The Science

Emerging technologies such as machine learning, exascale computing and 5g communications are advancing key elements important for predicting watershed hydro-biogeochemical behavior, including watershed characterization, data, informatics, and modeling. This invited commentary describes and recommends a systematic community development of codesign strategies, whereby the emerging technologies could seamlessly weave together characterization, data, and modeling capabilities across scales—enabling two-way, near-real time feedback between observation and modeling systems.

The Impact

While society depends on watersheds for clean water, energy, agricultural productivity, and other benefits, state-of-the-art scientific tools are not yet regularly used to underpin resource management. Recent advances in emerging technologies—together with instrumented watershed observatories, open-science principles, and new modes of collaboration—offer significant potential to transform the ability to address complex scientific questions, develop generalizable insights, and propel accurate yet tractable approaches to predict watershed hydrobiogeochemical behavior. As resource managers struggle to make increasingly difficult decisions in the coming decades, it is hoped that the concepts described in this commentary will mobilize the scientific enterprise toward the systematic developments needed to provide actionable information over space and time scales useful for such decisions.

Summary

Several emerging technologies are now starting to reveal their promise for greatly enhancing the predictive understanding of watershed hydro-biogeochemical behavior, including machine learning, artificial intelligence, exascale computing, 5G wireless communications, and cloud data storage and compute capacity. The paper describes a codesign strategy to unify diverse characterization, data, and simulation capabilities, allowing near real-time, autonomous communication and feedback between modelling and field observation systems. Paired with watershed observatory networks, open science principles, and radical collaboration strategies, the codesign strategies are expected to enable rapid progress on challenging scientific questions, such as: how do different types of watersheds respond to different stressors, such as climate change, droughts, floods, wildfire, and land-use? How will multiple stressors impact sustainability of municipal, industry, food, and energy systems that rely on water? Can generalizable metrics of resilience be identified and tracked? What is the minimum but sufficient amount of information needed to predict watershed behavior at temporal and spatial scales critical for underpinning resource management decisions? While systematic incorporation of emerging technologies and adoption of new modes of collaboration will require substantial coordination, resources, and commitment to overcome technical, social, and organizational barriers, the many recent efforts focused on advancing collaborations and tools across watershed communities, observatories, and government agencies are encouraging.

Principal Investigator

Susan Hubbard
Lawrence Berkeley National Laboratory
sshubbard@lbl.gov

Program Manager

Jennifer Arrigo
U.S. Department of Energy, Biological and Environmental Research (SC-33)
Environmental System Science
jennifer.arrigo@science.doe.gov

Paul Bayer
U.S. Department of Energy, Biological and Environmental Research (SC-33)
Environmental System Science
paul.bayer@science.doe.gov

Funding

This work was conducted as part of the Watershed Function Scientific Focus Area at Lawrence Berkeley National Laboratory and was supported by the Office of Biological and Environmental Research (BER) Environmental System Science program(formerly, the Subsurface Biogeochemical Research program), within the U. S. Department of Energy’s (DOE) Office of Science under DE‐AC02‐05CH11231.

References