1 Introduction Oil resources in tight reservoirs are widely distributed in China. Tight oil reservoirs have been discovered in Songliao Basin, Bohai Bay, Qaidam Basin, Tuha Basin, Sichuan Basin, etc. However, such oil reservoirs have poor physical properties. Conventional vertical wells are hard to bring about economic benefits, and the horizontal well multi-stage fracturing technology is often used to increase their productivity. It has become a necessary technical means of developing such oil reservoirs. The horizontal well design for a tight reservoir is the key to development success, while its productivity is the exact index for evaluating whether or not the horizontal well design is successful. Currently, an empirical formula is mainly used for horizontal well productivity prediction, which is mainly directed toward reservoirs with good physical properties and their oil and water seepages generally complying with Darcy's law. Thus, the productivity prediction features certain accuracy. For a tight sandstone reservoir reconstructed via fracturing, it macroscopically features low porosity, wide permeability variety, and complex porosity-permeability relation, and it microscopically features complex and variable pore structures and space types as well as incompliance of oil and water seepages with Darcy's law. So, conventional productivity models often fail to meet the required prediction accuracy requirement. In the past few years, the artificial neural network technology has emerged. Because it has the ability to infinitely approach any non-linear function or system, and is independent of any available model, it is very suitable for non-linear modeling. It can effectively improve the prediction accuracy of the fractured horizontal well productivity prediction. Traditionally, the neural network is used only to create the non-linear relations of post- fracturing horizontal well productivity and geological/ engineering factors, and the impact of horizontal well type on productivity prediction is omitted. Post-fracturing horizontal well productivity and geological/engineering factors, and the impact of horizontal well type on productivity prediction is omitted. So, the paper presents a neural network prediction method based on horizontal well classification, followed by a productivity prediction of fractured horizontal wells in the tight Fuyu Reservoir in the horizontal well development area in northern Honggang, Jilin Oilfield, with the purpose of improving the productivity prediction accuracy of fractured horizontal wells in tight oil reservoirs. 2 Neural Network Model Productivity Predicion In the study, the grey relational analysis method was firstly employed to sequence the parameters affecting the fractured horizontal well productivity in the tight Fuyu Reservoir in the horizontal well development area in northern Honggang, south Songliao Basin and identify main influencing parameters; then, a fuzzy cluster analysis of fractured horizontal wells in the study area was carried out so as to divide the fractured horizontal wells in the study area into four categories. Finally, the horizontal well classification results and influencing parameters were integrated into a BP neural network as its input, and on the basis of the daily production capacity data, a neural network model that could predict the post-fracturing horizontal well productivity was created, and the check data were used to verify the model. JI Tianliang, LU Shuangfang, TANG Mingming, WANG Min, WANG Wenguang, LIANG Hongru and MIN Chunjia, 2015. 1 Application of BP Neural Network Model in Fracturing Productivity Prediction of Fuyu Tight Oil Reservoir in Jilin Oilfield. Acta Geologica Sinica (English Edition), 89(supp.): 154-155. Application of BP Neural Network Model in Fracturing Productivity Prediction of Fuyu Tight Oil Reservoir in Jilin Oilfield JI Tianliang 1,* , LU Shuangfang 1 , TANG Mingming 1 , WANG Min 1 , WANG Wenguang 2 , LIANG Hongru 1 and MIN Chunjia 1 1 Research institute of Unconventional Oil and Gas and New Energy, China University of Petroleum, Qingdao, Shandong 266580, 2 Earth Science Institute, Northeast Petroleum University, Daqing, Jilin 163318 Vol. 89 Supp. * Corresponding author. E-mail: lushuangfang@qq.com 154 ACTA GEOLOGICA SINICA (English Edition) http://www.geojournals.cn/dzxben/ch/index.aspx http://mc.manuscriptcentral.com/ags June 2015