Atmospheric discharges offer great risks to the population and activities that involve different systems such as telecommunications, energy distribution and transportation. Lightning prediction can contribute to minimize the risks of this natural phenomenon. Therefore the present paper presents a model for lightning prediction based on satellite atmospheric sounding data, calibrated and validated with lightning data in an Amazon region particular area through an investigation that considered five period cases for validation of lightning prediction: case 1 (one hour), case 2 (two hours), case 3 (three hours), case 4 (four hours) and case 5 (five hours). The machine learning technique used to predict lightning was the Artificial Neural Network (ANN) trained with Levenberg-Marquardt backpropagation algorithm to classify modeling related to lightning prediction. This classification relied on the possibility of lightning prediction from the vertical profile of air temperature obtained from satellite NOAA-19. Results show that ANN was capable of identifying adequately the class to which a new event belongs to in relation to categories of occurrence and absence of lightning with better performance than traditional methodologies.
ManzatoA., Sounding-derived indices for neural network based short-term thunderstorm and rainfall forecast, Atmospheric Research83 (2007), 349–365.
2.
LeeA.C.L., An experimental study of the remote location of lightning flashes using a VLF arrival time difference technique, Quart, J R Met Soc112 (1986), 203–229.
3.
AliA.F., JohariD., IsmailN.F.N., MusirinI. and HashimN., Thunderstorm forecasting by using artificial neural network, Proceedings of 5th International Power Engineering and Optimization Conference, Shah Alam, Selangor, Malaysia, 2011, pp. 369–374.
4.
ShowalterA.K., A stability index for forecasting thunderstorms, Bull Amer Meteor Soc34 (1947), 250–252.
5.
ErkelA.R.V. and PattynamaP.M.T., Receiver operating characteristic (ROC) analysis: Basic principles and applications in radiology, European Journal of Radiology27(2) (1998), 88–94.
6.
LiuC. and HeckmanS., Using total lightning data in severe storm prediction: Global case study analysis from North America, Brazil and Australia, Proceedings of 11th International Symposium on Lightning Protection, Fortaleza, Brazil, 2011.
7.
MoralesC.A, NevesJ.R. and AnselmoE., Sferics Timing and Ranging Network-Starnet: Evaluation over South America, Proceedings of 11th International Symposium on Lightning Protection, Fortaleza, Brazil, 2011.
8.
FrankelD., SchillerI., DraperJ.S. and BarnesA.A., Use de neural network to prediction lightning at kennedy space center, Seattle International Joint Conference Neural Network1 (1991), 319–324.
9.
JohariD., RahmanT.K.A. and MusirinI., Artificial neural network technique for lightning prediction, Proceedings 5th Student Conference on Research and Development, Malaysia, 2007.
10.
MacgormanD.R. and RustW.D., The electrical nature of storms, New York: Oxford University Press1998, p. 422.
11.
LiD.-M., Identification of chaotic systems with large noise on regularized feedforward neural network, International Conference on Machine Learning and Cybernetics7 (2005), pp. 4060–4063.
12.
YuE.S., ChenC.Y.R., Traffic prediction using neural network, Global Telecommunications Conference, Including a Communications Theory Mini-Conference, Technical Program Conference a Record, IEEE in Houston2 (1993), pp. 991–995.
13.
ColbyF.P.Jr, Convective inhibition as a predictor of convection during AVE-SESAME II, Mon Wea Rev1984(112), 2239–2252.
14.
JuntianG., ShanQiangG. and WanxingF., A lightning motion prediction technology based on spatial clustering method, Proceedings 7th Asia-Pacific International Conference on Lightning, Chengdu, China, 2011.
15.
ZepkaG.S. and SaraivaA.C.V., Forecast using WRF model over EDP distribution companies areas, Proceedings of 12th International Symposium on Lightning Protection, Belo Horizonte, Brazil, 2013.
16.
ZepkaG.S., PintoO.Jr. and SaraivaA.C.V, Lightning forecasting in southeastern Brazil using the WRF model, Atmospheric Research135-136 (2014), 344–362.
17.
PintoI.R.C.A. and PintoO.Jr., Cloud-to-ground lightning distribution in Brazil, Journal of Atmospheric and Solar-Terrestrial Physics65 (2003), 733–737.
18.
LiJ., WolfW.W., MenzelW.P., ZhangW., HuangH.L. and AchtorH.T., Global sounding of the atmosphere from atovs measurements: The algorithm and validation, Journal of Applied Meteorology39 (2000), 1248–1268.
19.
LuJ., ZhangH., YangL., LiB., FangZ. and XuX., Forecast method of lightning activity based on the weather conditions, Proceedings of 7th Asia-Pacific International Conference on Lightning, Chengdu, China, 2011.
20.
WangJ., ZhouB. and ZhouS., Lightning potential forecast over Nanjing with denoised sounding-derived indices based on SSA and CS-BP, Atmospheric Research137 (1994), 245–256.
21.
SáJ.A.S., RochaB.R.P., AlmeidaA.C. and SouzaJ.R.S., Recurrent self-organizing map for severe weather patterns recognition, In Recurrent Neural Networks and Soft Computing, ISBN 979-953-307-546-3, 2011.
22.
GalwayJ.G., The lifted index as a predictor of latent instability, Bull Amer Meteor Soc (1956), 528–529.
23.
GeorgeJ.J., Weather Forecasting for Aeronautics, Academic Press, 1960, p. 673.
24.
WoodsK. and BowyerK.W., Generating ROC curves for artificial neural networks, IEEE Transactions on Medical Imaging16(3) (1997), pp. 329–337.
25.
PuL., DengJ., QianS., GuS. and CaoX., A new method to study on distribution characteristics of cloud-to-ground lightning, Proceedings International Conference on High Voltage Engineering and Application, Shanghai, China, 2012, pp. 17–20.
26.
WengL.Y., OmarJ.B., SiahY.K., AhmedS.K. and AbidinI.B.Z., Lightning forecast using ANN-BP e radiosonde, Proceedings International Conference on Intelligent Computing and Cognitive Informatics, Kuala Lumpur, Malaysia, 2010, pp. 152–155.
27.
Looy, et al., Prediction of dose escalation for rheumatoid arthritis patientes under infliximab treatment, Engineering Applications of Artificial Intelligence19 (2006), 819–828.
28.
UmanM.A., Natural lightning, IEEE Transactions on Industry Applications30(3) (1994), 785–790.
29.
FunM.H., HaganM.T., Levenberg-Marquardt training for modular networks, Proceedings of International Conference on Neural Network1 (1996), 468–473.
30.
AkyinyemiM.L., BoyoA.O., EmetereM.E., UsikaluM.R., OlawoleF.O., Lightning a fundamental of atmospheric electricity, Proceedings International Conference on Environment Systems Science and Engineering9 (2014), pp. 47–52.
31.
MoncrieffM.W., MillerM.J., The dynamics and simulation of tropical cumulonimbus and squall lines, Quart J Roy Meteor Soc1976 (102), 373–394.
32.
TanP.N., SteinbachM. and KumarV., Introduction to data mining, Boston: Addison-Wesley Longman: Boston, USA, 2005.
33.
ZengQ., WangZ., GuoF., FengM., ZouS., WangH. and XuD., The application of lightning forecasting based on surface electrostatic field observations and radar data, Atmospheric Research71 (2013), 6–13.
34.
PippierR., A review of static stability indices and related thermodynamic parameters, Ilinois State Water Survey Climate and Metereology Section, USA, 1988, P. 94.
35.
MillerR.C., Notes on analysis and severe storm forecasting procedures of the Air Force GlobalWeather Central, Tech Rept 200(R), Headquarters, Air Weather Service, USAF, 1972, p. 190.
36.
HolleR.J., Some Aspects of Global Lightning Impacts, Proceedings International Conference on Lightning Protection (ICLP), Shanghai, China, 2014, pp. 1390–1395.
37.
HolleR.L., Annual rates of lightning fatalities by country, Preprints, International Lightning Detection Conference, Tucson, Arizona, Vaisala, 2008, p. 14.
38.
FawcettT., An introduction to ROC analysis, Pattern Recognition Letters27(86) (2006), 861–874.
39.
MusaT.A., AmirS., OthmanR., SesS., OmarK., AbdullahK., LimS. and RizosC., GPS meteorology in a lowlatitude region: Remote sensing of atmospheric water vapor over the Malaysian Peninsula, Journal Atmosp Solar-Terrest Phys73 (2011), 2410–2422.
40.
CoorayV., CoorayC. and AndrewsC., Lightning caused injuries in humans, Journal of Electrostatics65(5-6) (2007), 386–394.
41.
RakovV.A. and, UmanM.A., Lightning: Physics and Effects, New York: Cambridge Universty Press, 2003.
42.
RakovV.A., UmanM.A., FernandezM.I., MataC.T., RamboK.J., StapletonM.V. and SutilR.R, Direct lightning strikes to the lightning protective system of a residential building: Triggered-lightning experiments, IEEE Transaction on Power Delivery17(2) (2002), 575–586.
43.
ZhangW., LiangJ., WangJ., CheJ., Chaotic time series forecasting based on fuzzy adaptive PSO for feedforward neural network training, The 9th International Conference for Young Computer Scientists (2008), pp. 3022–3027.
