A Spatially‐Distributed Machine Learning Approach for Fractional Snow Covered Area Estimation

Abstract Snowpack in mountainous areas often provides water storage for summer and fall, especially in the Western United States. In situ observations of snow properties in mountainous terrain are limited by cost and effort, impacting both temporal and spatial sampling, while remote sensing estimate...

Full description

Saved in:
Bibliographic Details
Main Authors: Shalini Mahanthege, William Kleiber, Karl Rittger, Balaji Rajagopalan, Mary J. Brodzik, Edward Bair
Format: Article
Language:English
Published: Wiley 2024-11-01
Series:Water Resources Research
Subjects:
Online Access:https://doi.org/10.1029/2023WR036162
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849227328655196160
author Shalini Mahanthege
William Kleiber
Karl Rittger
Balaji Rajagopalan
Mary J. Brodzik
Edward Bair
author_facet Shalini Mahanthege
William Kleiber
Karl Rittger
Balaji Rajagopalan
Mary J. Brodzik
Edward Bair
author_sort Shalini Mahanthege
collection DOAJ
description Abstract Snowpack in mountainous areas often provides water storage for summer and fall, especially in the Western United States. In situ observations of snow properties in mountainous terrain are limited by cost and effort, impacting both temporal and spatial sampling, while remote sensing estimates provide more complete spacetime coverage. Spatial estimates of fractional snow covered area (fSCA) at 30m are available every 16 days from the series of multispectral scanning instruments on Landsat platforms. Daily estimates at 463m spatial resolution are also available from the Moderate Resolution Imaging Spectroradiometer (MODIS) instrument on the Terra satellite. Fusing Landsat and MODIS fSCA images creates high resolution daily spatial estimates of fSCA that are needed for various uses: to support scientists and managers interested in energy and water budgets for water resources and to understand the movement of animals in a changing climate. Here, we propose a new machine learning approach conditioned on MODIS fSCA, as well as a set of physiographic features, and fit to Landsat fSCA over a portion of the Sierra Nevada USA. The predictions are daily 30m fSCA. The approach relies on two stages of spatially‐varying models. The first classifies fSCA into three categories and the second yields estimates within (0, 100) percent fSCA. Separate models are applied and fitted within sub‐regions of the study domain. Compared with a recently‐published machine learning model (Rittger, Krock, et al., 2021), this approach uses spatially local (rather than global) random forests, and improves the classification error of fSCA by 16%, and fractionally‐covered pixel estimates by 18%.
format Article
id doaj-art-e4888f4c86ea4c7587ff2da589f008f0
institution Kabale University
issn 0043-1397
1944-7973
language English
publishDate 2024-11-01
publisher Wiley
record_format Article
series Water Resources Research
spelling doaj-art-e4888f4c86ea4c7587ff2da589f008f02025-08-23T13:05:51ZengWileyWater Resources Research0043-13971944-79732024-11-016011n/an/a10.1029/2023WR036162A Spatially‐Distributed Machine Learning Approach for Fractional Snow Covered Area EstimationShalini Mahanthege0William Kleiber1Karl Rittger2Balaji Rajagopalan3Mary J. Brodzik4Edward Bair5Department of Statistics University of Missouri Columbia MO USADepartment of Applied Mathematics University of Colorado at Boulder Boulder CO USAInstitute of Arctic and Alpine Research University of Colorado at Boulder Boulder CO USADepartment of Civil, Environmental and Architectural Engineering Cooperative Institute for Research in Environmental Sciences University of Colorado Boulder CO USANational Snow and Ice Data Center Cooperative Institute for Research in Environmental Sciences University of Colorado Boulder CO USALeidos Inc. Reston VA USAAbstract Snowpack in mountainous areas often provides water storage for summer and fall, especially in the Western United States. In situ observations of snow properties in mountainous terrain are limited by cost and effort, impacting both temporal and spatial sampling, while remote sensing estimates provide more complete spacetime coverage. Spatial estimates of fractional snow covered area (fSCA) at 30m are available every 16 days from the series of multispectral scanning instruments on Landsat platforms. Daily estimates at 463m spatial resolution are also available from the Moderate Resolution Imaging Spectroradiometer (MODIS) instrument on the Terra satellite. Fusing Landsat and MODIS fSCA images creates high resolution daily spatial estimates of fSCA that are needed for various uses: to support scientists and managers interested in energy and water budgets for water resources and to understand the movement of animals in a changing climate. Here, we propose a new machine learning approach conditioned on MODIS fSCA, as well as a set of physiographic features, and fit to Landsat fSCA over a portion of the Sierra Nevada USA. The predictions are daily 30m fSCA. The approach relies on two stages of spatially‐varying models. The first classifies fSCA into three categories and the second yields estimates within (0, 100) percent fSCA. Separate models are applied and fitted within sub‐regions of the study domain. Compared with a recently‐published machine learning model (Rittger, Krock, et al., 2021), this approach uses spatially local (rather than global) random forests, and improves the classification error of fSCA by 16%, and fractionally‐covered pixel estimates by 18%.https://doi.org/10.1029/2023WR036162random forestMODISLandsatfeature importancedownscalingdata fusion
spellingShingle Shalini Mahanthege
William Kleiber
Karl Rittger
Balaji Rajagopalan
Mary J. Brodzik
Edward Bair
A Spatially‐Distributed Machine Learning Approach for Fractional Snow Covered Area Estimation
Water Resources Research
random forest
MODIS
Landsat
feature importance
downscaling
data fusion
title A Spatially‐Distributed Machine Learning Approach for Fractional Snow Covered Area Estimation
title_full A Spatially‐Distributed Machine Learning Approach for Fractional Snow Covered Area Estimation
title_fullStr A Spatially‐Distributed Machine Learning Approach for Fractional Snow Covered Area Estimation
title_full_unstemmed A Spatially‐Distributed Machine Learning Approach for Fractional Snow Covered Area Estimation
title_short A Spatially‐Distributed Machine Learning Approach for Fractional Snow Covered Area Estimation
title_sort spatially distributed machine learning approach for fractional snow covered area estimation
topic random forest
MODIS
Landsat
feature importance
downscaling
data fusion
url https://doi.org/10.1029/2023WR036162
work_keys_str_mv AT shalinimahanthege aspatiallydistributedmachinelearningapproachforfractionalsnowcoveredareaestimation
AT williamkleiber aspatiallydistributedmachinelearningapproachforfractionalsnowcoveredareaestimation
AT karlrittger aspatiallydistributedmachinelearningapproachforfractionalsnowcoveredareaestimation
AT balajirajagopalan aspatiallydistributedmachinelearningapproachforfractionalsnowcoveredareaestimation
AT maryjbrodzik aspatiallydistributedmachinelearningapproachforfractionalsnowcoveredareaestimation
AT edwardbair aspatiallydistributedmachinelearningapproachforfractionalsnowcoveredareaestimation
AT shalinimahanthege spatiallydistributedmachinelearningapproachforfractionalsnowcoveredareaestimation
AT williamkleiber spatiallydistributedmachinelearningapproachforfractionalsnowcoveredareaestimation
AT karlrittger spatiallydistributedmachinelearningapproachforfractionalsnowcoveredareaestimation
AT balajirajagopalan spatiallydistributedmachinelearningapproachforfractionalsnowcoveredareaestimation
AT maryjbrodzik spatiallydistributedmachinelearningapproachforfractionalsnowcoveredareaestimation
AT edwardbair spatiallydistributedmachinelearningapproachforfractionalsnowcoveredareaestimation