Performance Analysis Among Predictive Models of Lightning Occurrence Using Artificial Neural Networks and SMOTE
Keywords:
ann, Artificial Neural Network, forcasting lightning and smoteAbstract
Lightning represent a potential threat to various society activities, such as damage to telecommunication systems and the distribution of electric power, as well as injury or death of humans beings. Predicting the occurrence of lightning can help in making decisions about the actions that must be taken to minimize the risks of this natural phenomenon. In this study, data from air temperature profiles, dew point temperature and historical lightning data were used to obtain two predictive models of lightning occurrence. The models were obtained by using an artificial neural network. The first model was obtained through unbalanced data and the second one with data balanced with Synthetic Minority Over-sampling Technique (SMOTE). The model performance was tested in five different classes of lightning predictions: ABSENCE, LOW, MODERATE, VERY and SEVERE, considering five prediction periods: case 1 (one hour), case 2 (two hours), case 3 (three hours), case 4 (four hours) and case 5 (five hours). It was observed that the use of the Synthetic Minority Over-sampling Technique improved accuracy in the recognition of atmospheric patterns that lead to the incidence of lightning in the five classes used in the five prediction cases.
Downloads
References
. A. Uman, “Natural lightning",IEEE Transactions on Industry Appli-cations, vol. 30, no. 3, pp. 785-790, May/Jun, 1994.
E. R. Alves, “Previsão de raios utilizando técnicas de inteligênciacomputacional e dados de sondagem atmosférica por satélite", PhD.thesis, Programa de Pós-Graduação em Engenharia Elétrica, UniversidadeFederal do Pará, Belém, Pará, 2017.
E. R. Ferreira, Adônis, F. R. Leal, W. L. N. Matos, G. O. Almeida,R. Shinkai and M. N. G. Lopes, “Lightning deaths and injuries in the Brazilian Amazon region in the period of 2009-2019",in Proceedings ofthe International Symposium on Lightning Protection (XV SIPDA), SãoPaulo, Brazil, Sept-Oct, 2019, pp. 1-8.
M. Gijben, L. L. Dyson. and M. T. Loots, “A statistical scheme to forecast the daily lightning threat over southern Africa using the Unified Model", Atmospheric Research, vol. 194, pp. 78-88, Sept, 2017.
L. Y. Weng, J. B. Omar, Y. K. Siah, S. K. Ahmed, I. B. Z. Abidin andN. Abdullah, “Lightning forecasting using ANN-BP & radiosonde",inProceedings of the International Conference on Intelligent Computingand Cognitive Informatics, Kuala Lumpur, Malaysia, Sept, 2010, pp. 1-8.
G. Juntian, G. ShanQiang and F. Wanxing, “A lightning motion prediction technology based on spatial clustering method",in Proceedings of the7th Asia-Pacific International Conference on Lightning, Chengdu, China,Dec, pp. 1-6, 2011.
V. A. Rakov, M.A. Uman, M.I. Fernandez, C.T. Mata, K.J. Rambo, M.V.Stapleton and R.R. Sutil, “Direct lightning strikes to the lightning protec-tive system of a residential building: Triggered-lightning experiments", IEEE Transactions on Power Delivery, vol. 17, no. 2, pp. 575-586, Aug,2002.
Q. Zeng, Z. Wang, F. Guo, M. Feng, M. Feng, S. Zhou and H. Wang,“The application of lightning forecasting based on surface electrostatic field observations and radar data",Journal of Electrostatics, vol. 71, pp.6-13, Feb, 2013.
G. S. Zepka, O. Pinto Jr. and A. C. V. Saraiva, “Lightning forecasting in southeastern Brazil using the WRF model", Atmospheric Research, vol.135-136, pp. 344-362, Jan, 2014.
G. S. Zepka, A. C. V. Saraiva, O. Pinto Jr and V. L. G. Gardiman,“Lightning forecasting using WRF model over EDP distribution companies areas",in Proceedings of the International Symposium on LightningProtection (XII SIPDA), Belo Horizonte, Brazil, Oct, 2013, pp. 1-8.
D. Johari, T. K. A. Rahman and I. Musirin, “Artificial neural network based technique for lightning prediction",in Proceedings of the 5thStudent Conference on Research and Development, Selangor, Malaysia,Dec, 2007, pp. 1-8.
N. H. Abdullah , R. Adnan, A. M. Samad and F. A. Ruslan, “Lightning forecasting modelling using artificial neural network (ANN): Case study Sultan Abdul Aziz Shah airport or Skypark Subang",in Proceedings ofthe IEEE Conference on Systems, Process and Control (ICSPC), Melaka,Malaysia, Dec, 2018, pp. 1-8.
J. Lu, H. Zhang, L. Yang, B. Li, Z. Fang, X. Xu, “Forecast method oflightning activity based on the weather conditions", in Proceedings of the7th Asia-Pacific International Conference on Lightning, Chengdu, China,Nov, 2011, pp. 1-8
J. A. S. de Sá, B. R. P. da Rocha, A. C. Almeida and J. R. Souza, “Recurrent self-organizing map for severe weather patterns recognition", Recurrent Neural Networks and Soft Computing, vol. 17, pp. 151-175,Oct, 2012.
E. R. Alves, B. R. P. da Rocha, C. T. C. Júnior, M. N. G. Lopes and J.A. S. de Sá, “Lightning prediction using satellite atmospheric sounding data and feed-forward artificial neural network", Journal of Intelligent &Fuzzy Systems, vol. 33, pp. 79-92, Jun, 2017
A. A. El-Sayed, M. A. M. Mahmood, N. A. Meguid and H. A. Hefny,“Handling autism imbalanced data using synthetic minority over-sampling technique (SMOTE)",in Proceedings of the Third World Conference on Complex Systems (WCCS), Marrakech, Morocco, Nov, 2015, pp. 1-8.
K. U. Rani, G. N. Ramadevi and D. Lavanya, “Performance of synthetic minority oversampling technique on imbalanced breast cancer data",in Proceedings of the 3rd International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India, Mar,2019, pp. 29-39.
P. Tan, M. Steinbach and V. Kumar, Introduction to data mining, (FirstEdition), Pearson Education India, 2005.
M.T. Hagan and M.B. Menhaj, “Training feedforward networks with theM arquardt algorithm", IEEE Transactions on Neural Networks, vol. 5,no. 6, pp. 989-993, Nov, 1994
C. A. Morales, J. R. Neves, E. M. Anselmo, K. S. Camara, W. Barreto,V. Paiva and R. L. Holle, “8 years of sferics timing and rangingnetwork - STARNET: A lightning climatology over South America",inInternational Lightning Detection Conference / International LightningMeteorology Conference (ILDC/ILMC), Mar, 2014, pp. 1-8.
A. C. Almeida, B. R. P. Rocha, J. R. S. Souza, J. A. S. Sá and J. A. P.Filho, “Cloud-to-ground lightning observations over the eastern AmazonRegion",Atmospheric Research, vol. 117, pp. 86-90, Nov, 2012.
M. R. Prusty, T. Jayanthi and K. Velusamy, “Weighted-SMOTE: Amodification to SMOTE for event classification in sodium cooled fastre actors, Progress in Nuclear Energy, vol. 100, pp. 355-364, Sept, 2017.
Y. Ge, D. Yue and L. Chen., “Prediction of wind turbine blades icing based on MBK-SMOTE and random forest in imbalanced data set",in Proceedings of the TIEEE Conference on Energy Internet and EnergySystem Integration (EI2), Beijing, China, Nov, 2017, pp. 1-6.
N. V. Chawla, K. W. Bowyer and L. O. Hall, “Smote: synthetic minorityover-sampling technique",Journal of articial intelligence research, vol.16, pp. 321-357, Jun, 2002.
T. Fawcett, “An introduction to ROC analysis", Pattern recognition letters, vol. 27, no. 8, pp. 861-874, Jun, 2006
