Spatial downscaling of SMAP radiometer soil moisture using radar data: Application of machine learning to the SMAPEx and SMAPVEX campaigns

IF 5.7 Q1 ENVIRONMENTAL SCIENCES Science of Remote Sensing Pub Date : 2024-02-21 DOI:10.1016/j.srs.2024.100122
Elaheh Ghafari , Jeffrey P. Walker , Liujun Zhu , Andreas Colliander , Alireza Faridhosseini
{"title":"Spatial downscaling of SMAP radiometer soil moisture using radar data: Application of machine learning to the SMAPEx and SMAPVEX campaigns","authors":"Elaheh Ghafari ,&nbsp;Jeffrey P. Walker ,&nbsp;Liujun Zhu ,&nbsp;Andreas Colliander ,&nbsp;Alireza Faridhosseini","doi":"10.1016/j.srs.2024.100122","DOIUrl":null,"url":null,"abstract":"<div><p>This study developed a random forest approach for downscaling the coarse-resolution (36 km) soil moisture measured by The National Aeronautics and Space Administration (NASA) Soil Moisture Active Passive (SMAP) mission to 1 km spatial resolution, utilizing airborne remotely sensed data (radar backscatter and radiometer retrieved soil moisture), vegetation characteristics (normalized difference vegetation index), soil properties, topography, and ground soil moisture measurements from before the launch of SMAP for training a random forest model. The 36 km SMAP soil moisture product was then downscaled by the trained model to 1 km resolution using the information from SMAP. The downscaled soil moisture was evaluated using airborne retrieved soil moisture observations and ground soil moisture measurements. Considering the airborne retrieved soil moisture as a reference, the results demonstrated that the proposed random forest model could downscale the SMAP radiometer product to 1 km resolution with a correlation coefficient of 0.97, unbiased Root Mean Square Error of 0.048 m<sup>3</sup> m<sup>−3</sup> and bias of 0.016 m<sup>3</sup> m<sup>−3</sup>. Accordingly, the downscaled soil moisture captured the spatial and temporal heterogeneity and demonstrated the potential of the proposed machine learning model for soil moisture downscaling.</p></div>","PeriodicalId":101147,"journal":{"name":"Science of Remote Sensing","volume":"9 ","pages":"Article 100122"},"PeriodicalIF":5.7000,"publicationDate":"2024-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666017224000063/pdfft?md5=90443d5f179fbc75eaf58cbf6d58a3df&pid=1-s2.0-S2666017224000063-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Science of Remote Sensing","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666017224000063","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0

Abstract

This study developed a random forest approach for downscaling the coarse-resolution (36 km) soil moisture measured by The National Aeronautics and Space Administration (NASA) Soil Moisture Active Passive (SMAP) mission to 1 km spatial resolution, utilizing airborne remotely sensed data (radar backscatter and radiometer retrieved soil moisture), vegetation characteristics (normalized difference vegetation index), soil properties, topography, and ground soil moisture measurements from before the launch of SMAP for training a random forest model. The 36 km SMAP soil moisture product was then downscaled by the trained model to 1 km resolution using the information from SMAP. The downscaled soil moisture was evaluated using airborne retrieved soil moisture observations and ground soil moisture measurements. Considering the airborne retrieved soil moisture as a reference, the results demonstrated that the proposed random forest model could downscale the SMAP radiometer product to 1 km resolution with a correlation coefficient of 0.97, unbiased Root Mean Square Error of 0.048 m3 m−3 and bias of 0.016 m3 m−3. Accordingly, the downscaled soil moisture captured the spatial and temporal heterogeneity and demonstrated the potential of the proposed machine learning model for soil moisture downscaling.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用雷达数据对 SMAP 辐射计土壤湿度进行空间降尺度:将机器学习应用于 SMAPEx 和 SMAPVEX 项目
本研究利用机载遥感数据(雷达后向散射和辐射计检索的土壤湿度)、植被特征(归一化差异植被指数)、土壤特性、地形和 SMAP 发射前的地面土壤湿度测量数据,开发了一种随机森林方法,用于将美国国家航空航天局(NASA)土壤湿度主动被动(SMAP)任务测量的粗分辨率(36 千米)土壤湿度降尺度到 1 千米空间分辨率。然后,经过训练的模型利用 SMAP 的信息,将 36 千米的 SMAP 土壤水分产品降尺度为 1 千米分辨率。利用机载土壤水分观测数据和地面土壤水分测量数据对降级后的土壤水分进行评估。结果表明,以航空获取的土壤水分为参考,所建议的随机森林模型可将 SMAP 辐射计产品降尺度至 1 km 分辨率,相关系数为 0.97,无偏均方根误差为 0.048 m3 m-3,偏差为 0.016 m3 m-3。因此,降尺度土壤水分捕捉到了时空异质性,证明了所提出的机器学习模型在土壤水分降尺度方面的潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
12.20
自引率
0.00%
发文量
0
期刊最新文献
Quantifying volumes of volcanic deposits using time-averaged ASTER digital elevation models Global soil moisture mapping at 5 km by combining GNSS reflectometry and machine learning in view of HydroGNSS Coastal vertical land motion across Southeast Asia derived from combining tide gauge and satellite altimetry observations Identifying thermokarst lakes using deep learning and high-resolution satellite images A two-stage deep learning architecture for detection global coastal and offshore submesoscale ocean eddy using SDGSAT-1 multispectral imagery
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1