Articles | Volume 14, issue 6
https://doi.org/10.5194/tc-14-1763-2020
https://doi.org/10.5194/tc-14-1763-2020
Research article
 | 
03 Jun 2020
Research article |  | 03 Jun 2020

Snow depth estimation and historical data reconstruction over China based on a random forest machine learning approach

Jianwei Yang, Lingmei Jiang, Kari Luojus, Jinmei Pan, Juha Lemmetyinen, Matias Takala, and Shengli Wu

Download

Interactive discussion

Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision
ED: Reconsider after major revisions (further review by editor and referees) (06 Jan 2020) by Florent Dominé
AR by Jianwei Yang on behalf of the Authors (12 Feb 2020)  Author's response   Manuscript 
ED: Referee Nomination & Report Request started (19 Feb 2020) by Florent Dominé
RR by Anonymous Referee #2 (25 Feb 2020)
RR by Divyesh Varade (08 Mar 2020)
ED: Publish subject to minor revisions (review by editor) (12 Mar 2020) by Florent Dominé
AR by Jianwei Yang on behalf of the Authors (22 Mar 2020)  Author's response   Manuscript 
ED: Publish subject to minor revisions (review by editor) (07 Apr 2020) by Florent Dominé
AR by Jianwei Yang on behalf of the Authors (13 Apr 2020)  Author's response   Manuscript 
ED: Publish as is (23 Apr 2020) by Florent Dominé
AR by Jianwei Yang on behalf of the Authors (02 May 2020)  Author's response   Manuscript 
Download
Short summary
There are many challenges for accurate snow depth estimation using passive microwave data. Machine learning (ML) techniques are deemed to be powerful tools for establishing nonlinear relations between independent variables and a given target variable. In this study, we investigate the potential capability of the random forest (RF) model on snow depth estimation at temporal and spatial scales. The result indicates that the fitted RF algorithms perform better on temporal than spatial scales.