基于高阶图卷积网络的城市空气质量推断模型
信息技术与网络安全
陈 杰1,许镇义1,2
(1.中国科学技术大学 自动化系,安徽 合肥230026; 2.合肥综合性国家科学中心人工智能研究院,安徽 合肥230088)
摘要: 能否精确地预测城市区域空气质量分布,对于政府环境治理以及人们日常预防等方面,具有重要的意义。该问题面临的挑战是:一是不同区域的空气质量分布具有时空交互性;二是空气质量分布受到外部因素的影响。通用化卷积神经网络以处理任意图结构数据,成为近些年来研究的热点之一,将城市空气质量预测问题可制定为时空图预测问题。基于提出的高阶图卷积网络,设计了一种有效的空气质量推断模型。该模型可以捕获空气质量分布的时空交互性和提取外部影响因素特征,从而精确预测空气质量分布。通过验证现实北京市空气质量数据,结果表明提出的模型远远优于目前已知的通用方法。
中圖分類號: P41
文獻標(biāo)識碼: A
DOI: 10.19358/j.issn.2096-5133.2021.04.006
引用格式: 陳杰,許鎮(zhèn)義. 基于高階圖卷積網(wǎng)絡(luò)的城市空氣質(zhì)量推斷模型[J].信息技術(shù)與網(wǎng)絡(luò)安全,2021,40(4):33-41,45.
文獻標(biāo)識碼: A
DOI: 10.19358/j.issn.2096-5133.2021.04.006
引用格式: 陳杰,許鎮(zhèn)義. 基于高階圖卷積網(wǎng)絡(luò)的城市空氣質(zhì)量推斷模型[J].信息技術(shù)與網(wǎng)絡(luò)安全,2021,40(4):33-41,45.
A high-order graph convolutional network for urban air quality inference
Chen Jie1,Xu Zhenyi1,2
(1.Department of Automation,University of Science and Technology,Hefei 230026,China; 2.Institute of Artificial Intelligence,Hefei Comprehensive National Science Center,Hefei 230088,China)
Abstract: Whether it can accurately predict the air quality distribution is of great significance to the government′s environmental governance and people′s daily health prevention. This problem is challenging for the following reasons:(1)The air quality distribution in different regions has temporal and spatial interaction;(2)The air quality distribution is affected by external factors. In recent years,generalized convolutional neural network(CNN) is one of the research hotspots to process arbitrary graph structured data, so the fine-grained air quality forecasting problem in urban areas is formulated as an urban spatio-temporal graph prediction problem.Based on the proposed high-order graph convolution, we design an effective air quality inference model for inferring the air quality distribution, which could capture the spatio-temporal interaction of air quality distribution and extract external influential factor features. Through the verification of Beijing air quality data, experimental results show that proposed approach far outperforms known baseline methods.
Key words : air quality;spatial-temporal interaction;graph convolutional network;semi-supervised learning
0 引言
近年來,隨著經(jīng)濟的增長,環(huán)境問題也變得日益突出,大氣污染問題正受到前所未有的關(guān)注和重視[1]。城市空氣中,如一氧化碳(CO)、碳?xì)浠?HC)、氮氧化物(NOx)、固體顆粒物(PM2.5、PM10)等污染物濃度與人們的身體健康息息相關(guān)[2-3]。空氣質(zhì)量指數(shù)(Air Quality Index,AQI)是定量描述空氣質(zhì)量狀況的指數(shù),其數(shù)值越大說明空氣污染狀況越嚴(yán)重,對人體健康的危害也就越大[4]。
本文詳細(xì)內(nèi)容請下載:http://m.ihrv.cn/resource/share/2000003475
作者信息:
陳 杰1,許鎮(zhèn)義1,2
(1.中國科學(xué)技術(shù)大學(xué) 自動化系,安徽 合肥230026;
2.合肥綜合性國家科學(xué)中心人工智能研究院,安徽 合肥230088)
此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。
