论文标题
部分可观测时空混沌系统的无模型预测
Don't Waste Data: Transfer Learning to Leverage All Data for Machine-Learnt Climate Model Emulation
论文作者
论文摘要
在培训机器读取气候模型时，我们如何从所有可用数据中学习，而不会在模拟时产生任何额外的费用？通常，训练数据包括粗粒的高分辨率数据。但是，只有保留此粗粒数据意味着其余的高分辨率数据被抛出。我们使用转移学习方法，可以应用于一系列机器学习模型，以利用所有高分辨率数据。我们使用三个混沌系统来证明它可以稳定训练，可改善概括性能，并带来更好的预测技能。我们的代码位于https://github.com/raghul-parthipan/dont_waste_data
How can we learn from all available data when training machine-learnt climate models, without incurring any extra cost at simulation time? Typically, the training data comprises coarse-grained high-resolution data. But only keeping this coarse-grained data means the rest of the high-resolution data is thrown out. We use a transfer learning approach, which can be applied to a range of machine learning models, to leverage all the high-resolution data. We use three chaotic systems to show it stabilises training, gives improved generalisation performance and results in better forecasting skill. Our code is at https://github.com/raghul-parthipan/dont_waste_data
