Filters: Categories: Data (X) > partyWithName: U.S. Geological Survey (X) > partyWithName: Alison P Appling (X)
18 results (9ms)|
Filters
Date Range
Extensions Types
Contacts
Categories Tag Types Tag Schemes
|
Using predicted lake temperatures from uncalibrated, process-based models (PB0) and process-guided deep learning models (PGDL), this dataset summarized a collection of thermal metrics to characterize lake temperature impacts on fish habitat for 881 lakes. Included in the metrics are daily thermal optical habitat areas and a set of over 172 annual thermal metrics.
Water temperature estimates from multiple models were evaluated by comparing predictions to observed water temperatures. The performance metric of root-mean square error (in degrees C) is calculated for each lake and each model type, and matched values for predicted and observed temperatures are also included to support more specific error estimation methods (for example, calculating error in a particular month). Errors for the process-based model are compared to predictions as shared in Model Predictions data since these models were not calibrated. Errors for the process-guided deep learning models were calculated from validation folds and therefore differ from the comparisons to Model Predictions because those...
This dataset provides shapefile outlines of the 2,332 lakes that had temperature modeled as part of this study. The format is a shapefile for all lakes combined (.shp, .shx, .dbf, and .prj files). A csv file of lake metadata is included, which includes lake metadata and all features that were considered for the meta transfer model (not all meta features were used). This dataset is part of a larger data release of lake temperature model inputs and outputs for 2,332 lakes in the U.S. (https://doi.org/10.5066/P9I00WFR).
Categories: Data;
Types: Downloadable,
Map Service,
OGC WFS Layer,
OGC WMS Layer,
Shapefile;
Tags: 007,
012,
IA,
IL,
Illinois,
This dataset provides shapefile outlines of the 881 lakes that had temperature modeled as part of this study. The format is a shapefile for all lakes combined (.shp, .shx, .dbf, and .prj files). A csv file of lake metadata is also included. This dataset is part of a larger data release of lake temperature model inputs and outputs for 881 lakes in the U.S. state of Minnesota (https://doi.org/10.5066/P9PPHJE2).
Categories: Data;
Types: Downloadable,
Map Service,
OGC WFS Layer,
OGC WMS Layer,
Shapefile;
Tags: MN,
Minnesota,
SD,
South Dakota,
US,
This data release component contains mean daily stream water temperature observations, retrieved from the USGS National Water Information System (NWIS) and used to train and validate all temperature models. The model training period was from 2010-10-01 to 2014-09-30, and the test period was from 2014-10-01 to 2016-09-30.
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 sites. Experiment B tested multi-task learning for predicting streamflow with 25 years of training data and using a single model for all 101 sites. Experiment C tested multi-task learning for predicting streamflow with just 2 years of training data. Experiment D tested multi-task learning for predicting water temperature with...
Categories: Data,
Data Release - Revised;
Tags: US,
USGS Science Data Catalog (SDC),
United States,
deep learning,
environment,
Predictions are evaluated against observed temperatures.
This dataset includes model inputs (specifically, meteorological inputs to the predictive models and flags for predicted ice-cover) and is part of a larger data release of lake temperature model inputs and outputs for 2,332 lakes in the U.S. states of North Dakota, South Dakota, Minnesota, Wisconsin, and Michigan (https://doi.org/10.5066/P9PPHJE2).
Multiple modeling frameworks were used to predict daily temperatures at 0.5m depth intervals for a set of diverse lakes in the U.S. states of South Dakota, North Dakota, Minnesota, Wisconsin, and Michigan. Process-Based (PB) models were configured and calibrated with training data to reduce root-mean squared error. Uncalibrated models used default configurations (PB0; see Winslow et al. 2016 for details) and no parameters were adjusted according to model fit with observations. Process-Guided Deep Learning (PGDL) models were deep learning models with an added physical constraint for energy conservation as a loss term. These models were pre-trained with uncalibrated Process-Based model outputs (PB0) before training...
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 graph convolution network - RGCN, and a temporal convolution graph model - Graph WaveNet). The associated manuscript explores how the architectural differences between the two models influence how they learn spatial and temporal relationships, and how those learned relationships influence a model's ability to accurately predict...
Categories: Data;
Types: Map Service,
OGC WFS Layer,
OGC WMS Layer,
OGC WMS Service;
Tags: DE,
Delaware,
Hydrology,
MD,
Maryland,
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...
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, and includes the West Branch of the Delaware River below Cannonsville Reservoir and the East Branch of the Delaware River below Pepacton Reservoir. Various model architectures, training schemes, and data assimilation methods were used to generate the table and figures in Chen et a.l (2021) and predictions of each model are...
Categories: Data;
Types: Downloadable,
Map Service,
OGC WFS Layer,
OGC WMS Layer,
Shapefile;
Tags: Hydrology,
NY,
New York,
PA,
Pennsylvania,
This data release component contains model inputs including river basin attributes, weather forcing data, and simulated and observed river discharge.
This data release component contains shapefiles of river basin polygons and monitoring site locations coincident with the outlets of those basins. A table of basin attributes is also supplied. Attributes, observations, and weather forcing data for these basins were used to train and test the stream temperature prediction models of Rahmani et al. (2021b).<\p>
Categories: Data;
Types: Downloadable,
Map Service,
OGC WFS Layer,
OGC WMS Layer,
Shapefile;
Tags: AL,
AR,
AZ,
Alabama,
Arizona,
This dataset provides model parameters used to estimate water temperature from a process-based model (Hipsey et al. 2019) using uncalibrated model configurations (PB0) and the trained model parameters for process-guided deep learning models (PGDL; Read et al. 2019). This dataset is part of a larger data release of lake temperature model inputs and outputs for 881 lakes in the U.S. state of Minnesota(https://doi.org/10.5066/P9PPHJE2).
Data release: Predicting Water Temperature Dynamics of Unmonitored Lakes with Meta Transfer Learning
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 in 2,332 lakes during 1980-2019. The data are organized into these items: This research was funded by the Department of the Interior Northeast and North Central Climate Adaptation Science Centers, a Midwest Glacial Lakes Fish Habitat Partnership grant through F&WS Access to computing facilities was provided by USGS Advanced Research Computing, USGS Yeti Supercomputer (https://doi.org/10.5066/F7D798MJ)....
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- isochlor, also known as the salt front, using daily river discharge, meteorological drivers, and tidal water level data. We use the ML model to predict the location of the salt front, measured in river miles (RM) along the Delaware River, during the period 2001-2020, and we compare the ML model results to results from the hydrodynamic...
This data release item contains water temperature predictions for 455 river sites across the U.S. Predictions are from the models described by Rahmani et al. (2021b).
|
|
