VARENN: Graphical representation of spatiotemporal data and application to climate studies
This provides an incremental improvement for climate researchers by offering a more efficient way to represent and analyze spatiotemporal data in climate models.
The authors tackled the problem of integrating spatiotemporal climate data into models by developing VARENN, a method that converts monthly climate observations from 1901-2016 into 2D graphical images, enabling successful classification of temperature and precipitation changes using convolutional neural networks.
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 2-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 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. VARENN is thus an effective method to summarize spatiotemporal data objectively and accurately.