Gong Jintao, Ding Lei, Lu Yingyu
The Library, Ningbo Polytechnic, Ningbo 315800, China.
Research Center of Industrial Economy Around Hangzhou Bay, Ningbo Polytechnic, Ningbo 315800, China.
Heliyon. 2023 Mar 11;9(3):e14526. doi: 10.1016/j.heliyon.2023.e14526. eCollection 2023 Mar.
The foundation for the environmental department to take suitable measures and make a significant contribution towards improving air quality is the precise and dependable prediction of PM concentration. It is essential to review the development process and hotspots of PM concentration prediction studies over the past 20 years (2000-2021) comprehensively and quantitatively. This study used detailed bibliometric methods and CiteSpace software to visually analyze the PM pollution level. The outcomes found that the prediction research phases of PM can be broadly divided into three phases and enter the rapid growth phase after 2017. Five categories of keywords are clustered, and the forecasting data and forecasting methods are typical cluster representatives. Then, the construction and processing of PM concentration prediction datasets, the prediction methods and technical processes, and the determination of the prediction spatial-temporal scales are the main content of the analysis. In the future, it is necessary to concentrate on multi-source data fusion for PM concentration prediction at multiple spatial-temporal scales and focus on technology integration and innovative applications in forecasting models, especially the optimal use of deep machine learning methods to improve prediction accuracy and practical application conversion.
环境部门采取适当措施并为改善空气质量做出重大贡献的基础是对颗粒物（PM）浓度进行精确可靠的预测。全面、定量地回顾过去20年（2000 - 2021年）PM浓度预测研究的发展历程和热点至关重要。本研究采用详细的文献计量方法和CiteSpace软件对PM污染水平进行可视化分析。结果发现，PM的预测研究阶段大致可分为三个阶段，并在2017年后进入快速增长阶段。五类关键词聚类，预测数据和预测方法是典型的聚类代表。然后，PM浓度预测数据集的构建与处理、预测方法与技术流程以及预测时空尺度的确定是分析的主要内容。未来，有必要专注于多源数据融合用于多时空尺度的PM浓度预测，并注重预测模型中的技术集成与创新应用，尤其是深度机器学习方法的优化使用，以提高预测精度和实际应用转化率。
