您好，欢迎访问广东省农业科学院 机构知识库！
广东省农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Vis-NIR spectra-image transformation based on circular spectral mapping for measurement of particulate matter concentration

文献类型： 外文期刊

作者： Pan, Tiantian 1 ; Dai, Xiaorong 2 ; Wang, Wei 5 ; Wang, Yuan 3 ; Xiao, Hang 3 ; Liu, Fei 1 ;

作者机构： 1.Zhejiang Univ, Coll Biosyst Engn & Food Sci, 866 Yuhangtang Rd, Hangzhou 310058, Peoples R China

2.Zhejiang Wanli Univ, Coll Biol & Environm Sci, Ningbo 315100, Peoples R China

3.Chinese Acad Sci, Inst Urban Environm, Key Lab Urban Environm & Hlth, Ningbo Observat & Res Stn, Xiamen 361021, Peoples R China

4.Chinese Acad Sci, Haixi Ind Technol Innovat Ctr Beilun, Zhejiang Key Lab Urban Environm Proc & Pollut Cont, Ningbo 315830, Peoples R China

5.Guangdong Acad Agr Sci, Inst Facil Agr, Guangzhou 510640, Peoples R China

关键词： Fine particulate matter (PM 2.5 ); Concentration; Visible near infrared (Vis-NIR) spectroscopy; Spectra-image transformation; Feature fusion

期刊名称：ANALYTICA CHIMICA ACTA （ 影响因子：6.0； 五年影响因子：5.7 ）

ISSN： 0003-2670

年卷期： 2025 年 1359 卷

页码：

收录情况： SCI

摘要： Background: The fine particulate matter (PM2.5), one of the most concerned airborne pollutants, significantly impacts air quality and human health. The potential hazard of PM2.5 related to its concentration, while the traditional methods for PM concentration measuring were expensive, time-consuming, while low-cost sensors often suffer from poor accuracy and stability. Therefore, there is a great need for a rapid, precise and stable measurement method for filter-based PM2.5. Results: We propose a novel spectra-image transformation and fusion method for filter-based PM2.5 measurement using a portable visible near infrared (Vis-NIR) spectrometer. Traditional machine learning models based on spectra alone achieved low accuracy (R2p < 0.8). To improve performance, we introduced the circular spectral mapping (CSM) method to transform PM2.5 spectra into CSM images, which were processed using ResNet-18, ShuffleNet V2, and MobileNet V2 networks with an attention mechanism module. The optimal model, ShuffleNetV2_Attn, improved R2p to 0.9935. To furtherly improve the model stability, the numerical and graphical feature fusions were conducted, and the ShuffleNetV2_Attn was selected as optimal feature extractor of CSM images. The machine learning models were built based on fusion features, and the optimal model was the partial least squares (PLS) model based on fusion features extracted by successive projections algorithm (SPA), of which the R2p, RMSEP and mean absolute percentage error (MAPEp) were 0.9947, 6.0213 mu g/m3 and 4.17 %, demonstrating high accuracy and stability overall concentration range. Significance: The proposed spectra-image transformation and fusion method greatly improved the accuracy and efficiency of filter-based PM2.5 measurement. It overcome the limitations of spectral-based machine learning methods, which often fail to capture full-band characteristics, and provides a new approach for integrating numerical and graphical spectral information.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：广东省农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台