2021
DOI: 10.3390/rs13204033
|View full text |Cite
|
Sign up to set email alerts
|

Application of Random Forest Algorithm for Merging Multiple Satellite Precipitation Products across South Korea

Abstract: Precipitation is a crucial component of the water cycle and plays a key role in hydrological processes. Recently, satellite-based precipitation products (SPPs) have provided grid-based precipitation with spatiotemporal variability. However, SPPs contain a lot of uncertainty in estimated precipitation, and the spatial resolution of these products is still relatively coarse. To overcome these limitations, this study aims to generate new grid-based daily precipitation based on a combination of rainfall observatio… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
8
1

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 36 publications
(12 citation statements)
references
References 63 publications
0
8
1
Order By: Relevance
“…Nevertheless, the monthly mean visibility estimation accuracy was as follows: bias=-0.11 km, RMSE=2.05 km, and r=0.93. These results showed lower variability and higher accuracy than previous studies that quantitatively estimated precipitation using satellite-based (Nguyen et al, 2021), radar-based (Shin et al, 2019), andnumerical model-based (Ko et al, 2020) data using ML algorithms. Therefore, the application of…”
Section: Accepted Manuscriptcontrasting
confidence: 54%
“…Nevertheless, the monthly mean visibility estimation accuracy was as follows: bias=-0.11 km, RMSE=2.05 km, and r=0.93. These results showed lower variability and higher accuracy than previous studies that quantitatively estimated precipitation using satellite-based (Nguyen et al, 2021), radar-based (Shin et al, 2019), andnumerical model-based (Ko et al, 2020) data using ML algorithms. Therefore, the application of…”
Section: Accepted Manuscriptcontrasting
confidence: 54%
“…An RF is a set of decision trees h(x, λ k ) k = 1,…, K, where x is the observed input vector of length p in association with X as a random vector and λ k is the independent vector with an identical distribution. In this study, Y represents the output vector of RF regression with an unweighted average of the results of decision trees (Nguyen et al, 2021;Segal, 2004),…”
Section: Random Forestmentioning
confidence: 99%
“…In recent years, RF has received more attention as an ensemble supervised learning algorithm due to its capability and versatility (Nguyen et al, 2021). An RF is a set of decision trees h(x, λ k ) k = 1,…, K, where x is the observed input vector of length p in association with X as a random vector and λ k is the independent vector with an identical distribution.…”
Section: Random Forestmentioning
confidence: 99%
See 1 more Smart Citation
“…Due to the dynamic, complex and variable nature of flood risk factors, the spatial distribution of the flood‐bearing components cannot fully utilize the spatial information of all variables, but is forced to use homogeneity assumptions. Currently, most of the uncertainty studies (Hall et al., 2005; Li et al., 2017; Nguyen et al., 2021; Yu et al., 2016) in damage assessment have focused on the hydrological processes of floods, while the variability of damage ratios within and outside the domain due to spatial scale variation in the flood‐bearing components is rarely considered. It is mainly attributed to that the spatial and temporal distribution of spatial information of real‐world flood‐bearing components cannot be fully obtained due to limited measurement methods and complex spatial and temporal variations (Anugraha et al., 2020; Liu et al., 2015; Toure et al., 2018).…”
Section: Introductionmentioning
confidence: 99%