{"title":"小尺度地理区域-区域远程气象参数模式识别的人工神经网络模型研究","authors":"S. Karmakar, M. Kowar, P. Guhathakurta","doi":"10.1109/ICIINFS.2008.4798370","DOIUrl":null,"url":null,"abstract":"Attempt to recognize pattern of meteorological parameters over the smaller scale geographical region (district) artificial neural network models have been developed. 54 years data for 1951-2004 have been used, of which the first 41 years (1951-1991) of data are used for training the network and data for the period 1991-2004 are used independently for validation. We have found that the mean absolute deviation (% of mean) between actual and predicted values of the each model is less than and half of the standard deviation (% of mean) in the independent period (1991-2004). The performances of these models in pattern recognition and prediction have been found to be extremely good. The models are developed and their evaluations have been presented in this paper.","PeriodicalId":429889,"journal":{"name":"2008 IEEE Region 10 and the Third international Conference on Industrial and Information Systems","volume":"48 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":"{\"title\":\"Development of Artificial Neural Network Models for Long-Range Meteorological Parameters Pattern Recognition over the Smaller Scale Geographical Region-District\",\"authors\":\"S. Karmakar, M. Kowar, P. Guhathakurta\",\"doi\":\"10.1109/ICIINFS.2008.4798370\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Attempt to recognize pattern of meteorological parameters over the smaller scale geographical region (district) artificial neural network models have been developed. 54 years data for 1951-2004 have been used, of which the first 41 years (1951-1991) of data are used for training the network and data for the period 1991-2004 are used independently for validation. We have found that the mean absolute deviation (% of mean) between actual and predicted values of the each model is less than and half of the standard deviation (% of mean) in the independent period (1991-2004). The performances of these models in pattern recognition and prediction have been found to be extremely good. The models are developed and their evaluations have been presented in this paper.\",\"PeriodicalId\":429889,\"journal\":{\"name\":\"2008 IEEE Region 10 and the Third international Conference on Industrial and Information Systems\",\"volume\":\"48 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2008-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"9\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2008 IEEE Region 10 and the Third international Conference on Industrial and Information Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICIINFS.2008.4798370\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2008 IEEE Region 10 and the Third international Conference on Industrial and Information Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICIINFS.2008.4798370","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Development of Artificial Neural Network Models for Long-Range Meteorological Parameters Pattern Recognition over the Smaller Scale Geographical Region-District
Attempt to recognize pattern of meteorological parameters over the smaller scale geographical region (district) artificial neural network models have been developed. 54 years data for 1951-2004 have been used, of which the first 41 years (1951-1991) of data are used for training the network and data for the period 1991-2004 are used independently for validation. We have found that the mean absolute deviation (% of mean) between actual and predicted values of the each model is less than and half of the standard deviation (% of mean) in the independent period (1991-2004). The performances of these models in pattern recognition and prediction have been found to be extremely good. The models are developed and their evaluations have been presented in this paper.