Constructing a data-driven rainfall-runoff model

Tianfang Xu, Albert J. Valocchi, University of Illinois at Urbana-Champaign

This activity is part of the On the Cutting Edge Peer Reviewed Teaching Activities collection.

This activity was selected for the On the Cutting Edge Reviewed Teaching Collection

This activity has received positive reviews in a peer review process involving five review categories. The five categories included in the process are

Scientific Accuracy
Alignment of Learning Goals, Activities, and Assessments
Pedagogic Effectiveness
Robustness (usability and dependability of all components)
Completeness of the ActivitySheet web page

For more information about the peer review process itself, please see https://serc.carleton.edu/teachearth/activity_review.html.

This page first made public: Jul 22, 2016

Introduction

The objective of this lesson is to introduce students to rainfall-runoff modeling using machine learning algorithms. In this lesson, students will walk through the process of accessing data, visualizing the data, statistically analyzing the data and using machine learning software packages to construct rainfall-runoff models.

Intended Audience

This unit is intended for senior undergraduate and beginning graduate students in hydrology, civil and environmental engineering and earth sciences.

Conceptual Learning Outcomes

Understanding introductory rainfall-runoff modeling
Understanding basic time series and data analysis concepts
Basic understanding the concept of machine learning
Evaluation of model performance

Practical Learning Outcomes

Learn to use CUAHSI HydroClient to access and view hydrologic data
Learn to plot and analyze time series
Learn to use machine learning software to build simple models
Learn to calculate summary statistics of model prediction performance

Student Time Required

5 Hours

Supporting Reference Documents and Files

Time series Wikipedia page: https://en.wikipedia.org/wiki/Time_series

Autocorrelation Wikipedia page: https://en.wikipedia.org/wiki/Autocorrelation

Mitchell, T.M. 1997. Machine Learning. McGraw Hill.

Instructions

Please follow the following steps included in this unit. While a sample dataset is provided for a gaging station on Univ. Illinois campus, you are encouraged to download and analyze your own rainfall and runoff data.