TY - JOUR
T1 - Analysis of secondary-factor combinations of landslides using improved association rule algorithms
T2 - a case study of Kitakyushu in Japan
AU - Li, Jiaying
AU - Wang, Wei Dong
AU - Han, Zheng
AU - Chen, Guangqi
N1 - Funding Information:
This work was supported by the National Natural Science Foundation of China under Grant No. 51478483 and No. 41702310 and the China Scholarship Council.
Publisher Copyright:
© 2021 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
PY - 2021
Y1 - 2021
N2 - Landslide analysis prevents landslides from threatening resident safety and property, and the predominant method is susceptibility assessment which is cumbersome and time-consuming. The association rule algorithm (ARA) is proposed to mine the correlation between the factors and landslides simply and rapidly. The original ARA cannot reflect the scope of landslides which is non-negligible for landslide analysis and is thus improved to mine the frequent secondary-factor combinations (SFCs). Firstly, eight factors are selected using the out-of-bag error and chi-squared ((Formula presented.)) test. The accuracy of the factor selection is further verified employing landslide susceptibility assessment which is predicted using 30% of study grid data selected randomly as the training data. The improved ARA employs the area of historical landslides to mine the frequent SFCs, and the results are then verified by the frequency ratio and (Formula presented.) test. It is concluded that the frequent SFCs are: (21, 41), (21, 74), (34, 41), (34, 74), (41, 74), (21, 41, 74), and (34, 41, 74), and the area with the SFCs needs special protection. The present study provides a valuable reference for the primary prevention of landslides.
AB - Landslide analysis prevents landslides from threatening resident safety and property, and the predominant method is susceptibility assessment which is cumbersome and time-consuming. The association rule algorithm (ARA) is proposed to mine the correlation between the factors and landslides simply and rapidly. The original ARA cannot reflect the scope of landslides which is non-negligible for landslide analysis and is thus improved to mine the frequent secondary-factor combinations (SFCs). Firstly, eight factors are selected using the out-of-bag error and chi-squared ((Formula presented.)) test. The accuracy of the factor selection is further verified employing landslide susceptibility assessment which is predicted using 30% of study grid data selected randomly as the training data. The improved ARA employs the area of historical landslides to mine the frequent SFCs, and the results are then verified by the frequency ratio and (Formula presented.) test. It is concluded that the frequent SFCs are: (21, 41), (21, 74), (34, 41), (34, 74), (41, 74), (21, 41, 74), and (34, 41, 74), and the area with the SFCs needs special protection. The present study provides a valuable reference for the primary prevention of landslides.
UR - http://www.scopus.com/inward/record.url?scp=85110936893&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85110936893&partnerID=8YFLogxK
U2 - 10.1080/19475705.2021.1947904
DO - 10.1080/19475705.2021.1947904
M3 - Article
AN - SCOPUS:85110936893
VL - 12
SP - 1885
EP - 1904
JO - Geomatics, Natural Hazards and Risk
JF - Geomatics, Natural Hazards and Risk
SN - 1947-5705
IS - 1
ER -