Geology topics

Alison P. Appling

Publications and source records attributed to Alison P. Appling.

At least 37 records · Page 2Linked to original sources

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 architecture (PGA) of LSTM models for uncertainty quantification in lake temperature modeling

This chapter focuses on meeting the need to produce neural network outputs that are physically consistent and also express uncertainties, a rare combination to date. It explains the effectiveness of physics-guided architecture - long-short-term-memory (PGA-LSTM) in achieving better generalizability and physical consistency over data collected from Lake Mendota in Wisconsin and Falling Creek Reservoir in Virginia, even with limited training data. Even though PGL formulations result in improvements in the generalization performance and lead to machine learning (ML) predictions that are more physically consistent, simply adding the physics-based loss function in the learning objective does not overcome the black-box nature of neural network architectures, which often involve arbitrary design choices. The temperature of water in a lake is a fundamental driver of lake biogeochemical processes, and it controls the growth, survival, and reproduction of fishes in the lake.

Virginia, Wisconsin↗

USGS2021

Deep learning approaches for improving prediction of daily stream temperature in data-scarce, unmonitored, and dammed basins

Basin-centric long short-term memory (LSTM) network models have recently been shown to be an exceptionally powerful tool for stream temperature (T s ) temporal prediction (training in one period and predicting in another period at the same sites). However, spatial extrapolation is a well-known challenge to modelling T s and it is uncertain how an LSTM-based daily T s model will perform in unmonitored or dammed basins. Here we compiled a new benchmark dataset consisting of >400 basins across the contiguous United States in different data availability groups (DAG, meaning the daily sampling frequency) with and without major dams, and studied how to assemble suitable training datasets for predictions in basins with or without temperature monitoring. For prediction in unmonitored basins (PUB), LSTM produced a root-mean-square error (RMSE) of 1.129°C and an R 2 of 0.983. While these metrics declined from LSTM's temporal prediction performance, they far surpassed traditional models' PUB values, and were competitive with traditional models' temporal prediction on calibrated sites. Even for unmonitored basins with major reservoirs, we obtained a median RMSE of 1.202°C and an R 2 of 0.984. For temporal prediction, the most suitable training set was the matching DAG that the basin could be grouped into (for example, the 60% DAG was most suitable for a basin with 61% data availability). However, for PUB, a training dataset including all basins with data was consistently preferred. An input-selection ensemble moderately mitigated attribute overfitting. Our results indicate there are influential latent processes not sufficiently described by the inputs (e.g., geology, wetland covers), but temporal fluctuations can still be predicted well, and LSTM appears to be a highly accurate T s modelling tool even for spatial extrapolation.

Hydrological Processes↗

USGS2021

Predicting water temperature dynamics of unmonitored lakes with meta-transfer learning

Most environmental data come from a minority of well-monitored sites. An ongoing challenge in the environmental sciences is transferring knowledge from monitored sites to unmonitored sites. Here, we demonstrate a novel transfer-learning framework that accurately predicts depth-specific temperature in unmonitored lakes (targets) by borrowing models from well-monitored lakes (sources). This method, meta-transfer learning (MTL), builds a meta-learning model to predict transfer performance from candidate source models to targets using lake attributes and candidates' past performance. We constructed source models at 145 well-monitored lakes using calibrated process-based (PB) modeling and a recently developed approach called process-guided deep learning (PGDL). We applied MTL to either PB or PGDL source models (PB-MTL or PGDL-MTL, respectively) to predict temperatures in 305 target lakes treated as unmonitored in the Upper Midwestern United States. We show significantly improved performance relative to the uncalibrated PB General Lake Model, where the median root mean squared error (RMSE) for the target lakes is 2.52°C. PB-MTL yielded a median RMSE of 2.43°C; PGDL-MTL yielded 2.16°C; and a PGDL-MTL ensemble of nine sources per target yielded 1.88°C. For sparsely monitored target lakes, PGDL-MTL often outperformed PGDL models trained on the target lakes themselves. Differences in maximum depth between the source and target were consistently the most important predictors. Our approach readily scales to thousands of lakes in the Midwestern United States, demonstrating that MTL with meaningful predictor variables and high-quality source models is a promising approach for many kinds of unmonitored systems and environmental variables.

Water Resources Research↗

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

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↗

USGS2020

Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data

Stream water temperature ( T s ) is a variable of critical importance for aquatic ecosystem health. T s is strongly affected by groundwater-surface water interactions which can be learned from streamflow records, but previously such information was challenging to effectively absorb with process-based models due to parameter equifinality. Based on the long short-term memory (LSTM) deep learning architecture, we developed a basin-centric lumped daily mean T s model, which was trained over 118 data-rich basins with no major dams in the conterminous United States, and showed strong results. At a national scale, we obtained a median root-mean-square error of 0.69°C, Nash–Sutcliffe model efficiency coefficient of 0.985, and correlation of 0.994, which are marked improvements over previous values reported in literature. The addition of streamflow observations as a model input strongly elevated the performance of this model. In the absence of measured streamflow, we showed that a two-stage model could be used, where simulated streamflow from a pre-trained LSTM model ( Q sim ) still benefited the T s model even though no new information was brought directly into the inputs of the T s model. The model indirectly used information learned from streamflow observations provided during the training of Q sim , potentially to improve internal representation of physically meaningful variables. Our results indicate that strong relationships exist between basin-averaged forcing variables, catchment attributes, and T s that can be simulated by a single model trained by data on the continental scale.

Environmental Research Letters↗

USGS2020

Application of the RSPARROW modeling tool to estimate total nitrogen sources to streams and evaluate source reduction management scenarios in the Grande River Basin, Brazil

Large-domain hydrological models are increasingly needed to support water-resource assessment and management in large river basins. Here, we describe results for the first Brazilian application of the SPAtially Referenced Regression On Watershed attributes (SPARROW) model using a new open-source modeling and interactive decision support system tool (RSPARROW) to quantify the origin, flux, and fate of total nitrogen (TN) in two sub-basins of the Grande River Basin (GRB; 43,000 km 2 ). Land under cultivation for sugar cane, urban land, and point source inputs from wastewater treatment plants was estimated to each contribute approximately 30% of the TN load at the outlet, with pasture land contributing about 10% of the load. Hypothetical assessments of wastewater treatment plant upgrades and the building of new facilities that could treat currently untreated urban runoff suggest that these management actions could potentially reduce loading at the outlet by as much as 20–25%. This study highlights the ability of SPARROW and the RSPARROW mapping tool to assist with the development and evaluation of management actions aimed at reducing nutrient pollution and eutrophication. The freely available RSPARROW modeling tool provides new opportunities to improve understanding of the sources, delivery, and transport of water-quality contaminants in watersheds throughout the world.

Grande River basin↗

USGS2019

Process-guided deep learning predictions of lake water temperature

The rapid growth of data in water resources has created new opportunities to accelerate knowledge discovery with the use of advanced deep learning tools. Hybrid models that integrate theory with state‐of‐the art empirical techniques have the potential to improve predictions while remaining true to physical laws. This paper evaluates the Process‐Guided Deep Learning (PGDL) hybrid modeling framework with a use‐case of predicting depth‐specific lake water temperatures. The PGDL model has three primary components: a deep learning model with temporal awareness (long short‐term memory recurrence), theory‐based feedback (model penalties for violating conversation of energy), and model pretraining to initialize the network with synthetic data (water temperature predictions from a process‐based model). In situ water temperatures were used to train the PGDL model, a deep learning (DL) model, and a process‐based (PB) model. Model performance was evaluated in various conditions, including when training data were sparse and when predictions were made outside of the range in the training data set. The PGDL model performance (as measured by root‐mean‐square error (RMSE)) was superior to DL and PB for two detailed study lakes, but only when pretraining data included greater variability than the training period. The PGDL model also performed well when extended to 68 lakes, with a median RMSE of 1.65 °C during the test period (DL: 1.78 °C, PB: 2.03 °C; in a small number of lakes PB or DL models were more accurate). This case‐study demonstrates that integrating scientific knowledge into deep learning tools shows promise for improving predictions of many important environmental variables.

Minnesota, Wisconsin↗

USGS2019

Detecting signals of large‐scale climate phenomena in discharge and nutrient loads in the Mississippi‐Atchafalaya River Basin

Agricultural runoff from the Mississippi‐Atchafalaya River Basin delivers nitrogen (N) and phosphorus (P) to the Gulf of Mexico, causing hypoxia, and climate drives interannual variation in nutrient loads. Climate phenomena such as El Niño–Southern Oscillation may influence nutrient export through effects on river flow, nutrient uptake, or biogeochemical transformation, but landscape variation at smaller spatial scales can mask climate signals in load or discharge time series within large river networks. We used multivariate autoregressive state‐space modeling to investigate climate signals in the long‐term record (1979–2014) of discharge, N, P, and SiO 2 loads at three nested spatial scales within the Mississippi‐Atchafalaya River Basin. We detected significant signals of El Niño–Southern Oscillation and land‐surface temperature anomalies in N loads but not discharge, SiO 2 , or P, suggesting that large‐scale climate phenomena contribute to interannual variation in nutrient loads through biogeochemical mechanisms beyond simple discharge‐load relationships.

Mississippi‐Atchafalaya River Basin↗

USGS2019

Metabolic rhythms in flowing waters: An approach for classifying river productivity regimes

Although seasonal patterns of ecosystem productivity have been extensively described and analyzed with respect to their primary forcings in terrestrial and marine systems, comparatively little is known about these same processes in rivers. However, it is now possible to perform a large‐scale synthesis on the patterns and drivers of river productivity regimes because of the recent sensor advances allowing for near‐continuous estimates of river productivity. Here, we explore a dataset of 47 U.S. rivers to examine whether there are characteristic river productivity regimes. We use classification approaches to develop a typology of productivity regimes and then use these regimes to examine differences with respect to potential controls of productivity. We identified two distinct metabolic regimes, which we named Summer Peak and Spring Peak Rivers, within our dataset. These regimes meaningfully differed in both the timing and magnitude of productivity and were robust to different approaches to classification. We also found that several variables, including watershed area and characteristics of water temperature or discharge, were able to predict the class membership of these regimes with modest accuracy. Our results support the presence of characteristic metabolic regimes and suggests that these regimes may have common sets of environmental controls. We present classification as one approach to begin exploring the productivity regimes of rivers. The strength of our approach is that it fully leverages these newly available high‐frequency productivity estimates to create classes that can be used to draw inferences about how the controls of river productivity differ between or within systems.

Limnology and Oceanography↗

USGS2019

Enhancement of primary production during drought in a temperate watershed is greater in larger rivers than headwater streams

Drought is common in rivers, yet how this disturbance regulates metabolic activity across network scales is largely unknown. Drought often lowers gross primary production (GPP) and ecosystem respiration (ER) in small headwaters but by contrast can enhance GPP and cause algal blooms in downstream estuaries. We estimated ecosystem metabolism across a nested network of 13 reaches from headwaters to the main stem of the Connecticut River from 2015 through 2017, which encompassed a pronounced drought. During drought, GPP and ER increased, but with greater enhancement in larger rivers. Responses of GPP and ER were partially due to warmer temperatures associated with drought, particularly in the larger rivers where temperatures during summer drought were > 10°C higher than typical summer baseflow. The larger rivers also had low canopy cover, which allowed primary producers to take advantage of lower turbidity and fewer cloudy days during drought. We conclude that GPP is enhanced by higher temperature, lower turbidity, and longer water residence times that are all a function of low discharge, but ecosystem response in temperate watersheds to these drivers depends on light availability regulated by riparian canopy cover. In larger rivers, GPP increased more than ER during drought, even leading to temporary autotrophy, an otherwise rare event in the typically light‐limited heterotrophic Connecticut River main stem. With climate change, rivers and streams may become warmer and drought frequency and severity may increase. Such changes may increase autotrophy in rivers with broad implications for carbon cycling and water quality in aquatic ecosystems.

Connecticut, Massachusetts, New Hampshire, Vermont↗

USGS2018

The metabolic regimes of 356 rivers in the United States

A national-scale quantification of metabolic energy flow in streams and rivers can improve understanding of the temporal dynamics of in-stream activity, links between energy cycling and ecosystem services, and the effects of human activities on aquatic metabolism. The two dominant terms in aquatic metabolism, gross primary production (GPP) and aerobic respiration (ER), have recently become practical to estimate for many sites due to improved modeling approaches and the availability of requisite model inputs in public datasets. We assembled inputs from the U.S. Geological Survey and National Aeronautics and Space Administration for October 2007 to January 2017. We then ran models to estimate daily GPP, ER, and the gas exchange rate coefficient for 356 streams and rivers across the continental United States. We also gathered potential explanatory variables and spatial information for cross-referencing this dataset with other datasets of watershed characteristics. This dataset offers a first national assessment of many-day time series of metabolic rates for up to 9 years per site, with a total of 490,907 site-days of estimates.

Scientific Data↗

USGS2018

Overcoming equifinality: Leveraging long time series for stream metabolism estimation

The foundational ecosystem processes of gross primary production (GPP) and ecosystem respiration (ER) cannot be measured directly but can be modeled in aquatic ecosystems from subdaily patterns of oxygen (O 2 ) concentrations. Because rivers and streams constantly exchange O 2 with the atmosphere, models must either use empirical estimates of the gas exchange rate coefficient ( K 600 ) or solve for all three parameters (GPP, ER, and K 600 ) simultaneously. Empirical measurements of K 600 require substantial field work and can still be inaccurate. Three-parameter models have suffered from equifinality, where good fits to O 2 data are achieved by many different parameter values, some unrealistic. We developed a new three-parameter, multiday model that ensures similar values for K 600 among days with similar physical conditions (e.g., discharge). Our new model overcomes the equifinality problem by (1) flexibly relating K 600 to discharge while permitting moderate daily deviations and (2) avoiding the oft-violated assumption that residuals in O 2 predictions are uncorrelated. We implemented this hierarchical state-space model and several competitor models in an open-source R package, streamMetabolizer . We then tested the models against both simulated and field data. Our new model reduces error by as much as 70% in daily estimates of K 600 , GPP, and ER. Further, accuracy benefits of multiday data sets require as few as 3 days of data. This approach facilitates more accurate metabolism estimates for more streams and days, enabling researchers to better quantify carbon fluxes, compare streams by their metabolic regimes, and investigate controls on aquatic activity.

Journal of Geophysical Research: Biogeosciences↗

USGS2017

The metabolic regimes of flowing waters

The processes and biomass that characterize any ecosystem are fundamentally constrained by the total amount of energy that is either fixed within or delivered across its boundaries. Ultimately, ecosystems may be understood and classified by their rates of total and net productivity and by the seasonal patterns of photosynthesis and respiration. Such understanding is well developed for terrestrial and lentic ecosystems but our understanding of ecosystem phenology has lagged well behind for rivers. The proliferation of reliable and inexpensive sensors for monitoring dissolved oxygen and carbon dioxide is underpinning a revolution in our understanding of the ecosystem energetics of rivers. Here, we synthesize our current understanding of the drivers and constraints on river metabolism, and set out a research agenda aimed at characterizing, classifying and modeling the current and future metabolic regimes of flowing waters.

Limnology and Oceanography↗