A generative adversarial network-based unified model integrating bias correction and downscaling for global SSTOA
本文提出了一种基于生成对抗网络的全球海表面温度(sea surface temperature,SST)偏差订正及降尺度整合模型.该模型的生成器使用偏差订正模块将数值模式预测结果进行校正,再用可复用的共享降尺度模块将订正后的数据分辨率逐次提高.该模型的判别器可鉴别偏差订正及降尺度结果的质量,以此为标准进行对抗训练。同时,在对抗损失函数中含有物理引导的动力学惩罚项以提高模型的性能.本研究基于分辨率为1°的GFDL SPEAR模式的SST预测结果,选择遥感系统(Remote Sensing System)的观测资料作为真值,面向月尺度ENSO与IOD事件以及天尺度海洋热浪事件开展了验证试验:模型在将分辨率提高到0.0625°×0.0625°的同时将预测误差减少约90.3%,突破了观测数据分辨率的限制,且与观测结果的结构相似性高达96.46%.
Shijin Yuan;Xin Feng;Bin Mu;Bo Qin;Xin Wang;Yuxuan Chen;
School of Software Engineering,Tongji University,Shanghai,China
海洋学
偏差订正降尺度海表面温度生成对抗网络物理引导的神经网络
《Atmospheric and Oceanic Science Letters》 2024 (001)
P.45-52 / 8
supported by the National Key Research and Development Program of China[grant number 2020YFA0608000];the National Natural Science Foundation of China[grant number 42075141];the Meteorological Joint Funds of the National Natural Science Foundation of China[grant number U2142211];the Key Project Fund of the Shanghai 2020“Science and Technology Innovation Action Plan”for Social Development[grant number 20dz1200702];the first batch of Model Interdisciplinary Joint Research Projects of Tongji University in 2021[grant number YB-21-202110].
评论