Technical note: Deep learning for creating surrogate models of precipitation in Earth system models
Technical note: Deep learning for creating surrogate models of precipitation in Earth system models
复制标题
DOI：
10.5194/acp-20-2303-2020
复制
发表时间：
2019-04
影响因子：
6.3
通讯作者：
Theodore Weber;Austin Corotan;Brian Hutchinson;B. Kravitz;R. Link
中科院分区：
文献类型：
--
作者：
Theodore Weber;Austin Corotan;Brian Hutchinson;B. Kravitz;R. Link
抽象。我们研究了使用深度神经网络为短期气候预测生成替代模型的技术。卷积神经网络是在第二代加拿大地球系统模型（CanESM 2）模拟的1pctCO2运行（CO2浓度每年增加1%）的97年月降水量输出上训练的。神经网络明显优于持久性预测，即使预测长度延长到120个月，也没有显示出明显的性能下降。该模型是容易低估降水的特点是强降水事件的地区。定时采样（迫使模型逐渐使用自己过去的预测，而不是地面实况）对于避免放大早期预测误差至关重要。然而，使用预定采样也需要预先预测（在第一个预测日期之前生成预测），以获得前几个预测时间步长的足够性能。我们记录的训练过程和超参数优化过程的研究人员谁希望扩大使用神经网络开发代理模型。
Abstract. We investigate techniques for using deep neural networks to produce surrogate models for short-term climate forecasts. A convolutional neural network is trained on 97 years of monthly precipitation output from the 1pctCO2 run (the CO2 concentration increases by 1 % per year) simulated by the second-generation Canadian Earth System Model (CanESM2). The neural network clearly outperforms a persistence forecast and does not show substantially degraded performance even when the forecast length is extended to 120 months. The model is prone to underpredicting precipitation in areas characterized by intense precipitation events. Scheduled sampling (forcing the model to gradually use its own past predictions rather than ground truth) is essential for avoiding amplification of early forecasting errors. However, the use of scheduled sampling also necessitates preforecasting (generating forecasts prior to the first forecast date) to obtain adequate performance for the first few prediction time steps. We document the training procedures and hyperparameter optimization process for researchers who wish to extend the use of neural networks in developing surrogate models.