Details

Autor(en) / Beteiligte

• Li Jing
• Xiong Feng
• Li Jintuo
• Ma Rui
• Liu Weiliang
• Lin Yongjun

Titel

Contrastive research of SVM and BP neural network in AOD prediction

Ist Teil von

• 2017 36th Chinese Control Conference (CCC), 2017, p.4072-4076

Ort / Verlag

Technical Committee on Control Theory, CAA

Erscheinungsjahr

2017

Link zum Volltext

• IEEE_Xplore

Quelle

IEEE Xplore

Beschreibungen/Notizen

• Atmospheric aerosol is one of the most important factors that cause the random variation of solar radiation intensity. In view of the problem that the atmospheric aerosol optical depth (AOD) is difficult to obtain real-timely and conveniently with high accuracy, estimation model of AOD using PM concentration is proposed in this paper. Two kinds of modeling methods BP neural network and support vector machine are adopted respectively to establish the estimation model, and contrast of their prediction result is performed. Experiment result indicate that both support vector machine(SVM) and BP neural network have strong nonlinear fitting ability and easy to realize; BP neural network model needs shorter computation time than SVM model, while the SVM model is more accurate than BP neural network model.