Search USGS⌕ Search

Geology topics

Jacob Aaron Zwart

Publications and source records attributed to Jacob Aaron Zwart.

At least 37 records · Page 2Linked to original sources
USGS2022

Physics-guided graph meta learning for predicting water temperature and streamflow in stream networks

This paper proposes a graph-based meta learning approach to separately predict water quantity and quality variables for river segments in stream networks. Given the heterogeneous water dynamic patterns in large-scale basins, we introduce an additional meta-learning condition based on physical characteristics of stream segments, which allows learning different sets of initial parameters for different stream segments. Specifically, we develop a representation learning method that leverages physical simulations to embed the physical characteristics of each segment. The obtained embeddings are then used to cluster river segments and add the condition for the meta-learning process. We have tested the performance of the proposed method for predicting daily water temperature and streamflow for the Delaware River Basin (DRB) over a 14 year period. The results confirm the effectiveness of our method in predicting target variables even using sparse training samples. We also show that our method can achieve robust performance with different numbers of clusterings.

Conference Paper↗
USGS2022

Using near-term forecasts and uncertainty partitioning to inform prediction of oligotrophic lake cyanobacterial density

Near-term ecological forecasts provide resource managers advance notice of changes in ecosystem services, such as fisheries stocks, timber yields, or water quality. Importantly, ecological forecasts can identify where there is uncertainty in the forecasting system, which is necessary to improve forecast skill and guide interpretation of forecast results. Uncertainty partitioning identifies the relative contributions to total forecast variance introduced by different sources, including specification of the model structure, errors in driver data, and estimation of current states (initial conditions). Uncertainty partitioning could be particularly useful in improving forecasts of highly variable cyanobacterial densities, which are difficult to predict and present a persistent challenge for lake managers. As cyanobacteria can produce toxic and unsightly surface scums, advance warning when cyanobacterial densities are increasing could help managers mitigate water quality issues. Here, we fit 13 Bayesian state-space models to evaluate different hypotheses about cyanobacterial densities in a low nutrient lake that experiences sporadic surface scums of the toxin-producing cyanobacterium, Gloeotrichia echinulata . We used data from several summers of weekly cyanobacteria samples to identify dominant sources of uncertainty for near-term (1- to 4-week) forecasts of G. echinulata densities. Water temperature was an important predictor of cyanobacterial densities during model fitting and at the 4-week forecast horizon. However, no physical covariates improved model performance over a simple model including the previous week's densities in 1-week-ahead forecasts. Even the best fit models exhibited large variance in forecasted cyanobacterial densities and did not capture rare peak occurrences, indicating that significant explanatory variables when fitting models to historical data are not always effective for forecasting. Uncertainty partitioning revealed that model process specification and initial conditions dominated forecast uncertainty. These findings indicate that long-term studies of different cyanobacterial life stages and movement in the water column as well as measurements of drivers relevant to different life stages could improve model process representation of cyanobacteria abundance. In addition, improved observation protocols could better define initial conditions and reduce spatial misalignment of environmental data and cyanobacteria observations. Our results emphasize the importance of ecological forecasting principles and uncertainty partitioning to refine and understand predictive capacity across ecosystems.

New Hampshire↗
USGS2022

Can machine learning accelerate process understanding and decision-relevant predictions of river water quality?

The global decline of water quality in rivers and streams has resulted in a pressing need to design new watershed management strategies. Water quality can be affected by multiple stressors including population growth, land use change, global warming, and extreme events, with repercussions on human and ecosystem health. A scientific understanding of factors affecting riverine water quality and predictions at local to regional scales, and at sub-daily to decadal timescales are needed for optimal management of watersheds and river basins. Here, we discuss how machine learning (ML) can enable development of more accurate, computationally tractable, and scalable models for analysis and predictions of river water quality. We review relevant state-of-the art applications of ML for water quality models and discuss opportunities to improve the use of ML for emerging computational and mathematical methods for model selection, hyperparameter optimization, incorporating process knowledge into ML models, improving explainablity, uncertainty quantification, and model-data integration. We then present considerations for using ML to address water quality problems given their scale and complexity, available data and computational resources, and stakeholder needs. When combined with decades of process understanding, interdisciplinary advances in knowledge-guided ML, information theory, data integration, and analytics can help address fundamental science questions and enable decision-relevant predictions of riverine water quality.

Hydrological Processes↗
USGS2022

Measurement and variability of lake metabolism

Aim : The aim of this article is to provide an overview of what contributes to lake metabolism, a brief overview of methods for estimating lake metabolism, and drivers of metabolism variability within and across lakes. Main concepts covered : In this article, we describe the key drivers of within and across lake variability in metabolism including lake morphometry, nutrients, light availability, temperature, and organic matter and how these drivers shape lake metabolic patterns across Earth's biomes. Conclusion/Outlook : We end the article with how interacting factors influence lake metabolic rates and how recent and future global changes may influence lake metabolism patterns.

Book chapter↗
USGS2022

Machine learning for understanding inland water quantity, quality, and ecology

This chapter provides an overview of machine learning models and their applications to the science of inland waters. Such models serve a wide range of purposes for science and management: predicting water quality, quantity, or ecological dynamics across space, time, or hypothetical scenarios; vetting and distilling raw data for further modeling or analysis; generating and exploring hypotheses; estimating physically or biologically meaningful parameters for use in further modeling; and revealing patterns in complex, multidimensional data or model outputs. An important research frontier is the injection of limnological knowledge into machine-learning models, which has shown great promise for increasing such models’ accuracy, trustworthiness, and interpretability. Here we describe a few of the most powerful machine learning tools, describe best practices for employing these tools and injecting knowledge guidance, and give examples of their applications to advance understanding of inland waters.

Book chapter↗
USGS2022

Multi-task deep learning of daily streamflow and water temperature

Deep learning (DL) models can accurately predict many hydrologic variables including streamflow and water temperature; however, these models have typically predicted hydrologic variables independently. This study explored the benefits of modeling two interdependent variables, daily average streamflow and daily average stream water temperature, together using multi-task DL. A multi-task scaling factor controlled the relative contribution of the auxiliary variable's error to the overall loss during training. Our experiments examined the improvement in prediction accuracy of the multi-task approach using paired streamflow and water temperature data from sites across the conterminous United States. Our results showed that for 56 out of 101 sites, the best performing multi-task models performed better overall than the single-task models in terms of Nash-Sutcliffe efficiency for predicting streamflow with single-site models. For 43 sites, the best multi-task, single-site models made no significant difference in predicting streamflow. The multi-task approach had a smaller effect when applied to a model trained with data from 101 sites together, significantly improving performance for only 17 sites. The multi-task scaling factor was consequential in determining to what extent the multi-task approach was beneficial. A naïve selection of this factor led to significantly worse-performing models for 3 of 101 sites when predicting streamflow as the primary variable, and 47 of 53 sites when predicting stream temperature as the primary variable. We conclude that a multi-task approach can make more accurate predictions by leveraging information from interdependent hydrologic variables, but only for some sites, variables, and model configurations.

Water Resources Research↗
USGS2022

Physics-guided machine learning from simulation data: An application in modeling lake and river systems

This paper proposes a new physics-guided machine learning approach that incorporates the scientific knowledge in physics-based models into machine learning models. Physics-based models are widely used to study dynamical systems in a variety of scientific and engineering problems. Although they are built based on general physical laws that govern the relations from input to output variables, these models often produce biased simulations due to inaccurate parameterizations or approximations used to represent the true physics. In this paper, we aim to build a new data-driven framework to monitor dynamical systems by extracting general scientific knowledge embodied in simulation data generated by the physics-based model. To handle the bias in simulation data caused by imperfect parameterization, we propose to extract general physical relations jointly from multiple sets of simulations generated by a physics-based model under different physical parameters. In particular, we develop a spatio-temporal network architecture that uses its gating variables to capture the variation of physical parameters. We initialize this model using a pre-training strategy that helps discover common physical patterns shared by different sets of simulation data. Then we fine-tune it using limited observation data via a contrastive learning process. By leveraging the complementary strength of machine learning and domain knowledge, our method has been shown to produce accurate predictions, use less training samples and generalize to out-of-sample scenarios. We further show that the method can provide insights about the variation of physical parameters over space and time in two domain applications: predicting temperature in streams and predicting temperature in lakes.

Conference Paper↗
USGS2022

Physics-guided recurrent neural networks for predicting lake water temperature

This chapter presents a physics-guided recurrent neural network model (PGRNN) for predicting water temperature in lake systems. Standard machine learning (ML) methods, especially deep learning models, often require a large amount of labeled training samples, which are often not available in scientific problems due to the substantial human labor and material costs associated with data collection. ML models have found tremendous success in several commercial applications, e.g., computer vision and natural language processing. The chapter presents PGRNN as a general framework for modeling physical processes in engineering and environmental systems. The proposed PGRNN explicitly incorporates physical laws such as energy conservation or mass conservation. In particular, researchers started pursing this direction by using residual modeling, where an ML model is learned to predict the errors, or residuals, made by a physics-based model. Advanced ML models, especially deep learning models, often require a large amount of training data for tuning model parameters.

Book chapter↗
USGS2021

Estimating pelagic primary production in lakes: Comparison of 14C incubation and free-water O2 approaches

Historically, estimates of pelagic primary production in lake ecosystems were made by measuring the uptake of carbon-14 ( 14 C)-labeled inorganic carbon in samples incubated under laboratory or in situ conditions. However, incubation approaches are increasingly being replaced by methods that analyze diel changes in high-frequency in situ data such as free-water dissolved oxygen (O 2 ). While there is a rich literature on the comparison of approaches for estimating primary production using incubations (e.g., 14 C and O 2 bottle experiments), as well for approaches using high-frequency data (e.g., diel O 2 and CO 2 metabolism models), there are few direct comparisons of 14 C incubations and free-water O 2 approaches for estimating primary production. We used 20 lake-years of concurrent measurements of primary production quantified from high-frequency free-water O 2 data and 14 C incubations in four different lakes (4–7 years per lake) to compare these different approaches. Across all lakes, 61% of the 14 C production estimates were within the 95% credible intervals of the free-water O 2 production estimates. Error-in-variable regressions support the assumption that 14 C methods estimate a production value between gross primary production and net primary production and the bottle effect is constant across the entire range of production values considered here. There was little evidence that daily pelagic, epilimnetic estimates of primary production differed substantially based on the selection of free-water O 2 or 14 C approaches in these lakes during summer stratified conditions.

Limnology and Oceanography: Methods↗
USGS2021

Projected changes of regional lake hydrologic characteristics in response to 21st century climate change

Inland lakes are socially and ecologically important components of many regional landscapes. Exploring lake responses to plausible future climate scenarios can provide important information needed to inform stakeholders of likely effects of hydrologic changes on these waterbodies in coming decades. To assess potential climate effects on lake hydrology, we combined a previously published spatially explicit, processed-based hydrologic modeling framework implemented over the lake-rich landscape of the Northern Highlands Lake District within the United States with an ensemble of climate change scenarios for the 2050s (2041–2070) and 2080s (2071–2100). Model results quantify the effects of climate change on water budgets and lake stage elevations for 3692 lakes and highlight the importance of landscape and hydrologic setting for the response of specific lake types to climate change. All future climate projections resulted in loss of ice cover and snowpack as well as increased evaporation, but variability in climate projections (warmer conditions, wet winters combined with wet or dry summers) interacted with lake characteristics and landscape position to produce variable lake hydrologic changes. Water levels for drainage lakes (lakes with substantial surface water inflows and outflows) showed nearly no change, whereas minimum water levels for seepage lakes (minimal surface water fluxes) decreased by an average of up to 2.64 m by the end of the 21st century. Our physically based modeling approach is parsimonious and computationally efficient and can be applied to other lake-rich regions to investigate interregional variability in lake hydrologic response to future climate scenarios.

Michigan, Wisconsin↗
USGS2021

Physics-guided machine learning for scientific discovery: An application in simulating lake temperature profiles

Physics-based models are often used to study engineering and environmental systems. The ability to model these systems is the key to achieving our future environmental sustainability and improving the quality of human life. This article focuses on simulating lake water temperature, which is critical for understanding the impact of changing climate on aquatic ecosystems and assisting in aquatic resource management decisions. General Lake Model (GLM) is a state-of-the-art physics-based model used for addressing such problems. However, like other physics-based models used for studying scientific and engineering systems, it has several well-known limitations due to simplified representations of the physical processes being modeled or challenges in selecting appropriate parameters. While state-of-the-art machine learning models can sometimes outperform physics-based models given ample amount of training data, they can produce results that are physically inconsistent. This article proposes a physics-guided recurrent neural network model (PGRNN) that combines RNNs and physics-based models to leverage their complementary strengths and improves the modeling of physical processes. Specifically, we show that a PGRNN can improve prediction accuracy over that of physics-based models (by over 20% even with very little training data), while generating outputs consistent with physical laws. An important aspect of our PGRNN approach lies in its ability to incorporate the knowledge encoded in physics-based models. This allows training the PGRNN model using very few true observed data while also ensuring high prediction accuracy. Although we present and evaluate this methodology in the context of modeling the dynamics of temperature in lakes, it is applicable more widely to a range of scientific and engineering disciplines where physics-based (also known as mechanistic) models are used.

ACM/IMS Transactions on Data Science↗
USGS2021

Physics-guided recurrent graph model for predicting flow and temperature in river networks

This paper proposes a physics-guided machine learning approach that combines machine learning models and physics-based models to improve the prediction of water flow and temperature in river networks. We first build a recurrent graph network model to capture the interactions among multiple segments in the river network. Then we transfer knowledge from physics-based models to guide the learning of the machine learning model. We also propose a new loss function that balances the performance over different river segments. We demonstrate the effectiveness of the proposed method in predicting temperature and streamflow in a subset of the Delaware River Basin. In particular, the proposed method has brought a 33%/14% accuracy improvement over the state-of-the-art physics-based model and 24%/14% over traditional machine learning models (e.g., LSTM) in temperature/streamflow prediction using very sparse (0.1%) training data. The proposed method has also been shown to produce better performance when generalized to different seasons or river segments with different streamflow ranges.

Conference Paper↗
USGS2021

Graph-based reinforcement learning for active learning in real time: An application in modeling river networks

Effective training of advanced ML models requires large amounts of labeled data, which is often scarce in scientific problems given the substantial human labor and material cost to collect labeled data. This poses a challenge on determining when and where we should deploy measuring instruments (e.g., in-situ sensors) to collect labeled data efficiently. This problem differs from traditional pool-based active learning settings in that the labeling decisions have to be made immediately after we observe the input data that come in a time series. In this paper, we develop a real-time active learning method that uses the spatial and temporal contextual information to select representative query samples in a reinforcement learning framework. To reduce the need for large training data, we further propose to transfer the policy learned from simulation data which is generated by existing physics-based models. We demonstrate the effectiveness of the proposed method by predicting streamflow and water temperature in the Delaware River Basin given a limited budget for collecting labeled data. We further study the spatial and temporal distribution of selected samples to verify the ability of this method in selecting informative samples over space and time.

Conference Paper↗
USGS2021

The AEMON-J “Hacking Limnology” workshop series & virtual summit: Incorporating data science and open science in aquatic research

Following the 2020 “Virtual Summit: Incorporating Data Science and Open Science in Aquatic Research” (DSOS; Meyer and Zwart 2020 ), a grassroots group of scientists convened the 2nd Virtual DSOS Summit on 22–23 July 2021. DSOS combined forces with the Aquatic Ecosystem MOdeling Network - Junior (AEMON-J; https://github.com/aemon-j) to host a 4-d “Hacking Limnology” Workshop Series prior to the summit (13–16 July 2021). The aim was to focus more deeply on skill development and networking among early career researchers (ECRs), both of which are key to growing a workforce of data-intensive aquatic scientists (López Moreira M et al. in press; Meyer et al. 2021 a ). To support ECRs further, we hosted a virtual job board, where participants could note if they were either looking for employment or hiring for a position. Like the 2020 summit, there was high enthusiasm for both the summit and the workshops. In total, 686 people from over 50 countries registered for the AEMON-J Workshop Series and the DSOS Summit. Countries with the highest number of registrants included the United States (41%), Nigeria (20%), Canada (6%), Brazil (6%), and Germany (5%) (Fig. 1). To increase accessibility, there were no registration costs for the workshops and summit, and we centralized introductory training materials, coding scripts, and presentation recordings in one community website (https://aquaticdatasciopensci.github.io/; Fig. 2), which we hope will continue to support the AEMON-J and DSOS communities over time.

Limnology and Oceanography Bulletin↗
USGS2021

Partial differential equation driven dynamic graph networks for predicting stream water temperature

This paper presents a physics-guided machine learning approach that incorporates partial differential equations (PDEs) in a graph neural network model to improve the prediction of water temperature in river networks. The standard graph neural network model often uses pre-defined edge weights based on distance or similarity measures. Such static graph structure can be limited in capturing multiple processes in a physical system that interact and evolve over time. The limitation to represent underlying physical processes can severely affect the performance of the predictive model, especially when we have access to limited training data. To better capture the dynamic interactions among multiple segments in a river network, we built a dynamic graph model, where the graph structure is driven by the PDE that describes underlying physical processes. We further combine the dynamic graph structure and the recurrent layers to model temporal dependencies and improve the prediction. We demonstrate the effectiveness of the proposed method in a subnetwork of the Delaware River Basin. In particular, we show that the proposed method outperforms existing physics-based and machine learning models in temperature prediction using sparse observation data for training. The proposed method has also been shown to produce better performance when generalized to different seasons.

Conference Paper↗
USGS2021

Heterogeneous stream-reservoir graph networks with data assimilation

Accurate prediction of water temperature in streams is critical for monitoring and understanding biogeochemical and ecological processes in streams. Stream temperature is affected by weather patterns (such as solar radiation) and water flowing through the stream network. Additionally, stream temperature can be substantially affected by water releases from man-made reservoirs to downstream segments. In this paper, we propose a heterogeneous recurrent graph model to represent these interacting processes that underlie stream-reservoir networks and improve the prediction of water temperature in all river segments within a network. Because reservoir release data may be unavailable for certain reservoirs, we further develop a data assimilation mechanism to adjust the deep learning model states to correct for the prediction bias caused by reservoir releases. Our evaluation for the Delaware River Basin has demonstrated the superiority of our proposed method over multiple existing methods. We have extensively studied the effect of the data assimilation mechanism under different scenarios.

IEEE International Conference on Data Mining (ICDM↗
USGS2021

Using machine learning to develop a predictive understanding of the impacts of extreme water cycle perturbations on river water quality

This whitepaper addresses to two focal areas – (3) Insight gleaned from complex data using Artificial Intelligence (AI), and other advanced techniques (primary), and (2) Predictive modeling through the use of AI techniques and AI-derived model components (secondary). This topic is directly relevant to four DOE Earth and Environmental Systems Science Division Grand Challenges: integrated water cycle, biogeochemistry, drivers and responses in the Earth system, and data-model integration.

Technical Report↗