Snow drought to hydrologic drought progression using machine learning and probabilistic analysis

Abstract Snow plays a crucial role in water resource management, acting as a natural reservoir that sustains agricultural, domestic, and ecological needs. However, declining snowpack poses significant challenges to water availability, particularly in snow-dominated regions. This study explores the r...

Full description

Saved in:
Bibliographic Details
Main Authors: Pouya Moghaddasi, Keyhan Gavahi, Hamid Moradkhani
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-05978-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849768803093708800
author Pouya Moghaddasi
Keyhan Gavahi
Hamid Moradkhani
author_facet Pouya Moghaddasi
Keyhan Gavahi
Hamid Moradkhani
author_sort Pouya Moghaddasi
collection DOAJ
description Abstract Snow plays a crucial role in water resource management, acting as a natural reservoir that sustains agricultural, domestic, and ecological needs. However, declining snowpack poses significant challenges to water availability, particularly in snow-dominated regions. This study explores the relationship between Snow Water Equivalent (SWE) and streamflow in snow-dominated watersheds using the Long Short-Term Memory (LSTM) model and probabilistic analysis. While LSTM model is typically used for prediction, we employed it primarily to understand how snow affects streamflow. Our analysis yielded several key findings: (1) By analyzing multiple SWE products, we found a strong relationship between SWE and streamflow, particularly with a lookback of 60–90 days. (2) The University of Arizona (UAZ) dataset consistently provided the most reliable results, showing that SWE during winter significantly influences streamflow in spring and summer. (3) Our spatial analysis revealed that basins in the western United States consistently exhibited strong model performance, underscoring the robust relationship between SWE and streamflow in these snow-dominated regions. (4) Our probabilistic analysis revealed a systematic progression from snow drought to hydrologic drought, with the likelihood of hydrologic drought increasing from 0.32 in early phases (0–14 days) to over 0.8 in later phases (60–90 days). This progression provides an early warning indicator for hydrologic drought, improving our ability to anticipate and prepare for drought conditions in snow-dominated regions.
format Article
id doaj-art-58c8a64fd6714d41a6cf4eb6c44ace19
institution DOAJ
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-58c8a64fd6714d41a6cf4eb6c44ace192025-08-20T03:03:40ZengNature PortfolioScientific Reports2045-23222025-07-0115111710.1038/s41598-025-05978-ySnow drought to hydrologic drought progression using machine learning and probabilistic analysisPouya Moghaddasi0Keyhan Gavahi1Hamid Moradkhani2Department of Civil, Construction and Environmental Engineering, Center for Complex Hydrosystems Research, The University of AlabamaDepartment of Civil, Construction and Environmental Engineering, Center for Complex Hydrosystems Research, The University of AlabamaDepartment of Civil, Construction and Environmental Engineering, Center for Complex Hydrosystems Research, The University of AlabamaAbstract Snow plays a crucial role in water resource management, acting as a natural reservoir that sustains agricultural, domestic, and ecological needs. However, declining snowpack poses significant challenges to water availability, particularly in snow-dominated regions. This study explores the relationship between Snow Water Equivalent (SWE) and streamflow in snow-dominated watersheds using the Long Short-Term Memory (LSTM) model and probabilistic analysis. While LSTM model is typically used for prediction, we employed it primarily to understand how snow affects streamflow. Our analysis yielded several key findings: (1) By analyzing multiple SWE products, we found a strong relationship between SWE and streamflow, particularly with a lookback of 60–90 days. (2) The University of Arizona (UAZ) dataset consistently provided the most reliable results, showing that SWE during winter significantly influences streamflow in spring and summer. (3) Our spatial analysis revealed that basins in the western United States consistently exhibited strong model performance, underscoring the robust relationship between SWE and streamflow in these snow-dominated regions. (4) Our probabilistic analysis revealed a systematic progression from snow drought to hydrologic drought, with the likelihood of hydrologic drought increasing from 0.32 in early phases (0–14 days) to over 0.8 in later phases (60–90 days). This progression provides an early warning indicator for hydrologic drought, improving our ability to anticipate and prepare for drought conditions in snow-dominated regions.https://doi.org/10.1038/s41598-025-05978-ySnow droughtHydrologic droughtLong short-term memory (LSTM)Probabilistic analysisDrought progressionUnited States
spellingShingle Pouya Moghaddasi
Keyhan Gavahi
Hamid Moradkhani
Snow drought to hydrologic drought progression using machine learning and probabilistic analysis
Scientific Reports
Snow drought
Hydrologic drought
Long short-term memory (LSTM)
Probabilistic analysis
Drought progression
United States
title Snow drought to hydrologic drought progression using machine learning and probabilistic analysis
title_full Snow drought to hydrologic drought progression using machine learning and probabilistic analysis
title_fullStr Snow drought to hydrologic drought progression using machine learning and probabilistic analysis
title_full_unstemmed Snow drought to hydrologic drought progression using machine learning and probabilistic analysis
title_short Snow drought to hydrologic drought progression using machine learning and probabilistic analysis
title_sort snow drought to hydrologic drought progression using machine learning and probabilistic analysis
topic Snow drought
Hydrologic drought
Long short-term memory (LSTM)
Probabilistic analysis
Drought progression
United States
url https://doi.org/10.1038/s41598-025-05978-y
work_keys_str_mv AT pouyamoghaddasi snowdroughttohydrologicdroughtprogressionusingmachinelearningandprobabilisticanalysis
AT keyhangavahi snowdroughttohydrologicdroughtprogressionusingmachinelearningandprobabilisticanalysis
AT hamidmoradkhani snowdroughttohydrologicdroughtprogressionusingmachinelearningandprobabilisticanalysis