Sustainability · 2023 · 36 citations · 38 references
ComputingData ScienceEnvironmental SciencesAtmospheric ScienceForecastingMachine LearningAir QualityEnsemble ForecastingEnsemble LearningEnsemble MethodsExplainable Machine LearningParticulate MatterAir Pollution ForecastingAtmospheric Particulate PollutionDay-ahead ForecastingDeep Learning For ForecastingMachine Learning For Environmental DataMachine Learning Forecasting ModelsParticulate Matter PollutionPm2.5
Long-term forecasting and analysis of PM2.5, a significant air pollution source, is vital for environmental governance and sustainable development. We evaluated 10 machine learning and deep learning models using PM2.5 concentration data along with environmental variables. Employing explainable AI (XAI) technology facilitated explainability and formed the basis for factor analysis. At a 30-day forecasting horizon, ensemble learning surpassed deep learning in performance, with CatBoost emerging as the top-performing model. For forecasting horizons of 90 and 180 days, Bi-SLTM and Bi-GRU, respectively, exhibited the highest performance. Through an analysis of influencing factors by SHAP, it was observed that PM10 exerted the greatest impact on PM2.5 forecasting. However, this effect was particularly pronounced at higher concentrations of CO. Conversely, at lower CO concentrations, the impact of increased PM10 concentrations on PM2.5 was limited. Hence, it can be inferred that CO plays a pivotal role in driving these effects. Following CO, factors such as “dew point” and “temperature” were identified as influential. These factors exhibited varying levels of linear correlation with PM2.5, with temperature showing a negative correlation, while PM10, CO, and dew point generally demonstrated positive correlations with PM2.5.
38
Dong Xibin, Zhiwen Yu, Wenming Cao et al. · Frontiers of Computer Science · 2019 · 1.9K citations
Computing, Data Science, Data Mining +11
A survey on deep learning and its applications
Shi Dong, Ping Wang, Khushnood Abbas · Computer Science Review · 2021 · 1.5K citations
Algorithms to estimate Shapley value feature attributions
Hugh Chen, Ian Covert, Scott Lundberg et al. · Nature Machine Intelligence · 2023 · 416 citations
Explaining a series of models by propagating Shapley values
Hugh Chen, Scott Lundberg, Su‐In Lee · Nature Communications · 2022 · 241 citations · Full text