth Syst. Sci 14, 2487-2501. DOI: 10.5194/nhess-14-2487-2014

    • software

  • deform

    • I have just created the deform R package for nonstationary Gaussian processes models for spatial data. The package uses spatial deformations or dimension expansions to bring a space where processes can be modelled as isotropic. The package is available on CRAN at https://cran.r-project.org/package=deform.

  • evgam

    • I have created the evgam R package for generalised additive extreme-value models. Click above for some examples. The package is available on CRAN at https://cran.r-project.org/package=evgam.

  • ppgam

    • Theo Economou and I developed a similar - yet slightly more basic - R package for for generalised additive point process models, which accompanies Youngman and Economou (2017). Click above for some examples. The package is available on CRAN at https://cran.r-project.org/package=ppgam.

  • recalibrate

    • This is a fairly simple R package for recalibrating spatial fields using observations and model output. The idea is that a spatial process has some true values that we want to infer from imperfect data. The code is motivated by, but generalises beyond, European windstorms.

    teaching

  • I am module lead for MTH3045: Statistical Computing. Click here to go to the module's webpage.
  • I am currently teaching classes for MTH1004: Probability, Statistics and Data. Notes for the module can be found on its ELE page.
  • I am module convenor for MTHM044: MMath Project in Statistics. Here's the module's ELE page.
  • I'm also module convenor for MTHM050: Research Project in Statistics. Here's the module's ELE page.