Burn Area Processing to Generate False Alarm Data for Hotspot Prediction Models

Imas S Sitanggang, Razali Yaakob, Norwati Mustapha, Ainuddin A. N

Abstract


Developing hotspot prediction models using decision tree algorithms require target classes to which objects in a dataset are classified.  In modeling hotspots occurrence, target classes are the true class representing hotspots occurrence and the false class indicating non hotspots occurrence.  This paper presents the results of satellite image processing in order to determine the radius of a hotspot such that random points are generated outside a hotspot buffer as false alarm data.  Clustering and majority filtering were performed on the Landsat TM image to extract burn scars in the study area i.e. Rokan Hilir, Riau Province Indonesia.  Calculation on burn areas and FIRMS MODIS fire/hotspots in 2006 results the radius of a hotspot 0.90737 km.  Therefore, non-hotspots were randomly generated in areas that are located 0.90737 km away from a hotspot. Three decision tree algorithms i.e. ID3, C4.5 and extended spatial ID3 have been applied on a dataset containing 235 objects that have the true class and 326 objects that have the false class. The results are decision trees for modeling hotspots occurrence which have the accuracy of 49.02% for the ID3 decision tree, 65.24% for the C4.5 decision tree, and 71.66% for the extended spatial ID3 decision tree.

Keywords


hotspot;satellite image processing;data mining;decision tree

Full Text:

PDF

References


Tay, S. C., Hsu, W., Lim, K. H. & Yap, L. C. “Spatial data mining: clustering of hot spots and pattern recognition.” Paper presented at the IEEE International Geoscience and Remote Sensing Symposium (IGARSS'03), Toulouse, July 21-25, 2003.

Yu, L. & Bian, F. “An Incremental Data Mining Method for Spatial Association Rule in GIS Based Fireproof System.” Paper presented at the International Conference on Wireless Communications, Networking and Mobile Computing, (WiCom 2007), Shanghai, China, September 21 – 25, 2007.

Prasad, K. S. N. & Ramakrishna, S. 2008. An Autonomous Forest Fire Detection System based on Spatial Data Mining and Fuzzy Logic. International Journal of Computer Science and Network Security 8 (12): 49-55.

Hu, L., Zhou, G. & Qiu, Y. “Application of Apriori Algorithm to the Data Mining of the Wildfire.” Paper presented at the 6th international conference on Fuzzy systems and knowledge discovery, Tianjin, China, August 14-16, 2009.

Angayarkkani, K. & Radhakrishnan. 2009. Efficient Forest Fire Detection System: A Spatial Data Mining and Image Processing Based Approach. International Journal of Computer Science and Network Security 9(3): 100- 107.

Stojanova, D., Panov, P., Kobler, A., Džeroski, S., & Taškova, K. “Learning to Predict Forest Fires with Different Data Mining Techniques.” Paper presented at the conference on Data Mining and Data Warehouses, Ljubljana, Slovenia, October 16, 2009.

Sitanggang, I.S. & Ismail, M.H. 2011. Classification model for hotspot occurrences using a decision tree method. Geomatics, Natural Hazards and Risk, 2(2): 111-121.

Sitanggang I.S, Yaakob R, Mustapha N, & Nuruddin A.N. 2012. Application of classification algorithms in data mining for hotspots occurrence prediction in Riau Province Indonesia. Journal of Theoretical and Applied Information Technology, 43(2): 214-221.

Sitanggang I.S, Yaakob R, Mustapha N, & Nuruddin A.N, “An extended ID3 decision tree algorithm for spatial data.” Paper presented at the IEEE International Conference on Spatial Data Mining and Geographical Knowledge Services (ICSDM), Fuzhou, China, June 29 -July 1, 2011.

Rokan Hilir District. “Overview of District.” last modified 2009. Accessed May 30, 2012. http://www.rohilkab.go.id/?tampil=linkandact=profilandid=4.

Wahyunto, Ritung S., Suparto, & Subagjo H. Peatland distribution and its carbon content in Sumatera and Kalimantan. Project of Climate Change, Forests and Peatlands in Indonesia. Bogor: Wetlands International – Indonesia Programme and Wildlife Habitat Canada, 2005.

Gomarasca, M. Basics of Geomatics. New York: Springer, 2009.

KIM, K. E. 1996. Adaptive Majority Filtering for Contextual Classification of Remote Sensing Data. International Journal of Remote Sensing 17(1996): 1083–1087.

Canty, Morton J. Image Analysis, Classification, and Change Detection in Remote Sensing: with Algorithms for ENVI/IDL, 237-238. Boca Raton: CRC Press, 2010.

ILWIS 3.4 Open. “ILWIS (3.4) Help.” last modified 2008. Accessed July 13, 2011, http://spatial-analyst.net/ILWIS/help.html.

Marsland, S. Machine Learning: An Algorithmic Perspective. Chapman & Hall/CRC machine learning & pattern recognition series. Boca Raton: CRC Press, 2009.

Han, J. & Kamber, M. Data Mining: Concepts and Techniques. Second edition, The Morgan Kaufmann series in data management systems. San Francisco: Morgan Kaufmann, 2006.

Tansey, K., Beston, J., Hoscilo, A., Page, S. E., & Paredes Hernández, C. U. 2008. Relationship Between Modis Fire Hot Spot Count and Burned Area in a Degraded Tropical Peat Swamp Forest in Central Kalimantan, Indonesia. Journal of Geophysical Research, 113 (D23): 1–8.

Quinlan, J. R. 1986. Induction of decision trees. Machine Learning 1(1): 81–106.

Rinzivillo, S. & Franco, T. “Classification in Geographical Information Systems,” Paper presented at the 8th European Conference on Principles and Practice of Knowledge Discovery in Databases, Pisa, Italy, September 20-24, 2004.




DOI: http://doi.org/10.12928/telkomnika.v13i3.1543

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

TELKOMNIKA Telecommunication, Computing, Electronics and Control
ISSN: 1693-6930, e-ISSN: 2302-9293
Universitas Ahmad Dahlan, 4th Campus
Jl. Ringroad Selatan, Kragilan, Tamanan, Banguntapan, Bantul, Yogyakarta, Indonesia 55191
Phone: +62 (274) 563515, 511830, 379418, 371120
Fax: +62 274 564604

View TELKOMNIKA Stats