About

Sarah Fletcher is an Assistant Professor of Civil and Environmental Engineering and a Center Fellow at the Woods Institute for the Environment at Stanford University. Her research aims to advance water resources management to promote resilient and equitable responses to a changing world. Her work integrates methods from hydrology, policy analysis, and data science to inform decision-making around critical environmental challenges. The Fletcher lab emphasizes partnership for real-world impact, focusing on developing solutions that address pressing water management issues.

Research topics

• Geography
• Computer Science
• Business
• Environmental resource management
• Natural resource economics
• Environmental science
• Economics
• Artificial Intelligence
• Ecology
• Environmental planning
• Water resource management
• Environmental engineering
• Economic growth
• Biology
• Development economics
• Environmental economics

Selected publications

• Code and Data for paper: Bayesian-Belief Direct Policy Search for Adaptive Water Supply Planning with Endogenous Learning

  Zenodo (CERN European Organization for Nuclear Research) · 2026-01-18 · 1 citations

  otherOpen accessSenior author

  This record archives the code (and supporting data) used in Bayesian-Belief Direct Policy Search for Adaptive Water Supply Planning with Endogenous Learning.The repository includes: (i) policy training scripts (Bayesian DPS and standard DPS), (ii) simulation model and experiment configuration files, and (iii) scripts to reproduce the main figures and tables in the manuscript and Supporting Information. How to reproduce: Install dependencies (see Readme/Requirements). Run main_par.py to generate experiments.

  PublisherDOI

• Code and Data for paper: Bayesian-Belief Direct Policy Search for Adaptive Water Supply Planning with Endogenous Learning

  Zenodo (CERN European Organization for Nuclear Research) · 2026-01-18

  otherOpen accessSenior author

  This record archives the code (and supporting data) used in Bayesian-Belief Direct Policy Search for Adaptive Water Supply Planning with Endogenous Learning.The repository includes: (i) policy training scripts (Bayesian DPS and standard DPS), (ii) simulation model and experiment configuration files, and (iii) scripts to reproduce the main figures and tables in the manuscript and Supporting Information. How to reproduce: Install dependencies (see Readme/Requirements). Run main_par.py to generate experiments.

  PublisherDOI

• From vulnerability exploration to adaptive policy design in semi-arid coastal basins: surrogate-assisted robust pathways building in the Quilimarí case, Chile.

  2026-03-14

  articleOpen access

  Recent applications of Robust Decision Making (RDM) have demonstrated their value for exploring socio-hydrological vulnerabilities under deep uncertainty in water-scarce regions. A recent study in the semi-arid coastal Quilimarí basin (central Chile), used an RDM framework combining stakeholder engagement and an integrated WEAP-MODFLOW model to reveal critical trade-offs between agricultural production, drinking water security, groundwater depletion and saline intrusion under climate and development uncertainties. While this work provided valuable insights into system vulnerabilities and stressors, it remained focused on exploratory analysis rather than on the explicit design of adaptive strategies.This study builds directly on the Quilimarí RDM case study and advances the framework toward adaptive policy design, introducing two methodological innovations. First, we extend the RDM approach by integrating the Direct Policy Search (DPS) framework to identify robust and flexible water management strategies. Instead of evaluating a small set of predefined interventions, policies are formulated as adaptive decision rules that dynamically link observable system states such as groundwater levels, salinity thresholds or unmet drinking water demand, to management actions including abstraction restrictions, activation of alternative supplies or demand reallocation. This allows the systematic identification of pathways that evolve over time and remain robust across a wide ensemble of plausible hydroclimatic and socio-economic futures.Second, to enable the computational requirement of DPS in data and process intensive basins, we develop a surrogate model that emulates the behavior of the full integrated surface-groundwater system. The original WEAP-MODFLOW model for Quilimarí, which explicitly represents groundwater dynamics, agricultural water use, and seawater intrusion, is approximated using an LSTM (Long Short-Term Memory), a type of Recurrent Neural Networks (RNN), trained on large ensembles of simulation outputs. The surrogate model preserves key nonlinearities and memory effects inherent to groundwater systems while reducing computational costs by several orders of magnitude, making large-scale adaptive policy search feasible.The combined framework is applied to the Quilimarí basin to identify adaptive pathways that balance drinking water reliability, agricultural viability, and long-term groundwater sustainability under deep uncertainties as climate and land use change and growing population. Results show that the DPS using the surrogate model outperform static strategies identified in the original RDM analysis, particularly under severe drought and demand-growth scenarios, by avoiding maladaptation and reducing regret across objectives.By explicitly linking the vulnerability exploration with the design of adaptive strategies, this study shows how RDM can be operationalized into implementable and flexible water management policies. The approach is transferable to other semi-arid coastal basins that face strong groundwater dependence, institutional constraints, and profound climate and other uncertainties.

  PublisherDOI

• Spatiotemporal Gaussian Process Regression Advances Early Detection of Precipitation Emergence

  2026-03-10

  articleOpen accessSenior author

  Detecting long-term precipitation trends is difficult because internal variability obscures externally forced signals. Conventional methods, such as multimodel means (MMM), often suppress regional signals and inflate uncertainty. We develop Gaussian Process Regression (GPR) models that combine observations with Coupled Model Intercomparison Project Phase 6 (CMIP6)-based priors to predict long-term precipitation anomalies. We test three variants: a univariate GPR (UGPR) using only temporal covariances, a circulation-aware GPR (CGPR) incorporating circulation variability, and a spatio-temporal GPR (SGPR) that incorporates spatial and temporal covariances. Using leave-one-out cross-validation across 33 CMIP6 models, we compare the predictive skill, uncertainty reduction, and emergence detection of these methods. All three GPR frameworks substantially outperform the CMIP6 MMM, reducing global predictive errors by approximately 60% and narrowing uncertainty by about 12%, with broadly comparable global-mean performance among the GPR methods. Differences between GPR variants emerge primarily at regional scales. In particular, SGPR advances the detection of forced precipitation changes by up to 15 years relative to UGPR in regions including the Middle East, Northwestern Africa, Eastern Europe, Japan, and parts of South America, while CGPR yields more limited and regionally heterogeneous improvements. These results indicate that while GPR provides robust improvements, explicitly accounting for spatiotemporal covariances yields additional regional benefits for early detection of precipitation change. Our findings highlight the importance of regional covariance structure for early detection and underscore the value of flexible Bayesian frameworks for dynamically integrating observations into climate change detection and prediction.

  PublisherOA PDFDOI

• Stormwater Capture Efficiency of Dry Wells and Effects of Precipitation Conditions and Deployment Strategies

  ACS ES&T Water · 2025-07-03 · 1 citations

  articleOpen access

  Dry wells are increasingly used for stormwater capture and groundwater recharge in drought- and flood-prone regions like California, yet their performance and optimal deployment strategies remain poorly understood. This study developed a computational model and conducted a case study using long-term rainfall data and dry wells from the Laurel Canyon Boulevard Green Street Project in Los Angeles, CA, to evaluate the effects of precipitation conditions and deployment strategies on dry well performance. Results showed that the studied dry wells captured 28.8 ± 14.0 acre-feet of stormwater annually─sufficient to meet 10–30% of indoor residential demand within the catchment. When measured as a percentage of rainfall captured, dry well performance remained stable across years despite annual rainfall variability but was higher for long, mild storm events. The analysis also identified a maximum effective infiltration rate per system. Below this threshold, increasing the infiltration capacity of dry wells may be cost-effective, while above it, more wells are needed to improve capture. Additionally, dry wells in series at the catchment outlet maximize water capture, while distributed systems better mitigate flooding. These findings support improved dry well design and siting strategies and provide a foundation for planning under future climate conditions.

  PublisherDOI

• Bayesian Direct Policy Search for Adaptive Water Supply Planning with Endogenous Learning

  2025-12-12

  articleOpen accessSenior author

  Climate change uncertainty challenges water supply planning, where long-lived infrastructure must ensure reliable supply under evolving conditions. Adaptive planning addresses this by incrementally expanding infrastructure only as needed, reducing unnecessary investments. Direct Policy Search (DPS), a reinforcement learning approach, has been widely used to identify adaptive rules that specify when and how much to expand infrastructure based on system conditions. However, standard DPS assumes static climate uncertainty, overlooking the potential to update uncertainty as new information emerges—potentially leading to over- or under-investment as the climate evolves. We introduce Bayesian DPS, a novel framework that integrates Bayesian learning into DPS to account for learning about climate uncertainty in adaptive planning. We do this by expanding the DPS state space to include a belief state, representing evolving climate uncertainty. The belief state is updated using Gaussian process regression as new observations become available. For instance, uncertainty about end-of-century climate is greatest early on but declines over time as data accumulates. We apply Bayesian DPS to a case study in Mombasa, Kenya, where decision rules optimize infrastructure development over a 100-year horizon. We compare policy performance across diverse climate and infrastructure scenarios to assess when learning improves planning. Results suggest Bayesian DPS enhances robustness and cost-effectiveness—especially under nonlinear climates, where past trends do not linearly predict future change, and for long-lived investments, where incorrect assumptions about future climate can lead to high regret. By endogenously modeling climate beliefs, Bayesian DPS offers a scalable, generalizable framework for adaptive planning under deep uncertainty.

  PublisherOA PDFDOI

• Visual‐Analytics Bridge Complexity and Accessibility for Robust Urban Water Planning

  Water Resources Research · 2025-04-01 · 2 citations

  articleOpen accessSenior author

  Abstract Urban water resources planning is complicated by unprecedented uncertainty in supply and demand. Real‐world planning often simplifies the full range of uncertainty faced by a system into a limited set of deterministic scenarios to enhance accessibility for decision‐makers and the public. However, overlooking uncertainty can expose the system to failures. On the other end of the spectrum, academically developed tools for scenario analysis rigorously quantify the combined effects of multiple sources of uncertainty, but the practical application of these models is limited by the challenges of information visualization and communication of results. In short, municipal water supply planners lack access to planning frameworks that effectively integrate a rigorous treatment of uncertainty with accessible, user‐friendly visual and interactive tools to enhance user accessibility. In this work, we fill this gap by proposing Visual‐Robust Decision Making, and demonstrate an application for the city of Santa Barbara (SB), CA. Santa Barbara faces multiple uncertainties from pending state and federal regulations to changing hydrology and water demand. The city seeks to increase its water portfolio robustness by expanding its seawater desalination plant, but must decide how much capacity to add. We introduce computational tools that assess uncertainty across nine uncertain drivers identified with the help of water planners in SB. To allow public participation in the desalination expansion decision, we develop interactive visual‐analytics to aid decision‐makers and stakeholders in navigating complex scenario analysis outcomes. Our results quantify the tradeoffs between increased capacity and system robustness and aim to enhance participation and uncertainty characterization of urban water planning efforts.

  PublisherOA PDFDOI

• Climate change threatens urban water affordability

  Research Square · 2025-04-15

  preprintOpen accessSenior author
  PublisherOA PDFDOI

• MSD CoP Webinar: Accounting for distributive justice in model-based decision support

  OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · 2024-01-01

  articleOpen access

  Context: This webinar was hosted by the MultiSector Dynamics Community of Practice (MSD CoP; https://multisectordynamics.org). Abstract: Model-based analyses play an ever-increasing role in informing policy and decision-making. However, many large-scale societal challenges unavoidably involve questions about the fair distribution of positive and negative consequences. How are the costs of the energy transition distributed over households and businesses? How are flood risks redistributed under different flood risk management plans? How are the impacts of climate change and climate mitigation distributed over different parts of the world?These kinds of questions play an important role when deliberating public policy, and the lack, in many cases, of clear answers becomes an obstacle to decision-making. At recent COPs, for example, wicked questions about loss and damages and the phase-out versus phase-down of coal became obstacles to global climate action, illustrating the misalignment of the direction of scientific research and decision-makers' information needs. In this talk, I'll explore advances that are being made that enable analysts to start providing grounded model-based answers to questions of distributive justice, as well as argue that analysts should embrace and explicate the normative nature of their work instead of hiding behind the purported neutrality of science. Presenters: Dr. Jan Kwakkel (Delft University of Technology) Moderator(s): Rebecca Saari (MSD CoP Working Group Co-Chair; Univ. of Waterloo), Matt Sparks (Univ. of Waterloo); Sarah Fletcher (MSD CoP Working Group Co-Chair; Stanford University), Juan Moreno-Cruz (Univ. of Waterloo), Patrick Reed (MSD CoP Facilitation Team Member, Moderator and Organizer) This webinar was held on: November 13, 2024 from 1 PM - 2:15 PM ET

  PublisherDOI

• Equity and modeling in sustainability science: Examples and opportunities throughout the process

  Proceedings of the National Academy of Sciences · 2024-03-18 · 49 citations

  articleOpen access

  Equity is core to sustainability, but current interventions to enhance sustainability often fall short in adequately addressing this linkage. Models are important tools for informing action, and their development and use present opportunities to center equity in process and outcomes. This Perspective highlights progress in integrating equity into systems modeling in sustainability science, as well as key challenges, tensions, and future directions. We present a conceptual framework for equity in systems modeling, focused on its distributional, procedural, and recognitional dimensions. We discuss examples of how modelers engage with these different dimensions throughout the modeling process and from across a range of modeling approaches and topics, including water resources, energy systems, air quality, and conservation. Synthesizing across these examples, we identify significant advances in enhancing procedural and recognitional equity by reframing models as tools to explore pluralism in worldviews and knowledge systems; enabling models to better represent distributional inequity through new computational techniques and data sources; investigating the dynamics that can drive inequities by linking different modeling approaches; and developing more nuanced metrics for assessing equity outcomes. We also identify important future directions, such as an increased focus on using models to identify pathways to transform underlying conditions that lead to inequities and move toward desired futures. By looking at examples across the diverse fields within sustainability science, we argue that there are valuable opportunities for mutual learning on how to use models more effectively as tools to support sustainable and equitable futures.

  PublisherOA PDFDOI

Recent grants

• Adaptive Management of Water Supply Infrastructure for Persistent Anomalies versus Climate Trends

  NSF · $498k · 2023–2027

Frequent coauthors

• Kenneth Strzepek

  21 shared

• Megan Lickley

  20 shared

• Marta Zaniolo

  Stanford University

  17 shared

• Meagan S. Mauter

  Stanford University

  14 shared

• Afreen Siddiqi

  Massachusetts Institute of Technology

  14 shared

• Olivier de Weck

  Massachusetts Institute of Technology

  8 shared

• Jennifer B Skerker

  7 shared

• S. A. Montzka

  5 shared