[论文解读] A Deep Learning Approach for Forecasting Air Pollution in South Korea Using LSTM

Tien-Cuong Bui, Van-Duc Le+1 more|arXiv (Cornell University)|Apr 21, 2018

Air Quality Monitoring and Forecasting参考文献 11被引用 59

一句话总结

本文提出基于 LSTM 的编码器-解码器 RNN 框架，利用时间序列的空气质量与气象数据预测大邱、首尔、北京和沈阳的空气污染，并评估用于长期预测的不同网络配置。

ABSTRACT

Tackling air pollution is an imperative problem in South Korea, especially in urban areas, over the last few years. More specially, South Korea has joined the ranks of the world's most polluted countries alongside with other Asian capitals, such as Beijing or Delhi. Much research is being conducted in environmental science to evaluate the dangerous impact of particulate matters on public health. Besides that, deterministic models of air pollutant behavior are also generated; however, this is both complex and often inaccurate. On the contrary, deep recurrent neural network reveals potent potential on forecasting out-comes of time-series data and has become more prevalent. This paper uses Recurrent Neural Network (RNN) with Long Short-Term Memory units as a framework for leveraging knowledge from time-series data of air pollution and meteorological information in Daegu, Seoul, Beijing, and Shenyang. Additionally, we use encoder-decoder model, which is similar to machine comprehension problems, as a crucial part of our prediction machine. Finally, we investigate the prediction accuracy of various configurations. Our experiments prevent the efficiency of integrating multiple layers of RNN on prediction model when forecasting far timesteps ahead. This research is a significant motivation for not only continuing researching on urban air quality but also help the government leverage that insight to enact beneficial policies

研究动机与目标

• 动机：需要在韩国南部城市及邻近城市预测空气污染。
• 提出一个基于 LSTM 的编码器-解码器 RNN 框架，用于时间序列的空气质量和气象数据。
• 评估不同 RNN 配置对长时程（远时间步）预测精度的影响。

提出的方法

• 使用带有长短期记忆单元的循环神经网络来建模时间序列数据。
• 采用编码器-解码器架构将输入序列映射到预测的未来污染水平。
• 结合来自大邱、首尔、北京和沈阳的空气污染和气象信息。
• 通过实验比较不同配置，以评估多层 RNN 对长时程预测的影响。

实验结果

研究问题

• RQ1 基于 LSTM 的编码器-解码器框架是否能提升跨多城市的空气污染预测？
• RQ2 不同的多层 RNN 配置如何影响远时间步的预测精度？
• RQ3 该模型是否能够有效利用污染和气象数据进行长时程预测？

主要发现

• 本研究探讨将多层 RNN 集成用于远时步预测的有效性。
• 实验评估了编码器-解码器 LSTM 框架在各种配置下的预测准确性。