VARENN: graphical representation of periodic data and application to climate studies
VARENN: graphical representation of periodic data and application to climate studies
复制标题
DOI：
10.1038/s41612-020-0129-x
复制
发表时间：
2020-07
影响因子：
9
通讯作者：
T. Ise;Y. Oba
中科院分区：
文献类型：
--
作者：
T. Ise;Y. Oba
分析和利用时空大数据是气候变化研究的基础。然而，由于统计框架的限制，这些数据没有完全纳入气候模型。在这里，我们采用VARENN（神经网络环境的视觉增强表示）来有效地将1901-2016年气候数据的月度观测总结为二维图形图像。使用彩色图像的红色、绿色和蓝色通道，在单个图像中同时表示三个不同的变量。对于全局数据集，通过卷积神经网络训练模型。这些模型成功地对气温和降水的上升和福尔斯进行了分类。此外，输入变量和目标变量之间的相似性被观察到对模型准确性有显着影响。输入变量的季节和年际变化，其重要性量化模型的功效。我们成功地说明了短期（每月）波动对模型准确性的重要性，这表明我们基于人工智能的方法抓住了一些以前未知的模式，这些模式是后续气候趋势的指标。因此，VARENN是一种有效的方法来总结时空数据的客观和准确。
Analyzing and utilizing spatiotemporal big data are essential for studies concerning climate change. However, such data are not fully integrated into climate models owing to limitations in statistical frameworks. Herein, we employ VARENN (visually augmented representation of environment for neural networks) to efficiently summarize monthly observations of climate data for 1901–2016 into two-dimensional graphical images. Using red, green, and blue channels of color images, three different variables are simultaneously represented in a single image. For global datasets, models were trained via convolutional neural networks. These models successfully classified the rises and falls in temperature and precipitation. Moreover, similarities between the input and target variables were observed to have a significant effect on model accuracy. The input variables had both seasonal and interannual variations, whose importance was quantified for model efficacy. We successfully illustrated the importance of short-term (monthly) fluctuations in the model accuracy, suggesting that our AI-based approach grasped some previously unknown patterns that are indicators of succeeding climate trends. VARENN is thus an effective method to summarize spatiotemporal data objectively and accurately.