基于BP神经网络和FEFLOW模型模拟预测多年冻土活动层温度

郭林茂, 常娟, 徐洪亮, 叶仁政

Simulation and prediction of permafrost active layer temperature based on BP neural network and FEFLOW model： take the Fenghuoshan area on the Tibetan Plateau as an example

Linmao GUO, Juan CHANG, Hongliang XU, Renzheng YE

表4 各深度地温的模拟效率参数

Table 4 Simulated efficiency parameters of soil temperature at different depths

土壤深度/cm 5 10 15 20 40 80 160 320 RMSE/℃ 1.76 1.77 1.73 1.78 1.24 1.03 0.88 0.09 MAE/℃ 1.41 1.43 1.40 1.43 0.93 0.86 0.69 0.07 NSE 0.95 0.94 0.94 0.93 0.96 0.95 0.86 0.98 R 0.98 0.98 0.98 0.98 0.98 0.99 0.94 0.99