2006, Volume 8, Issue 2
Strategic Study of CAE >> 2006, Volume 8, Issue 2
ANN Analysis of Multi-correlation Between Forest Fire Risk and Weather Parameters
1. State Key Laboratory of Fire Science , University of Science and Technology of China , Hefei 230026 , China
2. National Research Institute of Fire and Disaster , Tokyo , Japan
Next Previous
Abstract
Calculation of forest fire probability is a complex issue concerning weather, tree species, geography conditions and human activities. The impact of weather parameters on fire has been one of the hot spots in the forest fire study. In this paper, the effect of 5 daily weather parameters on forest fire probability is investigtated. The 5 parameters are average humidity, precipitation, average wind speed, average temperature and sunshine time. Firstly, the correlation between each single parameter and fire probability is analyzed with a 24ayer BP neural network. The little value of MSE indicates ANN method gets close results with actual correlation. Secondly, the multi-correlaiton between fire probability and the 5 weather parameters is studied with a 3-layer BP network. From the 466 samples, 26 ones are randomly selected as test set, others as training set. The training MSE of BP network becomes smaller than 10-6 after 5 000 epochs. For the test set, the relative error is less than 9.9%. It is indicated from the results that there are steady correlaiton between fire probability and weather parameters, and the BP network is a practical method in fire risk analysis. The study has practical implicaitons for forest fire risk prediction and the results can act as a basic data in forest fire proteciton.
Keywords
neural network ; forest fire ; fire probability ; weather ; fire risk
Figures
图 1
图 2
图 3
图 4
References
[ 1 ] DeemingJE, Burgan RE, Cohen JE. The National Fire Danger Rating System-1978[A]. General Technical Report[R]. Intermountain Forest and Range Experiment Station,1977, INTT-39, USDA/FS
[ 2 ] Lee BS, Alexander ME, et al. Information systems in support of wildland fire management decision making in Canada[J]. Computers and Electronics in Agriculture,2002,37:185~198 link1
[ 3 ] Bradstock RA, Gill A M, et al. Bushfire risk at the urban interface estimated from historical weather records: consequences for the use of prescribed fire in the Sydney region of south-eastem Australia[J]. Joumal of Environmental Management,1998,52:259~271 link1
[ 4 ] Cruz MG, Alexander ME, Wakimoto R H. Assessing the probability of crown fire initiation based on fire danger indices[J]. Forestry Chronicle,2003,79:976~983 link1
[ 5 ] Castro FX, Tudela A, Sebastia M T. Modeling moisture content in shrubs to predict fire risk in Catalonia(Spain)[J]. Agricultural And Forest Meteorology,2003,116:49~59 link1
[ 6 ] Viegas DX, Pinoi J, et al. Estimating live fine fuels moisture content using meteorologically-based indices[J].Intemational Joumal of Wildland Fire.2001,(10):223-240 link1
[ 7 ] Flannigan M, Campbell I et al. Future fire in Canada´s boreal forest: paleoecology results and general circulation model-regional climate model simulations[J]. Canadian Joumal of Forest Research,2001,31:854~864 link1
[ 8 ] Wilams AA J, Karoly DJ, Tapper N. The sensitivity ofAustralian fire danger to climate change[J]. Climatic Change,2001,49:171~191 link1
[ 9 ] Williams AAJ, Karoly DJ. Extreme fire weather in Australia and the impact of the El Nino Southem Oscillation[J]. Australian Meteorological Magazine,1999,48:15~22
[10] Hoffmann WA, Schroeder W, Jackson R B. Regional feedbacks among fire, climate, and tropical deforestation[J]. Joumal of Geophysical Research-Atmospheres.2003,108(D23): Art. No.4721 link1
[11] Hoffmann WA, Schroeder W, Jackson R B. Positivefeedbacks of fire, climate, and vegetation and the conversion of tropical savanna[J]. Geophysical Research Letters,2002,29(22): Art. No.2052 link1
[12] Nepstad D, Lefebvre P, et al. Amazon drought and its implications for forest flammability and tree growth:a basin-wide analysis[J]. Global Change Biology,2004,10(5):704~717 link1
[13] Finney, MA. FARSITE: Fire Area Simulator-Model Development and Evaluation [R]. Rocky Mountain Research Station,1998, USDA/FS
[14] Satoh K, Kitamura S, KomurasakiS, et al.A system topredict occurrence and development of forest fires,-computer simulation of forest fires based on weather data(in Japanese)[A]. TED Conference 2002-JSME[C].Okinawa Japan,2002.457~458
[15] Song W G, Satoh K. Distribution analysis of forest fire related data in Japan[J]. Progress in Natural Science(in publish,2004)
[16] Satoh K, Kitamura S, Kuwahara K, et al. An analysis to predict forest fire danger and fire spread study to develop a fire danger rating and fire spread[A]. ASME Summer Heat Transfer Conference[C]. Las Vegas,2003.HT2003-47357.1～8
[17] Satoh K, Yang KT. An intelligent system to predict forest fire danger and fire spread[A], APSS 2003 Asia Pacifie Symposium on Safety[C]. Taipei,2003.287~290
[18] Satoh K, Song WG, YangK T.A study of forest fire danger prediction system in Japan[A].Intermational Conference of Database and Expert Systems Applications（DEXA04）[C].Zaragoza，Spain，2004
[19] HaykinS，神经网络原理[M].第二版.叶世伟，等译.北京：机械工业出版社，2004
[20] Armue B C，Ollero A，et al.Intelligent system for false alarm reduction in infrared forest-fire detection[J].IEEE Intelligent Systems and Their Applications.2000，15：64
[21] Femandes A M，Utkin A B，et al.Development of neural network committee machines for automatic forest firedetection using lidar[J].Paterm Recognition，2004，37：2039~2047
[22] Rose-Pehrsson S L，Shaffer R E，et al.Multi-criteria fire detection systems using a probabilistic neural network[J].Sensors and Actuators，2000，69：325~335 link1
[23] Derbel F.Performance improvement of fire detectors by means of gas sensors and neural networks[J].Fire Safety Jourmal，2004，39：383~398
[24] 范春年，等.用神经网络方法进行气象温度预测[J].计算机应用与软件，2004，21（3）：108~110 link1
[25] 赵博，等.基于神经网络的室内热舒适评判模型[J].哈尔滨工业大学学报，2003，35（12）：1436~1438 link1
京公网安备 11010502051620号
