Loading…
Spatial snow water equivalent estimation for mountainous areas using wireless-sensor networks and remote-sensing products
We developed an approach to estimate snow water equivalent (SWE) through interpolation of spatially representative point measurements using a k-nearest neighbors (k-NN) algorithm and historical spatial SWE data. It accurately reproduced measured SWE, using different data sources for training and eva...
Saved in:
Published in: | Remote sensing of environment 2018-09, Vol.215, p.44-56 |
---|---|
Main Authors: | , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c368t-d55647cd5d63d4c58e920057a19bc74eb1df755bb441f58063d0387c71bf6d353 |
---|---|
cites | cdi_FETCH-LOGICAL-c368t-d55647cd5d63d4c58e920057a19bc74eb1df755bb441f58063d0387c71bf6d353 |
container_end_page | 56 |
container_issue | |
container_start_page | 44 |
container_title | Remote sensing of environment |
container_volume | 215 |
creator | Zheng, Zeshi Molotch, Noah P. Oroza, Carlos A. Conklin, Martha H. Bales, Roger C. |
description | We developed an approach to estimate snow water equivalent (SWE) through interpolation of spatially representative point measurements using a k-nearest neighbors (k-NN) algorithm and historical spatial SWE data. It accurately reproduced measured SWE, using different data sources for training and evaluation. In the central-Sierra American River basin, we used a k-NN algorithm to interpolate data from continuous snow-depth measurements in 10 sensor clusters by fusing them with 14 years of daily 500-m resolution SWE-reconstruction maps. Accurate SWE estimation over the melt season shows the potential for providing daily, near real-time distributed snowmelt estimates. Further south, in the Merced-Tuolumne basins, we evaluated the potential of k-NN approach to improve real-time SWE estimates. Lacking dense ground-measurement networks, we simulated k-NN interpolation of sensor data using selected pixels of a bi-weekly Lidar-derived snow water equivalent product. k-NN extrapolations underestimate the Lidar-derived SWE, with a maximum bias of −10 cm at elevations below 3000 m and +15 cm above 3000 m. This bias was reduced by using a Gaussian-process regression model to spatially distribute residuals. Using as few as 10 scenes of Lidar-derived SWE from 2014 as training data in the k-NN to estimate the 2016 spatial SWE, both RMSEs and MAEs were reduced from around 20–25 cm to 10–15 cm comparing to using SWE reconstructions as training data. We found that the spatial accuracy of the historical data is more important for learning the spatial distribution of SWE than the number of historical scenes available. Blending continuous spatially representative ground-based sensors with a historical library of SWE reconstructions over the same basin can provide real-time spatial SWE maps that accurately represents Lidar-measured snow depth; and the estimates can be improved by using historical Lidar scans instead of SWE reconstructions.
•k-Nearest neighbors can blend ground measurements and space observations of snowpack.•Topographic variables can be used to reduce bias in k-NN estimates.•The accuracy of historical spatial data is important for k-NN approach. |
doi_str_mv | 10.1016/j.rse.2018.05.029 |
format | article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2100881486</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0034425718302578</els_id><sourcerecordid>2100881486</sourcerecordid><originalsourceid>FETCH-LOGICAL-c368t-d55647cd5d63d4c58e920057a19bc74eb1df755bb441f58063d0387c71bf6d353</originalsourceid><addsrcrecordid>eNp9kE1vEzEQhi0EEqHlB3CzxHmX8a69dsQJVVCQKnGAni2vPVs5JHbq8Tbqv69DOHOawzzvfDyMfRDQCxDTp11fCPsBhOlB9TBsX7GNMHrbgQb5mm0ARtnJQem37B3RDkAoo8WGPf86uhrdnlPKJ35yFQvHxzU-uT2mypFqPDQgJ77kwg95TdXFlFfirqAjvlJMD_wUC-6RqCNM1LiE9ZTLnwalwAsecsW_rTN7LDmsvtI1e7O4PeH7f_WK3X_7-vvme3f38_bHzZe7zo-TqV1QapLaBxWmMUivDG4HAKWd2M5eS5xFWLRS8yylWJSBRsFotNdiXqYwqvGKfbzMbYsf1_aQ3eW1pLbSDgLAGCHN1ChxoXzJRAUXeyzt8_JsBdizYbuzzbA9G7agbDPcMp8vGWznP0UslnzE5DE0Hb7akON_0i_jy4cC</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2100881486</pqid></control><display><type>article</type><title>Spatial snow water equivalent estimation for mountainous areas using wireless-sensor networks and remote-sensing products</title><source>ScienceDirect Journals</source><creator>Zheng, Zeshi ; Molotch, Noah P. ; Oroza, Carlos A. ; Conklin, Martha H. ; Bales, Roger C.</creator><creatorcontrib>Zheng, Zeshi ; Molotch, Noah P. ; Oroza, Carlos A. ; Conklin, Martha H. ; Bales, Roger C.</creatorcontrib><description>We developed an approach to estimate snow water equivalent (SWE) through interpolation of spatially representative point measurements using a k-nearest neighbors (k-NN) algorithm and historical spatial SWE data. It accurately reproduced measured SWE, using different data sources for training and evaluation. In the central-Sierra American River basin, we used a k-NN algorithm to interpolate data from continuous snow-depth measurements in 10 sensor clusters by fusing them with 14 years of daily 500-m resolution SWE-reconstruction maps. Accurate SWE estimation over the melt season shows the potential for providing daily, near real-time distributed snowmelt estimates. Further south, in the Merced-Tuolumne basins, we evaluated the potential of k-NN approach to improve real-time SWE estimates. Lacking dense ground-measurement networks, we simulated k-NN interpolation of sensor data using selected pixels of a bi-weekly Lidar-derived snow water equivalent product. k-NN extrapolations underestimate the Lidar-derived SWE, with a maximum bias of −10 cm at elevations below 3000 m and +15 cm above 3000 m. This bias was reduced by using a Gaussian-process regression model to spatially distribute residuals. Using as few as 10 scenes of Lidar-derived SWE from 2014 as training data in the k-NN to estimate the 2016 spatial SWE, both RMSEs and MAEs were reduced from around 20–25 cm to 10–15 cm comparing to using SWE reconstructions as training data. We found that the spatial accuracy of the historical data is more important for learning the spatial distribution of SWE than the number of historical scenes available. Blending continuous spatially representative ground-based sensors with a historical library of SWE reconstructions over the same basin can provide real-time spatial SWE maps that accurately represents Lidar-measured snow depth; and the estimates can be improved by using historical Lidar scans instead of SWE reconstructions.
•k-Nearest neighbors can blend ground measurements and space observations of snowpack.•Topographic variables can be used to reduce bias in k-NN estimates.•The accuracy of historical spatial data is important for k-NN approach.</description><identifier>ISSN: 0034-4257</identifier><identifier>EISSN: 1879-0704</identifier><identifier>DOI: 10.1016/j.rse.2018.05.029</identifier><language>eng</language><publisher>New York: Elsevier Inc</publisher><subject>Algorithms ; Bias ; Computer simulation ; Depth measurement ; Ecosystems ; Equivalence ; Estimates ; Gaussian process ; Hydrology ; Interpolation ; k-Nearest neighbors ; K-nearest neighbors algorithm ; Lidar ; MODIS ; Mountain hydrology ; Mountainous areas ; Real time ; Reconstructions ; Regression models ; Remote sensing ; Remote sensors ; River basins ; Rivers ; Sensors ; Sierra Nevada ; Snow ; Snow accumulation ; Snow depth ; Snow water equivalent ; Snowmelt ; Spatial data ; Spatial discrimination learning ; Spatial distribution ; Training ; Water resources ; Water resources management ; Wireless sensor networks</subject><ispartof>Remote sensing of environment, 2018-09, Vol.215, p.44-56</ispartof><rights>2018 Elsevier Inc.</rights><rights>Copyright Elsevier BV Sep 15, 2018</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c368t-d55647cd5d63d4c58e920057a19bc74eb1df755bb441f58063d0387c71bf6d353</citedby><cites>FETCH-LOGICAL-c368t-d55647cd5d63d4c58e920057a19bc74eb1df755bb441f58063d0387c71bf6d353</cites><orcidid>0000-0003-4733-8060 ; 0000-0001-7944-6985</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>315,786,790,27957,27958</link.rule.ids></links><search><creatorcontrib>Zheng, Zeshi</creatorcontrib><creatorcontrib>Molotch, Noah P.</creatorcontrib><creatorcontrib>Oroza, Carlos A.</creatorcontrib><creatorcontrib>Conklin, Martha H.</creatorcontrib><creatorcontrib>Bales, Roger C.</creatorcontrib><title>Spatial snow water equivalent estimation for mountainous areas using wireless-sensor networks and remote-sensing products</title><title>Remote sensing of environment</title><description>We developed an approach to estimate snow water equivalent (SWE) through interpolation of spatially representative point measurements using a k-nearest neighbors (k-NN) algorithm and historical spatial SWE data. It accurately reproduced measured SWE, using different data sources for training and evaluation. In the central-Sierra American River basin, we used a k-NN algorithm to interpolate data from continuous snow-depth measurements in 10 sensor clusters by fusing them with 14 years of daily 500-m resolution SWE-reconstruction maps. Accurate SWE estimation over the melt season shows the potential for providing daily, near real-time distributed snowmelt estimates. Further south, in the Merced-Tuolumne basins, we evaluated the potential of k-NN approach to improve real-time SWE estimates. Lacking dense ground-measurement networks, we simulated k-NN interpolation of sensor data using selected pixels of a bi-weekly Lidar-derived snow water equivalent product. k-NN extrapolations underestimate the Lidar-derived SWE, with a maximum bias of −10 cm at elevations below 3000 m and +15 cm above 3000 m. This bias was reduced by using a Gaussian-process regression model to spatially distribute residuals. Using as few as 10 scenes of Lidar-derived SWE from 2014 as training data in the k-NN to estimate the 2016 spatial SWE, both RMSEs and MAEs were reduced from around 20–25 cm to 10–15 cm comparing to using SWE reconstructions as training data. We found that the spatial accuracy of the historical data is more important for learning the spatial distribution of SWE than the number of historical scenes available. Blending continuous spatially representative ground-based sensors with a historical library of SWE reconstructions over the same basin can provide real-time spatial SWE maps that accurately represents Lidar-measured snow depth; and the estimates can be improved by using historical Lidar scans instead of SWE reconstructions.
•k-Nearest neighbors can blend ground measurements and space observations of snowpack.•Topographic variables can be used to reduce bias in k-NN estimates.•The accuracy of historical spatial data is important for k-NN approach.</description><subject>Algorithms</subject><subject>Bias</subject><subject>Computer simulation</subject><subject>Depth measurement</subject><subject>Ecosystems</subject><subject>Equivalence</subject><subject>Estimates</subject><subject>Gaussian process</subject><subject>Hydrology</subject><subject>Interpolation</subject><subject>k-Nearest neighbors</subject><subject>K-nearest neighbors algorithm</subject><subject>Lidar</subject><subject>MODIS</subject><subject>Mountain hydrology</subject><subject>Mountainous areas</subject><subject>Real time</subject><subject>Reconstructions</subject><subject>Regression models</subject><subject>Remote sensing</subject><subject>Remote sensors</subject><subject>River basins</subject><subject>Rivers</subject><subject>Sensors</subject><subject>Sierra Nevada</subject><subject>Snow</subject><subject>Snow accumulation</subject><subject>Snow depth</subject><subject>Snow water equivalent</subject><subject>Snowmelt</subject><subject>Spatial data</subject><subject>Spatial discrimination learning</subject><subject>Spatial distribution</subject><subject>Training</subject><subject>Water resources</subject><subject>Water resources management</subject><subject>Wireless sensor networks</subject><issn>0034-4257</issn><issn>1879-0704</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><recordid>eNp9kE1vEzEQhi0EEqHlB3CzxHmX8a69dsQJVVCQKnGAni2vPVs5JHbq8Tbqv69DOHOawzzvfDyMfRDQCxDTp11fCPsBhOlB9TBsX7GNMHrbgQb5mm0ARtnJQem37B3RDkAoo8WGPf86uhrdnlPKJ35yFQvHxzU-uT2mypFqPDQgJ77kwg95TdXFlFfirqAjvlJMD_wUC-6RqCNM1LiE9ZTLnwalwAsecsW_rTN7LDmsvtI1e7O4PeH7f_WK3X_7-vvme3f38_bHzZe7zo-TqV1QapLaBxWmMUivDG4HAKWd2M5eS5xFWLRS8yylWJSBRsFotNdiXqYwqvGKfbzMbYsf1_aQ3eW1pLbSDgLAGCHN1ChxoXzJRAUXeyzt8_JsBdizYbuzzbA9G7agbDPcMp8vGWznP0UslnzE5DE0Hb7akON_0i_jy4cC</recordid><startdate>20180915</startdate><enddate>20180915</enddate><creator>Zheng, Zeshi</creator><creator>Molotch, Noah P.</creator><creator>Oroza, Carlos A.</creator><creator>Conklin, Martha H.</creator><creator>Bales, Roger C.</creator><general>Elsevier Inc</general><general>Elsevier BV</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7QF</scope><scope>7QO</scope><scope>7QQ</scope><scope>7SC</scope><scope>7SE</scope><scope>7SN</scope><scope>7SP</scope><scope>7SR</scope><scope>7TA</scope><scope>7TB</scope><scope>7TG</scope><scope>7U5</scope><scope>8BQ</scope><scope>8FD</scope><scope>C1K</scope><scope>F28</scope><scope>FR3</scope><scope>H8D</scope><scope>H8G</scope><scope>JG9</scope><scope>JQ2</scope><scope>KL.</scope><scope>KR7</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>P64</scope><orcidid>https://orcid.org/0000-0003-4733-8060</orcidid><orcidid>https://orcid.org/0000-0001-7944-6985</orcidid></search><sort><creationdate>20180915</creationdate><title>Spatial snow water equivalent estimation for mountainous areas using wireless-sensor networks and remote-sensing products</title><author>Zheng, Zeshi ; Molotch, Noah P. ; Oroza, Carlos A. ; Conklin, Martha H. ; Bales, Roger C.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c368t-d55647cd5d63d4c58e920057a19bc74eb1df755bb441f58063d0387c71bf6d353</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Algorithms</topic><topic>Bias</topic><topic>Computer simulation</topic><topic>Depth measurement</topic><topic>Ecosystems</topic><topic>Equivalence</topic><topic>Estimates</topic><topic>Gaussian process</topic><topic>Hydrology</topic><topic>Interpolation</topic><topic>k-Nearest neighbors</topic><topic>K-nearest neighbors algorithm</topic><topic>Lidar</topic><topic>MODIS</topic><topic>Mountain hydrology</topic><topic>Mountainous areas</topic><topic>Real time</topic><topic>Reconstructions</topic><topic>Regression models</topic><topic>Remote sensing</topic><topic>Remote sensors</topic><topic>River basins</topic><topic>Rivers</topic><topic>Sensors</topic><topic>Sierra Nevada</topic><topic>Snow</topic><topic>Snow accumulation</topic><topic>Snow depth</topic><topic>Snow water equivalent</topic><topic>Snowmelt</topic><topic>Spatial data</topic><topic>Spatial discrimination learning</topic><topic>Spatial distribution</topic><topic>Training</topic><topic>Water resources</topic><topic>Water resources management</topic><topic>Wireless sensor networks</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zheng, Zeshi</creatorcontrib><creatorcontrib>Molotch, Noah P.</creatorcontrib><creatorcontrib>Oroza, Carlos A.</creatorcontrib><creatorcontrib>Conklin, Martha H.</creatorcontrib><creatorcontrib>Bales, Roger C.</creatorcontrib><collection>CrossRef</collection><collection>Aluminium Industry Abstracts</collection><collection>Biotechnology Research Abstracts</collection><collection>Ceramic Abstracts</collection><collection>Computer and Information Systems Abstracts</collection><collection>Corrosion Abstracts</collection><collection>Ecology Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>Materials Business File</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Meteorological & Geoastrophysical Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Copper Technical Reference Library</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Meteorological & Geoastrophysical Abstracts - Academic</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Biotechnology and BioEngineering Abstracts</collection><jtitle>Remote sensing of environment</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zheng, Zeshi</au><au>Molotch, Noah P.</au><au>Oroza, Carlos A.</au><au>Conklin, Martha H.</au><au>Bales, Roger C.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Spatial snow water equivalent estimation for mountainous areas using wireless-sensor networks and remote-sensing products</atitle><jtitle>Remote sensing of environment</jtitle><date>2018-09-15</date><risdate>2018</risdate><volume>215</volume><spage>44</spage><epage>56</epage><pages>44-56</pages><issn>0034-4257</issn><eissn>1879-0704</eissn><abstract>We developed an approach to estimate snow water equivalent (SWE) through interpolation of spatially representative point measurements using a k-nearest neighbors (k-NN) algorithm and historical spatial SWE data. It accurately reproduced measured SWE, using different data sources for training and evaluation. In the central-Sierra American River basin, we used a k-NN algorithm to interpolate data from continuous snow-depth measurements in 10 sensor clusters by fusing them with 14 years of daily 500-m resolution SWE-reconstruction maps. Accurate SWE estimation over the melt season shows the potential for providing daily, near real-time distributed snowmelt estimates. Further south, in the Merced-Tuolumne basins, we evaluated the potential of k-NN approach to improve real-time SWE estimates. Lacking dense ground-measurement networks, we simulated k-NN interpolation of sensor data using selected pixels of a bi-weekly Lidar-derived snow water equivalent product. k-NN extrapolations underestimate the Lidar-derived SWE, with a maximum bias of −10 cm at elevations below 3000 m and +15 cm above 3000 m. This bias was reduced by using a Gaussian-process regression model to spatially distribute residuals. Using as few as 10 scenes of Lidar-derived SWE from 2014 as training data in the k-NN to estimate the 2016 spatial SWE, both RMSEs and MAEs were reduced from around 20–25 cm to 10–15 cm comparing to using SWE reconstructions as training data. We found that the spatial accuracy of the historical data is more important for learning the spatial distribution of SWE than the number of historical scenes available. Blending continuous spatially representative ground-based sensors with a historical library of SWE reconstructions over the same basin can provide real-time spatial SWE maps that accurately represents Lidar-measured snow depth; and the estimates can be improved by using historical Lidar scans instead of SWE reconstructions.
•k-Nearest neighbors can blend ground measurements and space observations of snowpack.•Topographic variables can be used to reduce bias in k-NN estimates.•The accuracy of historical spatial data is important for k-NN approach.</abstract><cop>New York</cop><pub>Elsevier Inc</pub><doi>10.1016/j.rse.2018.05.029</doi><tpages>13</tpages><orcidid>https://orcid.org/0000-0003-4733-8060</orcidid><orcidid>https://orcid.org/0000-0001-7944-6985</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0034-4257 |
ispartof | Remote sensing of environment, 2018-09, Vol.215, p.44-56 |
issn | 0034-4257 1879-0704 |
language | eng |
recordid | cdi_proquest_journals_2100881486 |
source | ScienceDirect Journals |
subjects | Algorithms Bias Computer simulation Depth measurement Ecosystems Equivalence Estimates Gaussian process Hydrology Interpolation k-Nearest neighbors K-nearest neighbors algorithm Lidar MODIS Mountain hydrology Mountainous areas Real time Reconstructions Regression models Remote sensing Remote sensors River basins Rivers Sensors Sierra Nevada Snow Snow accumulation Snow depth Snow water equivalent Snowmelt Spatial data Spatial discrimination learning Spatial distribution Training Water resources Water resources management Wireless sensor networks |
title | Spatial snow water equivalent estimation for mountainous areas using wireless-sensor networks and remote-sensing products |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-22T17%3A38%3A27IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Spatial%20snow%20water%20equivalent%20estimation%20for%20mountainous%20areas%20using%20wireless-sensor%20networks%20and%20remote-sensing%20products&rft.jtitle=Remote%20sensing%20of%20environment&rft.au=Zheng,%20Zeshi&rft.date=2018-09-15&rft.volume=215&rft.spage=44&rft.epage=56&rft.pages=44-56&rft.issn=0034-4257&rft.eissn=1879-0704&rft_id=info:doi/10.1016/j.rse.2018.05.029&rft_dat=%3Cproquest_cross%3E2100881486%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c368t-d55647cd5d63d4c58e920057a19bc74eb1df755bb441f58063d0387c71bf6d353%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2100881486&rft_id=info:pmid/&rfr_iscdi=true |