Regional Typhoon Track Prediction Using Ensemble k-Nearest Neighbor Machine Learning in the GIS Environment

被引:5
|
作者
Tamamadin, Mamad [1 ,2 ]
Lee, Changkye [3 ]
Kee, Seong-Hoon [1 ,3 ]
Yee, Jurng-Jae [1 ,3 ]
机构
[1] Dong A Univ, Dept ICT Integrated Ocean Smart Cities Engn, Busan 49315, South Korea
[2] Inst Teknol Bandung, Dept Meteorol, Bandung 40132, Indonesia
[3] Dong A Univ, Univ Core Res Ctr Disaster free Safe Ocean City C, Busan 49315, South Korea
基金
新加坡国家研究基金会;
关键词
k-Nearest Neighbor; GIS processing; machine learning; similarity; typhoon track prediction;
D O I
10.3390/rs14215292
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
This paper presents a novel approach for typhoon track prediction that potentially impacts a region using ensemble k-Nearest Neighbor (k-NN) in a GIS environment. In this work, the past typhoon tracks are zonally split into left and right classes by the current typhoon track and then grouped as an ensemble member containing three (left-center-right) typhoons. The proximity of the current typhoon to the left and/or right class is determined by using a supervised classification k-NN algorithm. The track dataset created from the current and similar class typhoons is trained by using the supervised regression k-NN to predict current typhoon tracks. The ensemble averaging is performed for all typhoon track groups to obtain the final track prediction. It is found that the number of ensemble members does not necessarily affect the accuracy; the determination of similarity at the beginning, however, plays an important key role. A series of tests yields that the present method is able to produce a typhoon track prediction with a fast simulation time, high accuracy, and long duration.
引用
收藏
页数:22
相关论文
共 50 条
  • [1] Student Performance Prediction Using Support Vector Machine and K-Nearest Neighbor
    Al-Shehri, Huda
    Al-Qarni, Amani
    Al-Saati, Leena
    Batoaq, Arwa
    Badukhen, Haifa
    Alrashed, Saleh
    Alhiyafi, Jamal
    Olatunji, Sunday O.
    2017 IEEE 30TH CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING (CCECE), 2017,
  • [2] A novel ensemble method for k-nearest neighbor
    Zhang, Youqiang
    Cao, Guo
    Wang, Bisheng
    Li, Xuesong
    PATTERN RECOGNITION, 2019, 85 : 13 - 25
  • [3] Human Activity Recognition Using K-Nearest Neighbor Machine Learning Algorithm
    Mohsen, Saeed
    Elkaseer, Ahmed
    Scholz, Steffen G.
    SUSTAINABLE DESIGN AND MANUFACTURING, KES-SDM 2021, 2022, 262 : 304 - 313
  • [4] Breast Cancer Detection using K-nearest Neighbor Machine Learning Algorithm
    Al-hadidi, Mohd Rasoul
    Alarabeyyat, Abdulsalam
    Alhanahnah, Mohannad
    2016 9TH INTERNATIONAL CONFERENCE ON DEVELOPMENTS IN ESYSTEMS ENGINEERING (DESE 2016), 2016, : 35 - 39
  • [5] Hybridisation of evolutionary programming and machine learning with k-nearest neighbor estimation
    He, Jingsong
    Yang, Zhenyu
    Yao, Xin
    2007 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1-10, PROCEEDINGS, 2007, : 1693 - 1700
  • [6] Using k-Nearest Neighbor and Speaker Ranking for Phoneme Prediction
    Rizwan, Muhammad
    Anderson, David V.
    2014 13TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA), 2014, : 383 - 387
  • [7] Manifold learning using Euclidean k-nearest neighbor graphs
    Costa, JA
    Hero, AO
    2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL III, PROCEEDINGS: IMAGE AND MULTIDIMENSIONAL SIGNAL PROCESSING SPECIAL SESSIONS, 2004, : 988 - 991
  • [8] Solar Power Generation Prediction by using k-Nearest Neighbor Method
    Ramli, Nor Azuana
    Hamid, Mohd Fairuz Abdul
    Azhan, Nurul Hanis
    Ishak, Muhammad Alif As-siddiq
    5TH INTERNATIONAL CONFERENCE ON GREEN DESIGN AND MANUFACTURE 2019 (ICONGDM 2019), 2019, 2129
  • [9] Prediction of cavitation damage on spillway using K-nearest neighbor modeling
    Kermani, E. Fadaei
    Barani, G. A.
    Ghaeini-Hessaroeyeh, M.
    WATER SCIENCE AND TECHNOLOGY, 2015, 71 (03) : 347 - 352
  • [10] Heart Disease Prediction Using Weighted K-Nearest Neighbor Algorithm
    Khalidou Abdoulaye Barry
    Youness Manzali
    Mohamed Lamrini
    Flouchi Rachid
    Mohamed Elfar
    Operations Research Forum, 5 (3)