Dataset for "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantification" Willard et al. (2025).

Willard, Jared; Varadharajan, Charuleka

doi:10.15485/2527393

Title: Dataset for "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantification" Willard et al. (2025).

Dataset
Other Related Research

Abstract

This data release provides all data and code used in the paper " "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantifications" Willard et al. (2025)" to model stream temperature, evaluate, and assess results. The associated manuscript explores the effect of different ensemble construction techniques across different common machine learning (ML) architectures for predictions in unmonitored basins. Modeling was done using long short-term memory (LSTM), gated recurrent unit (GRU), temporal convolution network (TCN), and extreme gradient boosting (XGBoost) models, and stream site coverage spans 1362 locations across the conterminous United States. The ensemble construction techniques investigated include ensemble by random weight initialization, differing hyperparameters, different random subsets of training data, different subselections of input features, different architectures, and Monte Carlo Dropout. The data is organized into these items items:Code repository and data for the paper " "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantifications" Willard et al. (2025).Code: stream_temp_ml_regionalization.zip contains the code repositoryData to run the code:- data_dir.zip -- contains all files that should be moved to the "DATA_DIR" variable defined in the "set_env_vars.sh" script in the code repository- metadata_dir.zip -- contains all files that should be moved to the "METADATA_DIR" variable defined in the "set_env_vars.sh" scriptmore »« less

Authors:

;

Lawrence Berkeley National Laboratory

Publication Date:: Tue Dec 31 23:00:00 EST 2024

DOE Contract Number:: AC02-05CH11231

Research Org.:: iNAIADS

Sponsoring Org.:: U.S. DOE > Office of Science > Biological and Environmental Research (BER)

Subject:: 54 ENVIRONMENTAL SCIENCES; DEEP LEARNING; EARTH SCIENCE > TERRESTRIAL HYDROSPHERE > SURFACE WATER; EARTH SCIENCE > TERRESTRIAL HYDROSPHERE > WATER QUALITY/WATER CHEMISTRY; EARTH SCIENCE > TERRESTRIAL HYDROSPHERE > WATER QUALITY/WATER CHEMISTRY > WATER CHARACTERISTICS > WATER TEMPERATURE; ENSEMBLE MODELING; MACHINE LEARNING; UNCERTAINTY QUANTIFICATION

OSTI Identifier:: 2527393

DOI:: https://doi.org/10.15485/2527393

Citation Formats


                    Willard, Jared, and Varadharajan, Charuleka. Dataset for "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantification" Willard et al. (2025)..  United States: N. p., 2024. 
        Web.  doi:10.15485/2527393.

Copy to clipboard


                    Willard, Jared, & Varadharajan, Charuleka. Dataset for "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantification" Willard et al. (2025)..  United States.  doi:https://doi.org/10.15485/2527393

Copy to clipboard


                    Willard, Jared, and Varadharajan, Charuleka. 2024.  
"Dataset for "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantification" Willard et al. (2025).".  United States.  doi:https://doi.org/10.15485/2527393.  https://www.osti.gov/servlets/purl/2527393. Pub date:Tue Dec 31 23:00:00 EST 2024

Copy to clipboard


                    
@article{osti_2527393,

  title        = {Dataset for "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantification" Willard et al. (2025).},

  author       = {Willard, Jared and Varadharajan, Charuleka},

  abstractNote = {This data release provides all data and code used in the paper " "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantifications" Willard et al. (2025)" to model stream temperature, evaluate, and assess results. The associated manuscript explores the effect of different ensemble construction techniques across different common machine learning (ML) architectures for predictions in unmonitored basins. Modeling was done using long short-term memory (LSTM), gated recurrent unit (GRU), temporal convolution network (TCN), and extreme gradient boosting (XGBoost) models, and stream site coverage spans 1362 locations across the conterminous United States. The ensemble construction techniques investigated include ensemble by random weight initialization, differing hyperparameters, different random subsets of training data, different subselections of input features, different architectures, and Monte Carlo Dropout. The data is organized into these items items:Code repository and data for the paper " "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantifications" Willard et al. (2025).Code: stream_temp_ml_regionalization.zip contains the code repositoryData to run the code:- data_dir.zip -- contains all files that should be moved to the "DATA_DIR" variable defined in the "set_env_vars.sh" script in the code repository- metadata_dir.zip -- contains all files that should be moved to the "METADATA_DIR" variable defined in the "set_env_vars.sh" script in the code repositoryData produced by the code and used in the paper:- outputs_dir.zip - contains model output and results (outputs_dir/results), model weights (outputs_dir/models), and all other outputs used for the paper including feature importances.To cite this code, please use the following BibTeX or MLA entries:bibtex:@misc{willard2025streamensembles,author = {Jared Willard and Charuleka Varadharajan},title = {Dataset for "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantification"},year = {2024},doi = {10.15485/2527393},publisher = {ESS-DIVE Repository},url = {https://data.ess-dive.lbl.gov/datasets/doi:10.15485/2527393}}MLA: Willard, Jared, et al. Dataset for "Machine Learning Ensembles Can Enhance Hydrologic Predictions and Uncertainty Quantification". 2025. ESS-DIVE Repository, doi:10.15485/2448016.},

  doi          = {10.15485/2527393},

  journal      = {},

  number       = ,

  volume       = ,

  place        = {United States},

  year         = {Tue Dec 31 23:00:00 EST 2024},

  month        = {Tue Dec 31 23:00:00 EST 2024}

}

Copy to clipboard

Dataset:

View Dataset

DOI: https://doi.org/10.15485/2527393

Save / Share:

Export Metadata

Save to My Library

Similar records in DOE Data Explorer and OSTI.GOV collections:

Dataset for "Evaluating Deep Learning Approaches for Predictions in Unmonitored Basins with Continental-scale Stream Temperature Models" Willard et al. (2024)

Dataset Willard, Jared ; Ciulla, Fabio ; Weierbach, Helen ; ...

This data release provides all data and code used in the paper " "Evaluating Deep Learning Approaches for Predictions in Unmonitored Basins with Continental-scale Stream Temperature Models" Willard et al. (2024)" to model stream temperature, evaluate, and assess results. The associated manuscript explores current open questions in prediction in ungauged and unmonitored basins concerning top-down versus bottom-up approaches, tradeoffs between data available and input requirements, and the appropriate representation of catchment attributes as inputs to deep learning models. Modeling was done primarily with long short-term memory (LSTM) models, and stream site coverage spans 1362 locations across the conterminous United States.more »« less
Dataset for the Danczak et al., 2025 manuscript about bacterial-fungal interactions

Dataset Danczak, Robert E. ; Bell, Sheryl L. ; Warburton, Evan J. ; ...

We generated genome-resolved multiomics data from a series of metagenomic and metatranscriptomic sequencing. Specifically, we acquired, functionally annotated, and taxonomically classified both bacterial and eukaryotic metagenome assembled genomes (MAGs). For bacterial MAGs, we assembled eukaryotic float metagenomic sequencing data from JGI using MEGAHIT, binned and refined MAGs using MetaWRAP and dRep, functionally annotated MAGs using eggNOG mapper, and assigned taxonomy using GTDB-tk. For eukaryotic MAGs, we first identified potentially eukaryotic contigs from a coassembly of eukaryotic float metagenomic sequencing data from JGI using EukRep and Whokaryote, binned MAGs using MetaBAT2, functionally annotated MAGs using eggNOG mapper, and assigned taxonomy usingmore »« less
Davis et al. (2025) MDPI Hydrogen Supplement

Dataset W Davis, Tyler ; Mahumud, Roksana ; McNaul, Shannon ; ...

The raw data and figures used in Davis et al. (2025), "A Comparative Analysis of Waste-as-a-Feedstock Accounting Methods in Life Cycle Assessments," published in MDPI Hydrogen journal.
Rittenhouse et al. 1960s Historical Archived Produced Water Dataset

Dataset Siefert, Nicholas

Around 1960, a private company entered into a research agreement to analyze for dissolved solids in water produced from >800 fields in the U.S. and Canada.. The elemental compositions provided were measured spectrochemically by Rittenhouse et al. The information has been made available to the public as a public service, but the names off of the companies and exact well locations have been removed. The samples are now located at the University of Texas in Austin. More details can be found in the following reference: Gordon Rittenhouse, Robert B. Fulton, Robert J. Grabowski, Joseph L. Bernard, Minor elements in oil-fieldmore »« less
Data for Grogan et al. "Bringing Hydrologic Realism to Water Markets"

Dataset Grogan, Danielle ; Lisk, Matthew ; Zuidema, Shan ; ...

This data set provides model output and post-processing files required to reproduce the results, tables, and figures in the paper "Bringing Hydrologic Realism to Water Markets" by Grogan et al. (in review). Other input data used in this study includes: Lisk, M., Grogan, D., Zuidema, S., Caccese, R., Peklak, D., Zheng, J., Fisher-Vanden, K., Lammers, R., Olmstead, S., & Fowler, L. (2023). Harmonized Database of Western U.S. Water Rights (HarDWR) (Version v1) [Data set]. MSD-LIVE Data Repository. https://doi.org/10.57931/2205619 Two models were used in this study: (1) The University of New Hampshire Water Balance Model WBM, and (2) a Water Marketmore »« less

Similar Records