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

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.

How you teach changes who you reach: understanding the effect of teaching modality on student engagement, content interest, and learning in undergraduate hydrology

“…Prior hydrologic education investigations studying the impact of shifting teaching modalities away from lecturing have focused heavily on aggregated student perceptions of learning (Gallagher et al, 2021;Knoben & Spieler, 2022; S. W. Lyon et al, 2013;Merck et al, 2021;Pérez-Sánchez et al, 2022). The result that we observed was similar to prior studies noting improved student perceptions of learning as well as foundational research on studentled education.…”

“…7). Evaluating this result in the context of prior research on hydrology education is challenging because few studies have employed multiple methods of quantifying student outcomes beyond questionnaires distributed to students (Gallagher et al, 2021;Knoben & Spieler, 2022;S. W. Lyon et al, 2013;Merck et al, 2021;Pérez-Sánchez et al, 2022).…”

“…Integration of computer simulation into teaching exercises has long been explored for opportunities to increase student engagement above that of the lecture-centric approach (Burt & Butcher, 1986). Several studies focused on student appraisals of in-class activities suggest that course modules focused on hydrological simulations resulted in student perceptions of enriched educational experiences (Gallagher et al, 2021;Knoben & Spieler, 2022;S. W. Lyon et al, 2013;Merck et al, 2021;Pérez-Sánchez et al, 2022).…”

“…Another challenge is that prior studies place strong emphasis on group mean outcomes of hydrology courses (i.e., average perceptions, average assessment scores), rather than the outcomes of individuals (Gallagher et al, 2021;Knoben & Spieler, 2022;S. W. Lyon et al, 2013;Merck et al, 2021;Pérez-Sánchez et al, 2022).…”

The ParFlow Sandtank: An interactive educational tool making invisible groundwater visible

“…Although our development of the PFST began prior to the initial lockdown of 2020, we quickly saw that this tool could be highly useful under these rapidly changing circumstances that required educators to make extremely quick pivots to online teaching. In addition to the PFST model, we have developed a user manual, additional templates (described in Section Custom templates and additional functionality), and a machine learning teaching tool based on PFST, called Sandtank-ML (Gallagher et al, 2021).…”