Back to Search
Start Over
In situ observation-constrained global surface soil moisture using random forest model
- Source :
- Remote Sensing, Vol 13, Iss 4893, p 4893 (2021), Remote sensing, 13(23):4893. MDPI, Remote Sensing; Volume 13; Issue 23; Pages: 4893
- Publication Year :
- 2021
-
Abstract
- The inherent biases of different long-term gridded surface soil moisture (SSM) products, unconstrained by the in situ observations, implies different spatio-temporal patterns. In this study, the Random Forest (RF) model was trained to predict SSM from relevant land surface feature variables (i.e., land surface temperature, vegetation indices, soil texture, and geographical information) and precipitation, based on the in situ soil moisture data of the International Soil Moisture Network (ISMN.). The results of the RF model show an RMSE of 0.05 m3 m􀀀3 and a correlation coefficient of 0.9. The calculated impurity-based feature importance indicates that the Antecedent Precipitation Index affects most of the predicted soil moisture. The geographical coordinates also significantly influence the prediction (i.e., RMSE was reduced to 0.03 m3 m􀀀3 after considering geographical coordinates), followed by land surface temperature, vegetation indices, and soil texture. The spatiotemporal pattern of RF predicted SSM was compared with the European Space Agency Climate Change Initiative (ESA-CCI) soil moisture product, using both time-longitude and latitude diagrams. The results indicate that the RF SSM captures the spatial distribution and the daily, seasonal, and annual variabilities globally.
- Subjects :
- 010504 meteorology & atmospheric sciences
Correlation coefficient
Soil texture
Science
0207 environmental engineering
Climate change
02 engineering and technology
Atmospheric sciences
Spatial distribution
01 natural sciences
Latitude
Global scale
Precipitation
020701 environmental engineering
Water content
soil moisture
random forest
global scale
in situ constrained
feature importance
antecedent precipitation index
0105 earth and related environmental sciences
Antecedent precipitation index
In situ constrained
Vegetation
15. Life on land
Feature importance
13. Climate action
ITC-ISI-JOURNAL-ARTICLE
General Earth and Planetary Sciences
Environmental science
Soil moisture
ITC-GOLD
Random forest
Subjects
Details
- Language :
- English
- ISSN :
- 20724292
- Volume :
- 13
- Issue :
- 23
- Database :
- OpenAIRE
- Journal :
- Remote sensing
- Accession number :
- edsair.doi.dedup.....cf91533756709d85662906b3fd272763