Process-guided deep learning water temperature predictions: 6 Model evaluation (test data and RMSE)

Metadata Updated: November 12, 2020

This dataset includes evaluation data ("test" data) and performance metrics for water temperature predictions from multiple modeling frameworks. 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. Deep Learning (DL) models were Long Short-Term Memory artificial recurrent neural network models which used training data to adjust model structure and weights for temperature predictions (Jia et al. 2019). Process-Guided Deep Learning (PGDL) models were DL 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 on actual temperature observations. Performance was measured as root-mean squared errors relative to temperature observations during the test period. Test data include compiled water temperature data from a variety of sources, including the Water Quality Portal (Read et al. 2017), the North Temperate Lakes Long-TERM Ecological Research Program (https://lter.limnology.wisc.edu/), the Minnesota department of Natural Resources, and the Global Lake Ecological Observatory Network (gleon.org). This dataset is part of a larger data release of lake temperature model inputs and outputs for 68 lakes in the U.S. states of Minnesota and Wisconsin (http://dx.doi.org/10.5066/P9AQPIVD).

Access & Use Information

License: No license information was provided. If this work was prepared by an officer or employee of the United States government as part of that person's official duties it is considered a U.S. Government Work.

Downloads & Resources

Dates

Metadata Date November 13, 2019
Metadata Created Date November 12, 2020
Metadata Updated Date November 12, 2020
Reference Date(s) November 13, 2019 (publication)
Frequency Of Update notPlanned

Metadata Source

Harvested from DOI Open Data

Additional Metadata

Resource Type Dataset
Metadata Date November 13, 2019
Metadata Created Date November 12, 2020
Metadata Updated Date November 12, 2020
Reference Date(s) November 13, 2019 (publication)
Responsible Party U.S. Geological Survey (Point of Contact)
Contact Email
Guid
Access Constraints Use Constraints: These data are open access usable via creative commons as long as original data providers are acknowledged, Access Constraints: none
Bbox East Long -87.9475441739278
Bbox North Lat 48.6427837911633
Bbox South Lat 42.5692312672573
Bbox West Long -94.2609062307949
Coupled Resource
Frequency Of Update notPlanned
Licence Unless otherwise stated, all data, metadata and related materials are considered to satisfy the quality standards relative to the purpose for which the data were collected. Although these data and associated metadata have been reviewed for accuracy and completeness and approved for release by the U.S. Geological Survey (USGS), no warranty expressed or implied is made regarding the display or utility of the data on any other system or for general or scientific purposes, nor shall the act of distribution constitute any such warranty.
Metadata Language
Metadata Type geospatial
Progress completed
Spatial Data Service Type
Spatial Reference System
Spatial Harvester True
Temporal Extent Begin 1980-04-01
Temporal Extent End 2018-12-31

Didn't find what you're looking for? Suggest a dataset here.