A Novel Time Series-to-Image Encoding Approach for Weather Phenomena Classification

TL;DR

This paper introduces a novel method to classify weather phenomena by converting RSL time series data from 4G/LTE signals into images and applying CNNs, enabling effective data augmentation and improved classification accuracy.

Contribution

The paper presents a new time series-to-image encoding technique for weather classification using CNNs, enhancing data augmentation strategies for electromagnetic wave-based rainfall analysis.

Findings

Effective image data augmentation improves classification accuracy.

CNN-based approach successfully identifies weather phenomena from RSL data.

Proposed encoding method outperforms traditional time series analysis techniques.

Abstract

Rainfall estimation through the analysis of its impact on electromagnetic waves has sparked increasing interest in the research community. Recent studies have delved into its effects on cellular network performance, demonstrating the potential to forecast rainfall levels based on electromagnetic wave attenuation during precipitations. This paper aims to solve the problem of identifying the nature of specific weather phenomena from the received signal level (RSL) in 4G/LTE mobile terminals. Specifically, utilizing time-series data representing RSL, we propose a novel approach to encode time series as images and model the task as an image classification problem, which we finally address using convolutional neural networks (CNNs). The main benefit of the abovementioned procedure is the opportunity to utilize various data augmentation techniques simultaneously. This encompasses applying traditional approaches, such as moving averages, to the time series and enhancing the generated images. We have investigated various image data augmentation methods to identify the most effective combination for this scenario. In the upcoming sections, we will introduce the task of rainfall estimation and conduct a comprehensive analysis of the dataset used. Subsequently, we will formally propose a new approach for converting time series into images. To conclude, the paper's final section will present and discuss the experiments conducted, providing the reader with a brief yet comprehensive overview of the results.