Lauren E Koenig Snyder

Delaware River Basin Stream Salinity Machine Learning Models and Data

This model archive contains the input data, model code, and model outputs for machine learning models that predict daily non-tidal stream salinity (specific conductance) for a network of 459 modeled stream segments across the Delaware River Basin (DRB) from 1984-09-30 to 2021-12-31. There are a total of twelve models from combinations of two machine learning models (Random Forest and Recurrent Graph Convolution Neural Networks), two training/testing partitions (spatial and temporal), and three input attribute sets (dynamic attributes, dynamic and static attributes, and dynamic attributes and a minimum set of static attributes). In addition to the inputs and outputs for non-tidal predictions provided on the landing...

Categories: Data; Tags: DE, Delaware, MD, Maryland, NJ, All tags... NY, New Jersey, New York, PA, Pennsylvania, US, USGS Science Data Catalog (SDC), United States, Water Quality, Water Resources, deep learning, environment, explainable AI (XAI), inlandWaters, machine learning, modeling, salinity, stream salinity, water, water resources, Fewer tags

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 for improving groundwater process representation: 1) a custom loss function that leverages the unique patterns of air and water temperature coupling resulting from different temperature drivers, 2) inclusion of additional groundwater-relevant catchment attributes, 3) incorporation of additional process model outputs, and...

Categories: Data; Tags: DE, Delaware, Hydrology, MD, Maryland, All tags... NJ, NY, New Jersey, New York, PA, Pennsylvania, US, USGS Science Data Catalog (SDC), United States, Water Quality, Water Resources, deep learning, environment, explainable AI (XAI), groundwater, hybrid modeling, inlandWaters, machine learning, modeling, process guided deep learning, stream temperature, temperature, water, water resources, Fewer tags

Estimated seasonal nitrogen and phosphorus loads in selected streams of the conterminous United States, 1999 - 2020

Estimated seasonal total nitrogen and total phosphorus loads during 1999 through 2020 in selected streams of the conterminous United States and water-quality and stream flow data used to generate those estimates are presented in this dataset. Loads were generated as part of the Integrated Water-Availability Assessment (IWAA) Program of the U.S. Geological Survey (www.usgs.gov/mission-areas/water-resources/science/integrated-water-availability-assessments#overview) using Fluxmaster (Schwarz and others, 2006, https://doi.org/10.3133/tm6B3) and Weighted Regression on Time, Discharge, and Season (WRTDS) (Hirsch and De Cicco, 2015, https://doi.org/10.1016/j.envsoft.2015.07.017). Loads were estimated initially for the...

Tags: Geochemistry, Hydrology, USGS Science Data Catalog (SDC), United States, United States, All tags... Water Quality, Water Resources, inlandWaters, nitrogen, nitrogen, phosphorus, phosphorus, stream load, water quality, Fewer tags

Data and model code used to evaluate a process-guided deep learning approach for in-stream dissolved oxygen prediction

This model archive contains data and code used to assess the use of process-informed multi-task deep learning models for predicting in-stream dissolved oxygen concentrations. Three holdout experiments were run to assess model performance, including a temporal holdout experiment, a spatial holdout experiment with similar sites held out, and a spatial holdout experiment with dissimilar sites held out. This model archive includes data from 10 sites in the lower Delaware River Basin that were used in the model experiments. Model training target data include dissolved oxygen concentrations downloaded from the National Water Information System (NWIS) (U.S. Geological Survey 2023). Model input data include daily meteorological...

Categories: Data; Tags: US, USGS Science Data Catalog (SDC), United States, deep learning, dissolved oxygen, All tags... environment, hybrid modeling, inlandWaters, machine learning, modeling, streams, water, water resources, Fewer tags

Long-term water-quality trends for rivers and streams within the contiguous United States using Weighted Regressions on Time, Discharge, and Season (WRTDS)

The U.S. Geological Survey (USGS) Water Mission Area (WMA) is working to address a need to understand where the Nation is experiencing water shortages or surpluses relative to the demand for water need by delivering routine assessments of water supply and demand. It is also improving understanding of the natural and human factors affecting the balance between supply and demand. A key part of these national assessments is identifying long-term trends in water availability, including groundwater and surface water quantity, quality, and use. To describe the long-term trends in the surface water quality component of water availability, data from the USGS and other Federal, State, and local agencies were accessed primarily...

Categories: Data, Data Release - In Progress; Tags: Hydrology, USGS Science Data Catalog (SDC), United States, Water Quality, Weighted regressions on time, discharge, and season (WRTDS), All tags... hydrology, surface water quality, water quality, Fewer tags