Browse > Article

Development of a Gangwon Province Forest Fire Prediction Model using Machine Learning and Sampling  

Chae, Kyoung-jae (인하대학교 통계학과)
Lee, Yu-Ri (인하대학교 통계학과)
cho, yong-ju (인하대학교 통계학과)
Park, Ji-Hyun (인하대학교 통계학과)
Publication Information
The Journal of Bigdata / v.3, no.2, 2018 , pp. 71-78 More about this Journal
Abstract
The study is based on machine learning techniques to increase the accuracy of the forest fire predictive model. It used 14 years of data from 2003 to 2016 in Gang-won-do where forest fire were the most frequent. To reduce weather data errors, Gang-won-do was divided into nine areas and weather data from each region was used. However, dividing the forest fire forecast model into nine zones would make a large difference between the date of occurrence and the date of not occurring. Imbalance issues can degrade model performance. To address this, several sampling methods were applied. To increase the accuracy of the model, five indices in the Canadian Frost Fire Weather Index (FWI) were used as derived variable. The modeling method used statistical methods for logistic regression and machine learning methods for random forest and xgboost. The selection criteria for each zone's final model were set in consideration of accuracy, sensitivity and specificity, and the prediction of the nine zones resulted in 80 of the 104 fires that occurred, and 7426 of the 9758 non-fires. Overall accuracy was 76.1%.
Keywords
Forest fire Weather Index(FWI); Machine learning model; sampling; imbalanced data;
Citations & Related Records
연도 인용수 순위
  • Reference
1 박흥석, 이시영, 채희문, 이우균 (2009) 현캐나다 산불 기상지수를 이용한 산불 발생 확률모형 개발, 한국방재학회논문집, 제9권, 제3, pp. 95-100.
2 이병두, 유계선, 김선용, 김경하 (2012) 로지스틱 회귀모형을 이용한 산불발생확률모형 개발, 한국임학회지, Vol. 101, No. 1, pp. 1-6.
3 Amiro, B.D., Logan, K.A., Wotton, B.M., Flaniga n, M.D., Todd, J.B., Stocks, B.J. and Martell, D.L. (2004) Fire Weather index system components for large fires in the Canadian boreal forest. Intern ational Journal of Wildland Fire, Vol 13, pp. 391-400.   DOI
4 Breiman, L. (2001) Random Forests. Machine Learning, Vol. 45, No. 1, pp. 5-32.   DOI
5 Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P.(2002). SMOTE: synth-etic minority over-sampling technique.
6 Freund, Y. and Schapire, R. (1996), Experim-ents with a new boosting algorithm, Machine Learning : Proceedings of the Thirteenth International Conference, San Francisco, USA, 148-156.
7 Gareth J, Daniela W, Trevor H, Robert T (2015), "An Introduction to Statistical Learning withAppli cations in R", Springer, NewYork.
8 XGBoost (2016) https://xgboost.readthedocs-.io/en/latest/