A new cross-domain prediction model of air pollutant concentration based on secure federated learning and optimized LSTM neural network

A novel hybrid optimization model for evaluating and forecasting air quality grades

Air pollution has a significant global impact on natural resources and public health. Accurate prediction of air pollution is crucial for effective prevention and control measures. However, due to regional variations, different cities may have varying primary pollutants, posing new challenges for accurate prediction. In this paper, we propose a novel method called FP-RF, which integrates clustering algorithms to categorize multiple cities according to their air quality index values. Subsequently, we apply functional principal component analysis to extract the primary components of air pollution within each cluster. Furthermore, an enhanced random forest algorithm is utilized to predict air quality grades for each city. We conduct experimental evaluations using authentic historical data from Anhui Province spanning from 2018 to 2023. The results unequivocally establish the effectiveness of our model, with an average accuracy rate of 98.6% in forecasting six pollution grades and 96.04% accuracy in predicting 16 prefecture-level cities, surpassing performance compared to other baseline models.

Breathing in danger: Understanding the multifaceted impact of air pollution on health impacts

Air pollution, a pervasive environmental threat that spans urban and rural landscapes alike, poses significant risks to human health, exacerbating respiratory conditions, triggering cardiovascular problems, and contributing to a myriad of other health complications across diverse populations worldwide. This article delves into the multifarious impacts of air pollution, utilizing cutting-edge research methodologies and big data analytics to offer a comprehensive overview. It highlights the emergence of new pollutants, their sources, and characteristics, thereby broadening our understanding of contemporary air quality challenges. The detrimental health effects of air pollution are examined thoroughly, emphasizing both short-term and long-term impacts. Particularly vulnerable populations are identified, underscoring the need for targeted health risk assessments and interventions. The article presents an in-depth analysis of the global disease burden attributable to air pollution, offering a comparative perspective that illuminates the varying impacts across different regions. Furthermore, it addresses the economic ramifications of air pollution, quantifying health and economic losses, and discusses the implications for public policy and health care systems. Innovative air pollution intervention measures are explored, including case studies demonstrating their effectiveness. The paper also brings to light recent discoveries and insights in the field, setting the stage for future research directions. It calls for international cooperation in tackling air pollution and underscores the crucial role of public awareness and education in mitigating its impacts. This comprehensive exploration serves not only as a scientific discourse but also as a clarion call for action against the invisible but insidious threat of air pollution, making it a vital read for researchers, policymakers, and the general public.

Study on carbon emission driving factors and carbon peak forecasting in power sector of Shanxi province

The realisation of the low-carbon transition of the energy system in resource-intensive regions, as embodied by Shanxi Province, depends on a thorough understanding of the factors impacting the power sector's carbon emissions and an accurate prediction of the peak trend. Because of this, the power industry's carbon emissions in Shanxi province are measured in this article from 1995 to 2020 using data from the Intergovernmental Panel on Climate Change (IPCC). To obtain a deeper understanding of the factors impacting carbon emissions in the power sector, factor decomposition is performed using the Logarithmic Mean Divisia Index (LMDI). Second, in order to precisely mine the relationship between variables and carbon emissions, the Sparrow Search Algorithm (SSA) aids in the optimisation of the Long Short-Term Memory (LSTM). In order to implement SSA-LSTM-based carbon peak prediction in the power industry, four development scenarios are finally built up. The findings indicate that: (1) There has been a fluctuating upward trend in Shanxi Province's total carbon emissions from the power industry between 1995 and 2020, with a cumulative growth of 372.10 percent. (2) The intensity of power consumption is the main factor restricting the rise of carbon emissions, contributing -65.19%, while the per capita secondary industry contribution factor, contributing 158.79%, is the main driver of the growth in emissions. (3) While the baseline scenario and the rapid development scenario fail to peak by 2030, the low carbon scenario and the green development scenario peak at 243,991,100 tonnes and 258,828,800 tonnes, respectively, in 2025 and 2028. (4) Based on the peak performance and the decomposition results, resource-intensive cities like Shanxi's power industry should concentrate on upgrading and strengthening the industrial structure, getting rid of obsolete production capacity, and encouraging the faster development of each factor in order to help the power sector reach peak carbon performance.

Federated Multi-Label Learning (FMLL): Innovative Method for Classification Tasks in Animal Science

Federated learning is a collaborative machine learning paradigm where multiple parties jointly train a predictive model while keeping their data. On the other hand, multi-label learning deals with classification tasks where instances may simultaneously belong to multiple classes. This study introduces the concept of Federated Multi-Label Learning (FMLL), combining these two important approaches. The proposed approach leverages federated learning principles to address multi-label classification tasks. Specifically, it adopts the Binary Relevance (BR) strategy to handle the multi-label nature of the data and employs the Reduced-Error Pruning Tree (REPTree) as the base classifier. The effectiveness of the FMLL method was demonstrated by experiments carried out on three diverse datasets within the context of animal science: Amphibians, Anuran-Calls-(MFCCs), and HackerEarth-Adopt-A-Buddy. The accuracy rates achieved across these animal datasets were 73.24%, 94.50%, and 86.12%, respectively. Compared to state-of-the-art methods, FMLL exhibited remarkable improvements (above 10%) in average accuracy, precision, recall, and F-score metrics.

Prediction of air pollutant concentrations based on the long short-term memory neural network

In recent years, environmental problems caused by air pollutants have received increasing attention. Effective prediction of air pollutant concentrations is an important way to protect the public from harm. Recently, due to extreme climate and social development, the forest fire frequency has increased. During the biomass combustion process caused by forest fires, the content of particulate matter (PM) in the atmosphere increases significantly. However, most existing air pollutant concentration prediction methods do not consider the considerable impact of forest fires, and effective long-term prediction models have not been established to provide early warnings for harmful gases. Therefore, in this paper, we collected a daily air quality data set (aerodynamic diameter smaller than 2.5 µm, PM2.5) for Heilongjiang Province, China, from 2017 to 2023 and A novel Long Short-Term Memory (LSTM) model was proposed to effectively predict the situation of air pollutants. The model could automatically extract information of the effective time step from the historical data set and combine forest fire disturbance and climate data as auxiliary data to improve the model prediction ability. Moreover, we created artificial neural network (ANN) and permissive regression (support vector machine, SVR) models for comparative experiments. The results showed that the precision accuracy of the developed LSTM model is higher. Unlike the other models, the LSTM neural network model could effectively predict the concentration of air pollutants in long-term series. Regarding long-term observation missions (7 days), the proposed model performed well and stably, with R2 reaching over 88%.