Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/88054
標題: 應用倒傳遞類神經網路於PM10預測之研究
Application of Back-Propagation Neural Network on the Prediction of PM10
作者: Long-Ming Huang
Wei-Jhong Gu
黃隆明
古緯中
關鍵字: Back-propagation neural network;PM10;The optimum input variables;倒傳遞類神經網路;PM10;最佳輸入變數組合
Project: 水土保持學報, Volume 44, Issue 4, Page(s) 341-360.
摘要: 
This study used back-propagation neural network to predict the concentration of PM10. For improving the prediction, meteorological parameters and environmental monitoring parameters from the Siansi air quality station were taken as input variables, and also used meteorological parameters from Wuqi weather station to be supporting input variables. Before setting parameters in the model, the data should be normalized and screened, and the results of setting parameters which could obtain the best prediction throughtraining and testing were as follows: the number of hidden neurons and training times were 17 and 35,000 respectively, the learning rate was 0.9, and the momentum modified coefficient was 0.1. The next step was screening variables, and the results showed that the optimum input variables included PM10 of the previous day, humidity, wind velocity, wind direction, sunshine hours, surface radiation, rainfall, and atmospheric pressure. The sensitivity analysis showed that PM10 of the previous day was the main factor which affected the sensitivity of the model. The result of this study showed that after sieving variables, it could surely improve the correlation between predictions and actual observed values and the prediction of extreme values. Also, it didn’t affect the concentration of PM10 which trended lower in summer and higher in winter.

本研究以倒傳遞類神經網路進行 PM10 濃度之預測,為提升其預測力,除了以線西空氣品質監測站之氣象參數與環境監測參數作為輸入變數之外,並增加梧棲氣象站之氣象參數作為輔助之輸入變數;而在輸入倒傳遞類神經網路前,先進行正規化及數據篩選,而後經由訓練與測試,可獲得內部參數之設定值,當隱藏層單元數為 17 個、訓練次數為 35,000 次、學習速率為 0.9 與動量修正係數為 0.1 時,所得之預測值最佳。接著再進行變數之篩選,得到最佳輸入變數之組合為前一日 PM10、濕度、風速、風向、日照時數、全天空輻射、降雨量與氣壓等八項;又於敏感度分析中發現,影響模式敏感度之主要因子為前一日 PM10 值。研究結果顯示,輸入變數經由篩選後,不但可提升預測值與實際值之相關性,亦可提升對極端值之預測能力,且不影響 PM10 季節性夏低冬高之分佈趨勢。
URI: http://hdl.handle.net/11455/88054
Appears in Collections:第44卷 第04期

Files in This Item:
File Description SizeFormat
84619-2.pdf1.99 MBAdobe PDFView/Open
Show full item record
 

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.