Sandtank-ML: An Educational Tool at the Interface of Hydrology and Machine Learning

Lisa K Gallagher,Laura E Condon,Calla Chennault,Sebastien Jourdain,Reed M Maxwell,Drew Lazzeri,Jill M Williams,Patrick O’Leary

doi:10.3390/w13233328

Lisa K Gallagher, Laura E Condon + Show 6 more

Open Access

https://doi.org/10.3390/w13233328

Copy DOI

Abstract

Hydrologists and water managers increasingly face challenges associated with extreme climatic events. At the same time, historic datasets for modeling contemporary and future hydrologic conditions are increasingly inadequate. Machine learning is one promising technological tool for navigating the challenges of understanding and managing contemporary hydrological systems. However, in addition to the technical challenges associated with effectively leveraging ML for understanding subsurface hydrological processes, practitioner skepticism and hesitancy surrounding ML presents a significant barrier to adoption of ML technologies among practitioners. In this paper, we discuss an educational application we have developed—Sandtank-ML—to be used as a training and educational tool aimed at building user confidence and supporting adoption of ML technologies among water managers. We argue that supporting the adoption of ML methods and technologies for subsurface hydrological investigations and management requires not only the development of robust technologic tools and approaches, but educational strategies and tools capable of building confidence among diverse users.

Highlights

Water is a driving force for extreme events, which are increasing in frequency and severity at an alarming rate
We presented animportance educational the interface of of machine learning a two examples is the of theapplication training data.atQuantity and quality data matters and MLthat models to see variety data examples to make about the best, most accurateML top hydrology can need be used toateach a of variety of user groups foundational predictions
These user examples mimic our method behind the main platas well as how Machine learning (ML) is leveraged to complement physics-based hydrological modeling

Summary

Introduction

Water is a driving force for extreme events, which are increasing in frequency and severity at an alarming rate. As of September 2021, there have been 18 weather and climate disaster events, each costing over one billion dollars [1]. Over half of the U.S is experiencing drought conditions [3], including the Colorado River, which is at risk of downstream user curtailments [4]. These extreme events put life, property, infrastructure, livelihoods, and our collective water future at risk. Researchers across scientific disciplines agree that climate change will drive the continued increase in the degree and frequency of extreme events [5]

Methods

Results

Conclusion