Geothermal productivity prediction method and system based on long and short term memory neural network

The invention relates to a geothermal energy productivity prediction method and system based on a long and short term memory neural network. The method comprises the following steps: acquiring a historical data set of a to-be-predicted geothermal system, wherein the historical data set comprises a water injection rate, a water sampling rate, a well spacing, a reservoir temperature, a reservoir permeability and a reservoir heat conductivity coefficient; and inputting the historical data set of the to-be-predicted geothermal system into a geothermal productivity prediction model to obtain a predicted value of productivity, wherein the productivity comprises production temperature and output thermal power. The prediction precision of the production temperature and the output thermal power of the geothermal system is improved. 本发明涉及一种基于长短时记忆神经网络的地热产能预测方法及系统。所述方法包括：获取待预测地热系统的历史数据集；所述历史数据集包括注水速率、采水速率、井间距、储层温度、储层渗透率和储层导热系数；将所述待预测地热系统的历史数据集输入地热产能预测模型得到产能的预测值，所述产能包括生产温度和输出热功率。本发明提高了地热系统生产温度及输出热功率的预测精度。