About

Take sessions anytime, at your own pace with unlimited course access for 30-days.

Not an advanced Python user? Register for the Python essentials for water on the link above before undertaking this advanced Python course.

In this course, attendees will learn how to perform; data wrangling and multivariate exploratory data analysis, time series analysis and data visualisation. Each session is hosted by experts in their field, who delve in-depth into the key topic, explaining best practice techniques and approaches. Practical examples and demonstrations are analysed, allowing attendees to apply the knowledge gained and learn hands-on how to use Python- in order to save you time, money and integrate systems effectively.

Details

Format 6+ hours of training recordings to step through via the learning platform
Cost AUD $695 (includes GST)
Code OD-21-3-012
Tags

Presenters

Luk Peeters

CSIRO

Luk has over 10 years research experience in environmental impact assessment and modelling groundwater dynamics at regional to continental scales for water resource management. His research features a... Read more

Chris Turnadge

CSIRO

Chris is an Adelaide-based hydrogeologist in Land and Water's Regional Scale Groundwater Analysis team. His research primarily involves the characterisation of various aspects of regional-scale ground... Read more

Vincent Post

Edinsi Groundwater & Flinders University

Vincent is a hydrogeologist with over 15 years of experience in Python programming. He uses it on a daily basis for many if not all of his tasks, such as working with logger data, preparation of model... Read more

This course is designed to be highly practical, with 6+ hours of training session recordings.

Course Contents

The course will cover 3 main topics across 3 parts.

Part 1 | Lead by Luk Peeters

Data wrangling and multivariate exploratory data analysis

1. Hydrochemistry data

  • Download data from GA’s website
  • Explore data through scatter plots
  • Make a Piper plot (and map)
  • Multivariate analysis: principal component analysis, clustering (touching on machine learning in scikit learn)

2. Exploratory Data Analysis APY Lands groundwater dataset

  • Load pre-compiled dataset
  • Summarise dataset
  • Visually explore relationships and test hypothesis in the dataset using violin-plots

3. Datacube: AWRA

  • Load dataset of Australian Water Resources Assessment model from Bureau of Meteorology website
  • Visualise and explore maps and time series of AWRA outputs
  • Multivariate analysis and visualisation

Part 2 | Lead by Chris Turnadge

Time series analysis

1. Data pre-processing

  • Using interpolation to fill gaps
  • Detection and removal of outliers
  • Resampling to higher or lower sampling resolution
  • Temporal differencing
  • Detrending data using time and frequency domain methods

2. Decomposing hydrograph data

  • Quantifying the relative contributions of component processes

3. Interpreting responses to time-lagged processes

  • Demonstration of convolution
  • Regression deconvolution

4. Interpreting responses to periodic processes

  • The discrete Fourier transform
  • Periodogram-based approaches
  • Harmonic least squares

Part 3 | Lead by Vincent Post

Data visualisation

1. Data visualisation and linking it with Google Earth
2. Visualisation of modelled flowpaths in 3D
3. Evaluation of pumping tests

Format

The course is delivered through units via the learning platform

  • 6+ hours of recordings
  • Pre-and-post-course materials to go through via the learning platform.
  • Exercises between the 3 parts.
  • Manual of the course and working model download/s.
  • Ability to access all the online course materials with unlimited course access for 30-days.

Preparation

Pre-course reading and video watching is encouraged.

Requirements

A good internet connection and software and downloads as described in the learning platform.

Outcome

On completion of the course attendees will be issued with a Certificate of Participation.

Register Now!

 

Refund Policy

Frequently Asked Questions (FAQ)