University of Canterbury Data Repository
Browse

Estimating uncertainty in flood model outputs using machine learning informed by Monte Carlo analysis - Script version

Version 2 2025-01-19, 22:01
Version 1 2025-01-19, 19:04
dataset
posted on 2025-01-19, 22:01 authored by Martin NguyenMartin Nguyen, Matthew Wilson, Emily Lane, James Brasington, Rose PearsonRose Pearson

Necessary data here are used for training and testing the Bayes Neural Network with Bayes by Backprop models - model 1, 2, and 3. There are three big folders and a file:


  • Model1_classification_proportion folder: Model 1 is used to predict the labelled map identifying where is always, sometimes, and never flooded. This output will be used as an input for the model 2. There are three 3 files correspond to 5-, 10-, and 20-m resolutions under 7zip format. Please unzip them to see the previous results and to use them.
  • Model2_regression_proportion folder: Model 2 is used to predict the propotion of each pixel being flooded (the pF map) using the output of the model 1 as one of the inputs. There are three 3 files correspond to 5-, 10-, 20-m resolutions under 7zip format. Please unzip them to see the previous results and to use them.
  • Model3_regression_sd folder: Model 3 is used to predict the standard deviation of maximum flood depth (the sdMWD map). There are three 3 files correspond to 5-, 10-, and 20-m resolutions under 7zip format. Please unzip them to see the previous resutls and to use them.
  • Figures_Tables.7zip: Stores all figures an tables used in the publication.

Please also refer to here to see the scripts for generating the Monte Carlo uncertainty data for developing the model 1,2, and 3, and here to see the scripts/package to predict the pF and sdMWD maps. For the necessary data used to generate the Monte Carlo uncertainty data, it is too large to be uploaded (about 4TB), so please contact the author via tmn52@uclive.ac.nz.

Funding

MBIE Endeavour Research Programme

History

Department

  • Earth and Environment

College

  • Te Kaupeka Pūtaiao | Faculty of Science

Research Group

  • Geospatial Research Institute (GRI)

Usage metrics

    University of Canterbury Data Repository

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC