Related Experiment Video
Updated: Jan 10, 2026
08:16
Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
Published on: October 24, 2025
448
Improving the accuracy of gridded snow depth estimation through multi-source data and a machine learning fusion
Dejing Qiao1,2,3, Xiaoxiao Chen4, Jianmin Zhou5
1College of Surveying and Geo-Informatics , North China University of Water Resources and Electric Power , 450046, Zhengzhou, China. qiao_dejing@163.com.
Scientific Reports
|November 20, 2025
Summary
A new random forest (RF) fusion method improves snow depth (SD) estimation by integrating multiple data sources. This approach enhances spatial distribution accuracy for water resources and climate change studies.
Area of Science:
- Earth Science
- Environmental Science
- Remote Sensing
Background:
- Snow depth (SD) is crucial for water resource assessment and climate change monitoring.
- Existing SD data from various sources (passive microwave, reanalysis, in-situ) often lack completeness and consistency.
- These limitations hinder their utility for scientific research.
Purpose of the Study:
- To develop and validate a novel snow depth fusion method using the random forest algorithm (RF).
- To generate a more accurate and consistent spatial distribution of snow depth over China.
- To improve the spatiotemporal representation of snow cover by integrating multi-source data.
Main Methods:
- Developed a snow depth fusion model based on the random forest (RF) algorithm.
- Integrated five SD products (WESTDC, ERA-Interim, CMC, GLDAS-NOAH, MERRA2) as input data.
- Incorporated ancillary data including land cover types, forest cover, geographical information, and surface roughness.
Main Results:
- The fused snow depth data (RF-SD) demonstrated improved accuracy compared to individual products.
- Kling-Gupta efficiency (KGE) increased from 0.21-0.64 to 0.73 against in-situ observations.
- Root mean square error (RMSE) was reduced to 5.1 cm, indicating enhanced precision.
Conclusions:
- The RF-based fusion method effectively integrates multi-source SD data, leveraging their respective strengths.
- This approach significantly enhances the accuracy and consistency of snow depth estimation.
- The improved RF-SD data are valuable for hydrological and climate change research in China.
Related Concept Videos
01:03Precipitation Gravimetry
13.2K
Precipitation gravimetry is based on converting an analyte into a sparingly soluble precipitate, which is separated by filtration and weighed. An ideal precipitate should be pure, insoluble, of known composition, and easily filtered from the reaction mixture.
In determining nickel by gravimetric analysis, a precipitant of ethanolic dimethylglyoxime is added to a hot nickel salt solution. This is quickly followed by the dropwise addition of dilute ammonia solution until precipitation occurs. A...
In determining nickel by gravimetric analysis, a precipitant of ethanolic dimethylglyoxime is added to a hot nickel salt solution. This is quickly followed by the dropwise addition of dilute ammonia solution until precipitation occurs. A...
13.2K
01:17Precipitation and Co-precipitation
4.0K
Precipitation and coprecipitation methods can be used to separate a mixture of ions in a solution. In qualitative inorganic analysis, ions that form sparingly soluble precipitates with the same reagent are separated based on the differences in solubility products. For example, consider the separation of Cu(II) and Fe(II) ions by precipitation as insoluble sulfides. First, copper(II) sulfide is precipitated by the addition of acidic H2S, where the dissociation of H2S is suppressed. Adding H2S...
4.0K