About

Julianne Quinn is an Associate Professor at the University of Virginia School of Engineering and Applied Science, specializing in environmental systems engineering with a focus on water resources management. Her research involves applying mathematical concepts to improve the design and management of water systems, aiming to protect communities from natural hazards such as floods and droughts, while also safeguarding ecosystems from pollution and overuse. Her work emphasizes the use of advanced sensing and forecasting techniques to inform multi-objective optimization processes that address risk and uncertainty, identifying vulnerable sectors and populations and developing strategies to reduce multi-sectoral vulnerabilities. With a background that includes a B.S. from Columbia University and a Ph.D. from Cornell University, Quinn has contributed to advancing the understanding of hydrologic model uncertainty, reservoir operations, and integrated energy-water management. She has been recognized with awards such as the Best Policy Oriented Paper Award from the Journal of Water Resources Planning and Management and the UVA Civil Engineering Teaching Award. Her projects often focus on building community resilience through better coordination of water management and infrastructure, including efforts to empower local institutions to address climate-induced flood risks and promote sustainable economic development through renewable energy initiatives.

Research topics

• Computer Science
• Artificial Intelligence
• Environmental science
• Environmental resource management
• Economics
• Engineering
• Business
• Geography
• Sociology
• Management science
• Ecology
• Environmental economics
• Simulation
• Statistics
• Biology
• Natural resource economics
• Risk analysis (engineering)
• Mathematics

Selected publications

• Climate Sensitivity of Agricultural Water Demand Depends on Control Over Growing Season

  2026-03-13

  articleOpen accessSenior author

  Changes to the relationship between precipitation and temperature due to climate change can exacerbate water scarcity by increasing evapotranspiration and reducing runoff and soil moisture. These changes are especially significant for the agricultural sector, where complex interactions between precipitation, temperature, and growing season dynamics produce deep uncertainties in agricultural water demands. While watershed managers have traditionally relied on “top-down” planning scenarios, these typically do not provide insights into the system’s internal variability, nor do they capture the range of plausible, yet deeply uncertain, changes in the regional hydroclimate. To address this shortcoming, we develop a multivariate, multisite, copula-based stochastic weather generator for bottom-up exploratory modeling analysis of agricultural water resources systems. Paired with a regional consumptive use model, this generator allows us to investigate differential impacts of climate change on diverse agricultural producers and crops. We demonstrate this framework in the Upper Colorado River Basin within the state of Colorado. The explored hydroclimatology shows precipitation and temperature as highly variable and elevation-dependent relative to their historical annual averages, spanning -95% and +600% and –10°C and +19°C at the extrema, respectively. As a result, we observe substantial changes in irrigation water requirements for agricultural parcels across the basin between –100% and +250% relative to historical averages; all producers see irrigation requirements increase higher than their historical averages in more than 50% of our sampled realizations, with producers at lower elevations seeing this increase in more than 75% of them. Global sensitivity analysis reveals that adequate access to water impacts producers' effective growing season lengths and thereby which climate variables most control crop water requirement: producers with adequate water are most sensitive to changes in temperature mean and variance while producers without adequate water are most sensitive to changes in precipitation variance—and not mean—with temperature contributions halving. These findings demonstrate how differential vulnerability drivers underscore the need for stakeholder-specific assessments that account for spatial heterogeneity and decision-relevant uncertainties in agricultural water demand.

  PublisherDOI

• Climate Sensitivity of Agricultural Water Demand Depends on Control Over Growing Season: Implications for Producers in the Upper Colorado River Basin

  2026-01-14

  articleOpen accessSenior author

  Impacts of climate change on agricultural water demands are deeply uncertain due to complex interactions between precipitation, temperature, and growing season dynamics. For the different agricultural users experiencing these climate impacts, traditional top-down approaches using downscaled climate projections may underrepresent this uncertainty and mask spatial heterogeneities. To address this shortcoming, we develop a multivariate, multisite, copula-based stochastic weather generator for bottom-up exploratory modeling analysis of agricultural water resources systems. Paired with a regional consumptive use model, this generator allows us to investigate differential impacts of climate change on diverse agricultural producers and crops. We demonstrate this framework in the Upper Colorado River Basin within the state of Colorado. Results show that all producers see irrigation requirements increase higher than their historical averages in more than 50% of our sampled realizations, with producers at lower elevations seeing this increase in more than 75% of them. Global sensitivity analysis reveals that adequate access to water impacts producers’ effective growing season lengths and thereby which climate variables most control crop water requirement: producers with adequate water are most sensitive to changes in temperature mean and variance while producers without adequate water are most sensitive to changes in precipitation variance—and not mean—with temperature contributions halving. We also find that access to water is more important than crop type, elevation, or location when considering producer sensitivity to climate. These findings demonstrate how differential vulnerability drivers underscore the need for stakeholder-specific assessments that account for spatial heterogeneity and decision-relevant uncertainties in agricultural water demand.

  PublisherDOI

• Comparing strategies for training LSTM models for street-scale urban flood prediction in Norfolk, Virginia

  Journal of Hydrology Regional Studies · 2026-04-18

  articleOpen accessSenior author

  Norfolk, Virginia, United States For real-time urban flood prediction at the street-scale, both speed and accuracy are critical. Among deep learning algorithms, Long Short-Term Memory (LSTM) networks are effective for time series prediction. However, the optimal approach for training LSTM models for accurate prediction remains debated in the hydrology literature. Using a dataset of 40 flood-prone streets, this study explores strategies for training LSTM models for street-scale flood prediction. Three experiments were designed to (1) compare different data-grouping approaches across global, clustered, and street models, (2) assess how the availability of water-depth information influences prediction accuracy, and (3) test the scalability of the models for newly added streets. Grouping streets into hydrologically similar clusters enhanced prediction accuracy over the global model for the test events, while street models achieved the lowest errors in most cases. This suggests that the uniqueness of street-scale flooding dynamics in urban environments requires hyper-focused model training. When testing model performance with varying water-depth inputs, LSTM models trained on streets experiencing a wide range of flood depths performed well for streets with shallow water depths. The cluster models outperformed the global model in predicting flooding on newly added streets. This suggests that flooding behavior is better captured when the training dataset consists of hydrologically similar streets rather than a diverse set. • Strategies for training LSTM models for street-scale flood prediction are explored. • Training using only local data for a single street outperforms all other models. • Training using hydrologically similar streets outperforms training using all streets. • Training using streets experiencing deep flooding can still predict shallow flooding. • Urban flood dynamics require localized and specific training data.

  PublisherDOI

• Quantifying and Designing Infrastructure for Nonstationary Flood Risks

  2025-05-02

  articleSenior author

  In recent years, climate change has led to a rise in intense precipitation events, presenting the need for efficient and cost-effective flood management infrastructure. In Charlottesville, VA, one key area identified for improvement is Meadow Creek. This paper examines different infrastructure options for flood management in Meadow Creek under various climate change scenarios. This analysis is carried out by optimizing infrastructure designs with the Environmental Protection Agency’s Storm Water Management Model under uncertain future conditions captured by climate projections from the Coupled Model Intercomparison Project 6. The optimization seeks to minimize cost and runoff volume while maximizing cobenefits. Our findings provide a set of non-dominated green infrastructure solutions and provide a methodology for selecting a recommended compromise solution. This analysis contributes to our goal of addressing flood risks and long-term sustainability in the Charlottesville area.

  PublisherDOI

• Comparing Robust Optimization Approaches for Addressing Hydrologic Model Uncertainty in Infrastructure Planning: A Green Infrastructure Example

  Journal of Water Resources Planning and Management · 2025-07-09 · 2 citations

  article

  Water resources planning is dependent on hydrologic models to estimate flows and storage in candidate engineering designs. However, such models are calibrated with limited flow data relative to the many model parameters. This may result in different equifinal parameterizations that imply different optimal designs. To assess if and how this uncertainty should be considered, we compare three methods for multiobjective optimization of green infrastructure (GI): one that designs to the most likely parameterization and two robust alternatives that use several likely parameterizations with (1) likelihood-weighted objective functions, and (2) min-max objective functions. To evaluate these methods, we set synthetic true values for model parameters, use them to simulate observed streamflow, and then use Bayesian calibration to estimate parametric uncertainty. We compare results from optimization to the synthetic parameterization against the three alternatives. The GI optimizations aim to minimize flooding, low-flow intensification, and cost. We find that the two robust methods provide objective values and decisions that are closer to those optimized to the synthetic truth, demonstrating value in considering hydrologic model uncertainty in water resource system designs.

  PublisherDOI

• Comparing Strategies for Training LSTM Models for Street-Scale Urban Flood Prediction

  SSRN Electronic Journal · 2025-01-01

  preprintOpen accessSenior author
  PublisherDOI

• Uncovering the Drivers of Urban Flood Reports: An Environmental and Socioeconomic Analysis Using 311 Data

  Water · 2025-11-06

  articleOpen accessSenior author

  Cities use 311 platforms for residents to report flooding, offering insight into flood-prone areas. The combined role of environmental and socioeconomic factors shaping these reports remains unexplored. This study analyzes five years of 311 flood reports in Norfolk, VA, using a logistic regression model to identify salient predictors and assess their influence on flood reporting. The model includes environmental variables (precipitation, tide level, and topographic wetness index) and socioeconomic indicators (race, income, and education). The model performed well with an area under the receiver operator characteristic (ROC) curve (AUC) of 0.8. Permutation-based feature importance revealed precipitation as the most important predictor (AUC contribution: 0.27), followed by the percentage of Black residents (0.02); tide only contributed ~0.01. The influence of the percentage of Hispanics was also ~0.01. Increases in the percentage of Black residents were associated with increased reporting, while the converse was true for a higher percentage of Hispanic residents. Higher reporting in Norfolk from locations with more Black residents is distinct from findings in other cities, suggesting Norfolk may have more effective communication with these residents about 311 reporting. However, lower reporting in locations with more Hispanic residents suggests Norfolk could improve outreach to non-native speakers, for example, by adding Spanish language options to their 311 platform.

  PublisherOA PDFDOI

• COMPARING ROBUST OPTIMIZATION APPROACHES FOR ADDRESSING HYDROLOGIC MODEL UNCERTAINTY IN INFRASTRUCTURE PLANNING: A GREEN INFRASTRUCTURE EXAMPLE

  2024-06-17

  preprint

  Water resources planning depends upon hydrologic models to estimate flows and storage under candidate engineering designs. However, such models are calibrated with limited flow data relative to the many model parameters. This may result in different equifinal parameterizations that imply different optimal designs. To assess if and how this uncertainty should be considered, we compare three methods for multi-objective optimization of green infrastructure (GI): one that designs to the most likely parameterization and two robust alternatives that use several likely parameterizations with 1) likelihood-weighted objective functions, and 2) min-max objective functions. To evaluate these methods, we set synthetic true values for model parameters, use them to simulate “observed” streamflow, and then use Bayesian calibration to estimate parametric uncertainty. We compare results from optimization to the synthetic parameterization against the three alternatives. The GI optimizations aim to minimize flooding, low flow intensification, and cost. We find the two robust methods provide objective values and decisions that are closer to those optimized to the synthetic truth, demonstrating value in considering hydrologic model uncertainty in water resources system designs.

  PublisherDOI

• Scenario Storyline Discovery for Planning in Multi‐Actor Human‐Natural Systems Confronting Change

  Earth s Future · 2024-09-01 · 6 citations

  articleOpen access

  Abstract Scenarios have emerged as valuable tools in managing complex human‐natural systems, but the traditional approach of limiting focus on a small number of predetermined scenarios can inadvertently miss consequential dynamics, extremes, and diverse stakeholder impacts. Exploratory modeling approaches have been developed to address these issues by exploring a wide range of possible futures and identifying those that yield consequential vulnerabilities. However, vulnerabilities are typically identified based on aggregate robustness measures that do not take full advantage of the richness of the underlying dynamics in the large ensembles of model simulations and can make it hard to identify key dynamics and/or storylines that can guide planning or further analyses. This study introduces the FRamework for Narrative Storylines and Impact Classification (FRNSIC; pronounced “forensic”): a scenario discovery framework that addresses these challenges by organizing and investigating consequential scenarios using hierarchical classification of diverse outcomes across actors, sectors, and scales, while also aiding in the selection of scenario storylines, based on system dynamics that drive consequential outcomes. We present an application of this framework to the Upper Colorado River Basin, focusing on decadal droughts and their water scarcity implications for the basin's diverse users and its obligations to downstream states through Lake Powell. We show how FRNSIC can explore alternative sets of impact metrics and drought dynamics and use them to identify drought scenario storylines, that can be used to inform future adaptation planning.

  PublisherOA PDFDOI

• Exploring the benefits of integrated energy-water management in reducing economic and environmental tradeoffs

  2024-08-01

  preprintOpen access1st authorCorresponding

  Integrated water-energy management is crucial for balancing socioeconomic and environmental objectives in multi-reservoir systems. Multipurpose reservoirs support clean energy production, recreation, navigation, and flood protection but also disrupt natural water flows and fish migration. As hydropower's role evolves with grid decarbonization, managing these tradeoffs becomes increasingly complex. An integrated model combining economic and environmental factors is essential to inform how to adapt hydropower operations effectively to complement decarbonization of the electric grid. However, existing literature lacks such comprehensive models. This study introduces an integrated water-energy optimization model using the Columbia River Basin (CRB) and Mid-Columbia (Mid-C) energy market as a case study. The model couples a simulation of operations of 48 CRB reservoirs with a unit commitment/economic dispatch model of the California and West Coast Power system (CAPOW). We employ Direct Policy Search (DPS) and a multi-objective evolutionary algorithm (MOEA) to optimize four objectives: maximize economic benefits from energy production, minimize fossil fuel electricity generation, minimize environmental flow violations, and minimize peak flood levels. Our findings reveal that the integrated model discovers superior operational strategies compared to existing rules, with some policies outperforming current operations on all objectives simultaneously. Insights from the optimized policies include strategies for improved coordination of reservoir operations using storage and inflow data, and the strategic timing of water releases to ensure increased hydropower production leads to less fossil fuel dependence and greater revenue. These results highlight the potential of integrated models to enhance the sustainability of hydropower operations amid a transitioning energy landscape.

  PublisherOA PDFDOI

Frequent coauthors

• Patrick M. Reed

  Cornell University

  47 shared

• Antonia Hadjimichael

  Pennsylvania State University

  29 shared

• Lawrence E. Band

  University of Virginia

  23 shared

• Andrea Castelletti

  Politecnico di Milano

  22 shared

• Matteo Giuliani

  21 shared

• Jared D. Smith

  University of Virginia

  18 shared

• Chris Vernon

  Pacific Northwest National Laboratory

  16 shared

• Jennifer Morris

  Moscow Institute of Thermal Technology

  15 shared

Labs

• Quinn Research GroupPI

Education

• PhD, Civil and Environmental Engineering

  Cornell University

  2017

• B.S., Earth and Environmental Engineering

  Columbia University

  2011

Awards & honors

• Best Policy Oriented Paper Award, Journal of Water Resources…
• UVA Civil Engineering Teaching Award, 2021
• UVA Graduate Engineering Student Council Advisor of the Year…
• Ph.D. Dissertation Award in Natural Science and Engineering,…