Paper Info
Title
Analyze the rainfall of landslide on Apache Spark
Abstract
In recent years, due to the frequent occurrence of extreme rainfall events, the intensity of rainfall characteristics in Taiwan has been changed. In the event of heavy rainfall, it is worth our attention for a long time. Through the big data analysis platform of Apache Spark and R language, this paper uses the random forest algorithm to construct the regional rainfall patterns. in order to obtain the meteorological information on the Internet, datasets are retrieved from the Pinglin Weather Station of Central Meteorological Administration of Taiwan's Ministry of Communications. The meteorological data such as rainfall, temperature and humidity at the weather station will be crawled from the web first. After pre-processing meteorological data, this paper applies random forest algorithm on the platform of Apache Spark to calculate and analyze the results. From simulation results, the obtained root mean square error of test data for the platform Apache Spark has better results than traditional platform.
Year
DOI
Venue
2018
10.1109/ICACI.2018.8377482
2018 Tenth International Conference on Advanced Computational Intelligence (ICACI)
Keywords
Field
DocType
big data,spark,random forest,decision tree
Meteorology,Spark (mathematics),Weather station,Mean squared error,Environmental science,Test data,Landslide,Random forest,Big data,Precipitation
Conference
ISBN
Citations 
PageRank 
978-1-5386-4363-1
0
0.34
References 
Authors
3
6
Name
Order
Citations
PageRank
Chou-Yuan Lee129517.36
Jian-Qiong Huang200.34
Wei-Ping Ma300.34
Yulin Weng441.46
Yuan-Chih Lee500.34
Zne-Jung Lee694043.45