Ise Takeshi, Oba Yurika
Field Science Education and Research Center (FSERC), Kyoto University, Kyoto, Japan.
Japan Science and Technology Agency (JST), Kawaguchi, Japan.
Front Robot AI. 2019 Apr 26;6:32. doi: 10.3389/frobt.2019.00032. eCollection 2019.
Climate change is undoubtedly one of the biggest problems in the 21st century. Currently, however, most research efforts on climate forecasting are based on mechanistic, bottom-up approaches such as physics-based general circulation models and earth system models. In this study, we explore the performance of a phenomenological, top-down model constructed using a neural network and big data of global mean monthly temperature. By generating graphical images using the monthly temperature data of 30 years, the neural network system successfully predicts the rise and fall of temperatures for the next 10 years. Using LeNet for the convolutional neural network, the accuracy of the best global model is found to be 97.0%; we found that if more training images are used, a higher accuracy can be attained. We also found that the color scheme of the graphical images affects the performance of the model. Moreover, the prediction accuracy differs among climatic zones and temporal ranges. This study illustrated that the performance of the top-down approach is notably high in comparison to the conventional bottom-up approach for decadal-scale forecasting. We suggest using artificial intelligence-based forecasting methods along with conventional physics-based models because these two approaches can work together in a complementary manner.
气候变化无疑是21世纪最大的问题之一。然而，目前大多数气候预测研究工作都是基于机械的、自下而上的方法，如基于物理的通用环流模型和地球系统模型。在本研究中，我们探索了一种使用神经网络和全球月平均温度大数据构建的唯象的、自上而下的模型的性能。通过使用30年的月温度数据生成图形图像，神经网络系统成功预测了未来10年温度的上升和下降。对于卷积神经网络使用LeNet，发现最佳全球模型的准确率为97.0%；我们发现，如果使用更多的训练图像，可以获得更高的准确率。我们还发现图形图像的配色方案会影响模型的性能。此外，不同气候带和时间范围的预测准确率也有所不同。本研究表明，与传统的自下而上方法相比，自上而下方法在年代际尺度预测方面的性能显著较高。我们建议将基于人工智能的预测方法与传统的基于物理的模型结合使用，因为这两种方法可以互补。
