Prediksi Intensitas Hujan Kota Surabaya dengan Matlab menggunakan Teknik Random Forest dan CART (Studi Kasus Kota Surabaya)

Maulana Dhawangkhara, Edwin Riksakomara
Submission Date: 2017-01-13 15:09:22
Accepted Date: 2017-03-17 10:12:41

Abstract


Keakuratan prediksi potensi curah hujan di Kota Surabaya dibutuhkan untuk antisipasi bencana akibat hujan seperti banjir bandang, membantu memprediksi kondisi penerbangan dan membantu majaemen saluran sanitasi di Surabaya. Prediksi dilakukan dengan data hari sebelumnya menggunakan perbandingan teknik Classification and Regression Trees (CART) dan Random Forest (RF)  pada data cuaca selama 17 tahun (2000-2016) berasal dari stasiun cuaca Juanda, Surabaya melalui website NCDC (National Climate Data Center) yang terdiri dari data suhu udara, titik embun, keepatan angin, tekanan udara, visibilitas dan curah hujan. Evaluasi pembuatan model dengan pengukuran akurasi, precision dan recall menunjukkan bahwa baik metode CART maupun Random Forest mampu mengklasifikasi dengan akurasi baik sebesar 78% untuk 4 dari 5 kelas intensitas hujan, dengan kelas terakhir belum mampu diklasifikasi oleh kedua metode. Metode Random forest memiliki nilai performa sedikit lebih baik dibandingkan dengan CART sebesar 6%. Eksperimen tuning parameter untuk kedua metode membuktikan performa lebih baik dibandingkan parameter default metode dan mampu memberikan kestabilan hasil performa dari segi uji coba proporsi data training dan testing. Variabel yang berpengaruh besar dalam model CART dan random forest dengan nilai uji performa yang baik antara lain adalah suhu udara, titik embun, suhu udara maksimum dan suhu udara minimum beserta variabel turunannya (selisih suhu udara maksimum dan minimum, selisih suhu udara dan titik embun dan kelembapan relatif). Penelitian  ini menghasilkan aplikasi pengklasifikasi intensitas hujan yang  memiliki akurasi baik atas kelas intesitas hujan (tidak hujan, ringan, sedang, deras, sangat deras).

Keywords


CART; Random Forest; RF; Matlab; Klasifikasi; Curah Hujan; Intensitas Hujan

References


& Shereef K Bab`oo S., "Applicability of Data Mining Techniques for Climate Prediction – A SurveyApproach," International Journal of Computer Science and Information Security, vol. 8, April 2010.

Klimatologi dan Geofisika Badan Meteorologi. (2016, September) [Online]. http://meteo.bmkg.go.id/prakiraan/mingguan

Donald B. Rubin, "Inference and missing data," Oxford Hournal Biometrika, 1975.

Silke Janitza, Jochen Kr uppa, Inke R. König Anne-Laure Boulesteix, "Over view of Random Forest Methodology and Practical Guidance with Emphasis on Computational Biology and Bioinformatics," Technical Report Number 129, Department of Statistics, University of Munich, 2012.

Mathworks. (2016) Mathworks Fitctree. [Online]. http://www.mathworks.com/help/stats/fitctree.html

Mathworks. (2016) Mathworks Treebagger. [Online]. http://www.mathworks.com/help/stats/treebagger.html

Friedman JH, Olshen RA, Stone CJ Breiman L, Classification and Regression Trees. New York: Chapman & Hall, 1993.

Wu W., Huang Y Zhang Z., "Mining dynamic interdimension association rules for local-scale weather prediction," In the Proceedings of the 28th Annual International Computer oftware and Applications Conference, 2004.

Kementrian Perhubungan RI, "Peraturan Menteri Perhubungan Republik Indonesia no 9 tahun 2015 tentang Peraturan Keselamatan Penerbangan Sipil Bagian 174 Tentanf Pelayanan Informasi Meteorologi Penerbangan (Aeronautical Meteorogocal Information Services," Peraturan Menteri Perhubungan Republik Indonesia no 9 tahun 2015 tentang Peraturan Keselamatan Penerbangan Sipil Bagian 174 (ivil Aviation Safety Regulations Part 174) Tentanf, 2015.

Tuan Zea Tan, "Rainfall intensity prediction by a spatial-temporal ensemble," 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence, 2008.

T R Prajwala, "A Comparative Study on Decision Tree and Random Forest Using R Tool," vol. 4, no. 1, 2015.

C. D. Sutton, "Classification and Regression Trees, Bagging, and Boosting," Handbook of Statistics, 2005.

D. A. Ahijevych, C. J. Kessinger, T. R. Saxen, M. Steiner and S. Dettling John K. Williams, "A Machine Learning Approach to Finding Weather Regimes and Skillful Predictor Combinations for Short-term Storm Forecasting," National Center for Atmospheric Research, 2008.

Elia Georgiana Petre, "A Decision Tree for Weather Prediction," Buletinul UniversităŃii Petrol – Gaze din Ploieşti, 2009.

Institute Indian Agricultural Statistics Research, Data Preprocessing Techniques for Data Mining.: Institute Indian Agricultural Statistics Research, 2007.

Satoshi Usami, Ross Jacobucci, and John J. McArdle Timothy Hayes, "Using Classification and Regression Trees (CART) and Random Forests to Analyze Attrition: Results From Two Simulations," Psychol Aging, 2015.

R. Kahavi, and M. Sahami J. Dougherty, "Supervised and unsupervised discretization of continuous features," In Machine Learning: Proceedings of the Twelth International Conference, 1995.

Amir Ahmad, "Data Transformation For Decision Tree Ensembles," Thesis for Degree of Doctor of Phylosophy University Of Manchester, 2009.

Michael J.A dan Linoff, Gordon S Berry, Data Mining Techniques For Marketing, Sales, Customer Relationship Management Second Editon. United States of America: Wiley Publishing, Inc , 2004.

Sneha Soni, "Implementation of Multivariate Data Set By Cart Algorithm," International Journal of Information Technology and Knowledge Management, 2010.

Friedman JH, Olshen RA, Stone CJ Brieman L, Classification and Regression Trees. New York: Chapman & Hall, 1984.

Mohammed Zakariah, "Classification of genome data using Random Forest Algorithm: Review," Interational Journal Computer Technology and Application (IJCTA), 2014.

E. C. Polley, and F. B. S. Briggs. B. A. Goldstein, "Random forests for genetic association studies," Statistical Applications in Genetics and Molecular Biology, 2011.

L. C. Thomas, "A survey of credit and behavioural scoring: forecasting financial risk of lending to consumers.," International Journal of Forecasting, vol. 16(2), 2000.

O. A., and R. E. Eskridge Alduchov, "Improved Magnus' form approximation of saturation vapor pressure," J. Appl. Meteor, pp. 601-609, 1996.


Full Text: PDF

CC Licencing


Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).

Refbacks

  • There are currently no refbacks.


Lembaga Penjaminan Mutu, Pengelolaan dan Perlindungan Kekayaan Intelektual (LPMP2KI) ITS
Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.