Samantha Oliver is a Hydrologist with the Upper Midwest Water Science Center.
Samantha Oliver received her PhD in Limnology and Freshwater Sciences from the University of Wisconsin-Madison, where she did continental-scale water quality research at the Center for Limnology. Prior to her Phd, she completed a Masters degree in Integrated Biosciences at the University of Minnesota-Duluth, where her research focused on nutrient transport of migrating zooplankton in Lake Superior. She joined the Wisconsin Water Science Center in 2017 first as a student in the Pathways program, and then as a hydrologist. Currently, she contributes to a variety of projects across the center, including long-term trends in stream water quality in urban and agricultural watersheds of Milwaukee and Madison, the biological relevance of contaminants in Great Lakes tributaries, the effects of best management practices on runoff from farm fields (edge-of-field monitoring), and the consequences of airport deicers in surface water runoff. Samantha also spends part of her time with the Data Science branch in the Integrated Information Dissemination Division (IIDD) as an instructor for the Intro to R course and contributer to various projects including predictions of lake water temperature.
Science and Products
Fish Habitat Restoration to Promote Adaptation: Resilience of Sport Fish in Lakes of the Upper Midwest
Understanding Historical and Predicting Future Lake Temperatures in North and South Dakota
“Hyperscale” Modeling to Understand and Predict Temperature Changes in Midwest Lakes
Deep learning approaches for improving prediction of daily stream temperature in data-scarce, unmonitored, and dammed basins
Data to support near-term forecasts of stream temperature using process-guided deep learning and data assimilation
Stream temperature predictions in the Delaware River Basin using pseudo-prospective learning and physical simulations
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
Predicting water temperature in the Delaware River Basin
Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data
Machine learning for understanding inland water quantity, quality, and ecology
Modeling reservoir release using pseudo-prospective learning and physical simulations to predict water temperature
Pesticide prioritization by potential biological effects in tributaries of the Laurentian Great Lakes
Prioritizing pesticides of potential concern and identifying potential mixture effects in Great Lakes tributaries using passive samplers
Teams, networks, and networks of networks advancing our understanding and conservation of inland waters
Can machine learning accelerate process understanding and decision-relevant predictions of river water quality?
Multi-task deep learning of daily streamflow and water temperature
Physics-guided machine learning from simulation data: An application in modeling lake and river systems
Deep learning approaches for improving prediction of daily stream temperature in data-scarce, unmonitored, and dammed basins
Integrating ecosystem metabolism and consumer allochthony reveals nonlinear drivers in lake organic matter processing
Predicting water temperature dynamics of unmonitored lakes with meta-transfer learning
Graph-based reinforcement learning for active learning in real time: An application in modeling river networks
Science and Products
- Science
Fish Habitat Restoration to Promote Adaptation: Resilience of Sport Fish in Lakes of the Upper Midwest
Many Midwestern lakes are experiencing warming water temperatures as a result of climate change. In general, this change is causing coldwater fish species such as cisco and coolwater species such as walleye to decline. Meanwhile, warmer water species such as largemouth and smallmouth bass are increasing as temperatures warm. However, some fish populations are more vulnerable to these changes thanUnderstanding Historical and Predicting Future Lake Temperatures in North and South Dakota
Lakes, reservoirs, and ponds are central and integral features of the North Central U.S. These water bodies provide aesthetic, cultural, and ecosystem services to surrounding wildlife and human communities. External impacts – such as climate change – can have significant impacts to these important parts of the region’s landscape. Understanding the responses of lakes to these drivers is critical fo...“Hyperscale” Modeling to Understand and Predict Temperature Changes in Midwest Lakes
Many inland waters across the United States are experiencing warming water temperatures. The impacts of this warming on aquatic ecosystems are significant in many areas, causing problems for fisheries management, as many economically and ecologically important fish species are experiencing range shifts and population declines. Fisheries and natural resource managers need timely and usable data and - Data
Deep 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 sitesData to support near-term forecasts of stream temperature using process-guided deep learning and data assimilation
This data release contains the forcings and outputs of 7-day ahead maximum water temperature forecasting models that made real-time predictions in the Delaware River Basin during 2021. The model is driven by weather forecasts and observed reservoir releases and produces maximum water temperature forecasts for the issue day (day 0) and 7 days into the future (days 1-7) at five sites. This data releStream 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 predictionMulti-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 releasePredicting water temperature in the Delaware River Basin
Daily 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 and mussel species. This data release supports a variety of flow and water temperature modeling efforts and provides the inputs and outputs of both machine learning and process-based modeling methods across 456 river reaExploring 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 - Multimedia
- Publications
Filter Total Items: 19
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; estModeling 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 riPesticide prioritization by potential biological effects in tributaries of the Laurentian Great Lakes
Watersheds of the Great Lakes Basin (USA/Canada) are highly modified and impacted by human activities including pesticide use. Despite labeling restrictions intended to minimize risks to nontarget organisms, concerns remain that environmental exposures to pesticides may be occurring at levels negatively impacting nontarget organisms. We used a combination of organismal-level toxicity estimates (inPrioritizing pesticides of potential concern and identifying potential mixture effects in Great Lakes tributaries using passive samplers
To help meet the objectives of the Great Lakes Restoration Initiative with regard to increasing knowledge about toxic substances, 223 pesticides and pesticide transformation products were monitored in 15 Great Lakes tributaries using polar organic chemical integrative samplers. A screening-level assessment of their potential for biological effects was conducted by computing toxicity quotients (TQsTeams, networks, and networks of networks advancing our understanding and conservation of inland waters
Networks are defined as groups of interconnected people and things, and by this definition, networks play a major role in the science of inland waters. In this article, we bring the latest social network research to understand and improve inland waters science and conservation outcomes. What we found is that relationships matter. Different teams and networks have different objectives and lifespanCan 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 predMulti-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 facPhysics-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, theseDeep 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 (Ts) 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 Ts and it is uncertain how an LSTM-based daily Ts model will perform in unmonitoredIntegrating ecosystem metabolism and consumer allochthony reveals nonlinear drivers in lake organic matter processing
Lakes process both terrestrial and aquatic organic matter, and the relative contribution from each source is often measured via ecosystem metabolism and terrestrial resource use in the food web (i.e., consumer allochthony). Yet, ecosystem metabolism and consumer allochthony are rarely considered together, despite possible interactions and potential for them to respond to the same lake characteristPredicting 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,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-b