Alison Appling, Ph.D., (she/her) is a data scientist and ecologist who applies machine learning and other data-driven methods to predict and understand water resources dynamics.
Current Roles
- Project Manager: Predictive Understanding of Multiscale Processes (PUMP)
- Task Lead: Advancing Machine Learning and Data Assimilation, within the PUMP Project
Alison studies the movement of energy, carbon, and nutrients through rivers, lakes, and floodplains to better predict and understand variations in water quality over space and time.
As a machine learning modeler and biogeochemist, she seeks modeling advances that bring together scientific knowledge and data-driven models. “Process-guided deep learning” and “differentiable hydrology” are two approaches on which she collaborates.
As a data scientist, she conducts analyses in ways that are reproducible, efficient, and transparent, and she has developed tools and workflows to support others in these goals.
In her leadership roles, she facilitates fluid skill sharing within teams and communities of practice, challenges individuals to excel in their projects and careers, and coordinates across projects to realize the Water Mission Area’s vision of broadly reusable, integrated tools for predicting water quantity and quality across the nation.
Alison is based in State College, PA, and is a member of the Analysis and Prediction Branch in the Integrated Modeling and Prediction Division in the Water Mission Area. She is on the USGS career track called Equipment Development Grade Evaluation (EDGE).
Professional Experience
Development Ecologist and Data Scientist, U.S. Geological Survey, 2019-Present
Ecologist, U.S. Geological Survey, 2016-2019
Postdoctoral Fellow, USGS Powell Center and University of Wisconsin-Madison. Mentors: E. H. Stanley, J. S. Read, E. G. Stets, and R. O. Hall, 2015-2016
Postdoctoral Associate, University of New Hampshire. Mentor: W. H. McDowell, 2013-2015
Postdoctoral Associate, Duke University. Mentor: J. B. Heffernan, 2012-2013
Ph.D. Student and Teaching Assistant: Organismal Diversity, Aquatic Field Ecology, and General Microbiology, University Program in Ecology, Duke University, 2006-2012
Research Technician, Stanford University & Carnegie Institution of Washington, 2004-2006
Undergraduate Teaching Assistant: Programming Paradigms and Discrete Mathematics, Computer Science, Stanford University, 2001-2003
Education and Certifications
Ph.D. Ecology, 2012. Duke University, Durham, NC.
Connectivity Drives Function: Carbon and Nitrogen Dynamics in a Floodplain-Aquifer Ecosystem. Advisors: E. S. Bernhardt and R. B. Jackson
B.S. Symbolic Systems, 2004. Stanford University, Stanford, CA.
Coursework in computer science, decision analysis, logic, linguistics, and psychology.
Science and Products
Model Code, Outputs, and Supporting Data for Approaches to Process-Guided Deep Learning for Groundwater-Influenced Stream Temperature Predictions
Predictions and supporting data for network-wide 7-day ahead forecasts of water temperature in the Delaware River Basin
A deep learning model and associated data to support understanding and simulation of salinity dynamics in Delaware Bay
Examining the influence of deep learning architecture on generalizability for predicting stream temperature in the Delaware River Basin
Deep learning approaches for improving prediction of daily stream temperature in data-scarce, unmonitored, and dammed basins
Model predictions for heterogeneous stream-reservoir graph networks with data assimilation
Stream temperature predictions in the Delaware River Basin using pseudo-prospective learning and physical simulations
Data release: Predicting Water Temperature Dynamics of Unmonitored Lakes with Meta Transfer Learning (Provisional Data Release)
Multi-task Deep Learning for Water Temperature and Streamflow Prediction (ver. 1.1, June 2022)
Data to support water quality modeling efforts in the Delaware River Basin
Data release: Walleye Thermal Optical Habitat Area (TOHA) of selected Minnesota lakes
Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data
Differentiable modelling to unify machine learning and physical models for geosciences
Evaluating deep learning architecture and data assimilation for improving water temperature forecasts at unmonitored locations
Stream temperature prediction in a shifting environment: The influence of deep learning architecture
Near-term forecasts of stream temperature using deep learning and data assimilation in support of management decisions
Physics-guided architecture (PGA) of LSTM models for uncertainty quantification in lake temperature modeling
Long-term change in metabolism phenology in north temperate lakes
Can machine learning accelerate process understanding and decision-relevant predictions of river water quality?
Multi-task deep learning of daily streamflow and water temperature
Long-term suspended sediment and particulate organic carbon yields from the Reynolds Creek Experimental Watershed and Critical Zone Observatory
Machine learning for understanding inland water quantity, quality, and ecology
Modeling reservoir release using pseudo-prospective learning and physical simulations to predict water temperature
Physics-guided machine learning from simulation data: An application in modeling lake and river systems
Non-USGS Publications**
**Disclaimer: The views expressed in Non-USGS publications are those of the author and do not represent the views of the USGS, Department of the Interior, or the U.S. Government.
Science and Products
- Data
Filter Total Items: 13
Model Code, Outputs, and Supporting Data for Approaches to Process-Guided Deep Learning for Groundwater-Influenced Stream Temperature Predictions
This model archive provides all data, code, and modeling results used in Barclay and others (2023) to assess the ability of process-guided deep learning stream temperature models to accurately incorporate groundwater-discharge processes. We assessed the performance of an existing process-guided deep learning stream temperature model of the Delaware River Basin (USA) and explored four approaches foPredictions and supporting data for network-wide 7-day ahead forecasts of water temperature in the Delaware River Basin
Daily maximum water temperature predictions in the Delaware River Basin (DRB) can inform decision makers who can use cold-water reservoir releases to maintain thermal habitat for sensitive fish species. This data release contains the forcings and outputs of 7-day ahead maximum water temperature forecasting models that makes predictions at 70 river reaches in the upper DRB. The modeling approach inA deep learning model and associated data to support understanding and simulation of salinity dynamics in Delaware Bay
Salinity dynamics in the Delaware Bay estuary are a critical water quality concern as elevated salinity can damage infrastructure and threaten drinking water supplies. Current state-of-the-art modeling approaches use hydrodynamic models, which can produce accurate results but are limited by significant computational costs. We developed a machine learning (ML) model to predict the 250 mg/L Cl- isocExamining the influence of deep learning architecture on generalizability for predicting stream temperature in the Delaware River Basin
This data release and model archive provides all data, code, and modelling results used in Topp et al. (2023) to examine the influence of deep learning architecture on generalizability when predicting stream temperature in the Delaware River Basin (DRB). Briefly, we modeled stream temperature in the DRB using two spatially and temporally aware process guided deep learning models (a recurrent graphDeep learning approaches for improving prediction of daily stream temperature in data-scarce, unmonitored, and dammed basins
This data release provides all data and code used in Rahmani et al. (2021b) to model stream temperature and assess results. Briefly, we modeled stream temperature at sites across the continental United States using deep learning methods. The associated manuscript explores the prediction challenges posed by reservoirs, the value of additional training sites when predicting in gaged vs ungaged sitesModel predictions for heterogeneous stream-reservoir graph networks with data assimilation
This data release provides the predictions from stream temperature models described in Chen et al. 2021. Briefly, various deep learning and process-guided deep learning models were built to test improved performance of stream temperature predictions below reservoirs in the Delaware River Basin. The spatial extent of predictions was restricted to streams above the Delaware River at Lordville, NY, aStream temperature predictions in the Delaware River Basin using pseudo-prospective learning and physical simulations
Stream networks with reservoirs provide a particularly hard modeling challenge because reservoirs can decouple physical processes (e.g., water temperature dynamics in streams) from atmospheric signals. Including observed reservoir releases as inputs to models can improve water temperature predictions below reservoirs, but many reservoirs are not well-observed. This data release contains predictionData release: Predicting Water Temperature Dynamics of Unmonitored Lakes with Meta Transfer Learning (Provisional Data Release)
These data are preliminary or provisional and are subject to revision. They are being provided to meet the need for timely best science. The data have not received final approval by the U.S. Geological Survey (USGS) and are provided on the condition that neither the USGS nor the U.S. Government shall be held liable for any damages resulting from the authorized or unauthorized use of the data.Multi-task Deep Learning for Water Temperature and Streamflow Prediction (ver. 1.1, June 2022)
This item contains data and code used in experiments that produced the results for Sadler et. al (2022) (see below for full reference). We ran five experiments for the analysis, Experiment A, Experiment B, Experiment C, Experiment D, and Experiment AuxIn. Experiment A tested multi-task learning for predicting streamflow with 25 years of training data and using a different model for each of 101 sitData to support water quality modeling efforts in the Delaware River Basin
This data release contains information to support water quality modeling in the Delaware River Basin (DRB). These data support both process-based and machine learning approaches to water quality modeling, including the prediction of stream temperature. Reservoirs in the DRB serve an important role as a source of drinking water, but also affect downstream water quality. Therefore, this data releaseData release: Walleye Thermal Optical Habitat Area (TOHA) of selected Minnesota lakes
Climate change and land use change have been shown to influence lake temperatures and water clarity in different ways. To better understand the diversity of lake responses to climate change and give managers tools to manage individual lakes, we focused on improving prediction accuracy for daily water temperature profiles and optical habitat in 881 lakes in Minnesota during 1980-2018. The data areExploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data
This data release provides all data and code used in Rahmani et al. (2020) to model stream temperature and assess results. Briefly, we used a subset of the USGS GAGES-II dataset as a test case for temperature prediction using deep learning methods. The associated manuscript explores the value of including stream discharge as a predictor in the temperature models, including the value of predicted d - Publications
Filter Total Items: 28
Differentiable modelling to unify machine learning and physical models for geosciences
Process-based modelling offers interpretability and physical consistency in many domains of geosciences but struggles to leverage large datasets efficiently. Machine-learning methods, especially deep networks, have strong predictive skills yet are unable to answer specific scientific questions. In this Perspective, we explore differentiable modelling as a pathway to dissolve the perceived barrierAuthorsChaopeng Shen, Alison P. Appling, Pierre Gentine, Toshiyuki Bandai, Hoshin Gupta, Alexandre Tartakovsky, Marco Baity-Jesi, Fabrizio Fenicia, Daniel Kifer, Li Li, Xiaofeng Liu, Wei Ren, Yi Zheng, Ciaran Harman, Martyn Clark, Matthew Farthing, Dapeng Feng, Praveen Kumar, Doaa Aboelyazeed, Farshid Rahmani, Yalan Song, Hylke E. Beck, Tadd Bindas, Dipankar Dwivedi, Kuai Fang, Marvin Höge, Chris Rackauckas, Binayak Mohanty, Tirthankar Roy, Chonggang Xu, Kathryn LawsonEvaluating deep learning architecture and data assimilation for improving water temperature forecasts at unmonitored locations
Deep learning (DL) models are increasingly used to forecast water quality variables for use in decision making. Ingesting recent observations of the forecasted variable has been shown to greatly increase model performance at monitored locations; however, observations are not collected at all locations, and methods are not yet well developed for DL models for optimally ingesting recent observationsAuthorsJacob Aaron Zwart, Jeremy Alejandro Diaz, Scott Douglas Hamshaw, Samantha K. Oliver, Jesse Cleveland Ross, Margaux Jeanne Sleckman, Alison P. Appling, Hayley R. Corson-Dosch, Xiaowei Jia, Jordan S Read, Jeffrey M Sadler, Theodore Paul Thompson, David Watkins, Elaheh (Ellie) WhiteStream temperature prediction in a shifting environment: The influence of deep learning architecture
Stream temperature is a fundamental control on ecosystem health. Recent efforts incorporating process guidance into deep learning models for predicting stream temperature have been shown to outperform existing statistical and physical models. This performance is in part because deep learning architectures can actively learn spatiotemporal relationships that govern how water and energy propagate thAuthorsSimon Nemer Topp, Janet R. Barclay, Jeremy Alejandro Diaz, Alexander Y. Sun, Xiaowei Jia, Daniel Lubin, Jeffrey M Sadler, Alison P. ApplingNear-term forecasts of stream temperature using deep learning and data assimilation in support of management decisions
Deep learning (DL) models are increasingly used to make accurate hindcasts of management-relevant variables, but they are less commonly used in forecasting applications. Data assimilation (DA) can be used for forecasts to leverage real-time observations, where the difference between model predictions and observations today is used to adjust the model to make better predictions tomorrow. In this usAuthorsJacob Aaron Zwart, Samantha K. Oliver, William Watkins, Jeffrey Michael Sadler, Alison P. Appling, Hayley R. Corson-Dosch, Xiaowei Jia, Vipin Kumar, Jordan ReadPhysics-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 ReservAuthorsArka Daw, R. Quinn Thomas, Cayelan C. Carey, Jordan Read, Alison P. Appling, Anuj KarpatneLong-term change in metabolism phenology in north temperate lakes
The phenology of dissolved oxygen (DO) dynamics and metabolism in north temperate lakes offers a basis for comparing metabolic cycles over multi-year time scales. Although proximal control over lake DO can be attributed to metabolism and physical processes, how those processes evolve over decades largely remains unexplored. Metabolism phenology may reveal the importance of coherence among lakes anAuthorsRobert Ladwig, Alison P. Appling, Austin D. Delany, Hilary A. Dugan, Qiantong Gao, Noah R. Lottig, Jemma Stachelek, Paul C. HansonCan 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 predAuthorsCharuleka Varadharajan, Alison P. Appling, Bhavna Arora, Danielle Christianson, Valerie Hendrix, Vipin Kumar, Aranildo R. Lima, Juliane Mueller, Samantha K. Oliver, Mohammed Ombadi, Talita Perciano, Jeffrey Michael Sadler, Helen Weierbach, Jared Willard, Zexuan Xu, Jacob Aaron ZwartMulti-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 facAuthorsJeffrey Michael Sadler, Alison P. Appling, Jordan Read, Samantha K. Oliver, Xiaowei Jia, Jacob Aaron Zwart, Vipin KumarLong-term suspended sediment and particulate organic carbon yields from the Reynolds Creek Experimental Watershed and Critical Zone Observatory
Long-term (>20 y) suspended sediment (SS) and particulate organic carbon (POC) records are relatively rare and yet are necessary for understanding linkages between climate, erosion and carbon export. We estimated long-term (>23 y) SS and POC yields from four nested catchments that ranged from <1 to 54 km2 in area across the Reynolds Creek Experimental Watershed and Critical Zone Observatory (RCEW-AuthorsKayla L Glossner, Kathleen A. Lohse, Alison P. Appling, Zane K Cram, Erin Murray, Sarah Godsey, Steve Van Vactor, Emma P McCorkle, Mark Seyfried, Frederick B PiersonMachine 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; estAuthorsAlison P. Appling, Samantha K. Oliver, Jordan Read, Jeffrey Michael Sadler, Jacob Aaron ZwartModeling reservoir release using pseudo-prospective learning and physical simulations to predict water temperature
This paper proposes a new data-driven method for predicting water temperature in stream networks with reservoirs. The water flows released from reservoirs greatly affect the water temperature of downstream river segments. However, the information of released water flow is often not available for many reservoirs, which makes it difficult for data-driven models to capture the impact to downstream riAuthorsXiaowei Jia, Shengyu Chen, Yiqun Xie, Haoyu Yang, Alison P. Appling, Samantha K. Oliver, Zhe JiangPhysics-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, theseAuthorsXiaowei Jia, Yiqun Xie, Sheng Li, Shengyu Chen, Jacob Aaron Zwart, Jeffrey Michael Sadler, Alison P. Appling, Samantha K. Oliver, Jordan ReadNon-USGS Publications**
J. S. Read, J. I. Walker, A. P. Appling, D. L. Blodgett, E. K. Read, and L. A. Winslow. 2015. geoknife: reproducible web-processing of large gridded datasets. Ecography. https://doi.org/10.1111/ecog.01880S.A. Sistla, A. P. Appling, A. M. Lewandowska, B. N. Taylor, and A. A. Wolf. 2015. Stoichiometric flexibility in response to fertilization along gradients of environmental and organismal nutrient richness. Oikos, 124: 949-959. https://doi.org/10.1111/oik.02385A. P. Appling, M. C. Leon, and W. H. McDowell. 2015. Reducing bias and quantifying uncertainty in watershed flux estimates: The R package loadflex. Ecosphere 6(12):269. https://doi.org/10.1890/ES14-00517.1A. P. Appling and J. B. Heffernan. 2014. Nutrient limitation and physiology mediate the fine-scale [de]coupling of biogeochemical cycles. The American Naturalist 184:384-406. https://doi.org/10.1086/677282A. P. Appling, E. S. Bernhardt, and J. A. Stanford. 2014. Floodplain biogeochemical mosaics: a multidimensional view of alluvial soils. Journal of Geophysical Research: Biogeosciences 119:2013JG002543. https://doi.org/10.1002/2013JG002543**Disclaimer: The views expressed in Non-USGS publications are those of the author and do not represent the views of the USGS, Department of the Interior, or the U.S. Government.