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

文献类型： 外文期刊

第一作者： Pan, Tiantian

作者： Pan, Tiantian;Liu, Fei;Dai, Xiaorong;Wang, Yuan;Xiao, Hang;Wang, Yuan;Xiao, Hang;Wang, Wei

作者机构：

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.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序