Skip to main content
  1. ScienceBase Catalog
  2. USGS Data Release Products
  3. Examining the influence of deep learning architecture on generalizability for predicting stream temperature in the Delaware River Basin

Examining the influence of deep learning architecture on generalizability for predicting stream temperature in the Delaware River Basin

Dates

Publication Date
Start Date
1980-04-01
End Date
2019-12-31

Citation

Topp, S.N., Barclay, J.R., Diaz, J.A., Sun, A.Y., Jia, X., Lu, D., Sadler, J.M., and Appling, A.P., 2023, Examining the influence of deep learning architecture on generalizability for predicting stream temperature in the Delaware River Basin: U.S. Geological Survey data release, https://doi.org/10.5066/P9HU7BLR.

Summary

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 stream temperature [...]

Contacts

Point of Contact :
Simon N Topp
Originator :
Simon N Topp, Janet R Barclay, Jeremy A Diaz, Alexander Y. Sun, Xiaowei Jia, Dan Lu, Jeffrey M Sadler, Alison P Appling
Metadata Contact :
Simon N Topp
Publisher :
U.S. Geological Survey
Distributor :
U.S. Geological Survey - ScienceBase
SDC Data Owner :
Integrated Information Dissemination Division
USGS Mission Area :
Water Resources

Attached Files

Click on title to download individual files attached to this item.

data_release_metadata.xml
Original FGDC Metadata
View 		27.41 KB application/fgdc+xml
sb_posted_files.csv 340 Bytes text/csv
01_Data_Prep.zip 8.95 KB application/zip
02_Model_Code.zip 54.79 KB application/zip
03_Model_Predictions.zip 5.12 MB application/zip

Purpose

This release is relevant to various deep learning tasks, including model understanding and interrogation through explainable AI as well as implementation of complex deep learning architectures for water resource problems.

Map

Map Preview

Spatial Services

ScienceBase WMS

Communities

  • USGS Data Release Products

Tags

Provenance

Additional Information

Identifiers

Type Scheme Key
DOI https://www.sciencebase.gov/vocab/category/item/identifier doi:10.5066/P9HU7BLR

Item Actions

View Item as ...

JSON ATOM ISO XML

Save Item as ...

JSON FGDC MODS XML ISO XML

View Item...

Metrics