Prediction and explanation for ozone variability using cross-stacked ensemble learning model.

With the development of monitoring technology, the variety of ozone precursors that can be detected by monitoring stations has been increased dramatically. And this has brought a great increment of information to ozone prediction and explanation studies. This study completes feature mining and reconstruction of multi-source data (meteorological data, conventional pollutant data, and precursors data) by using a machine learning approach, and built a cross-stacked ensemble learning model (CSEM). In the feature engineering process, this study reconstructed two VOCs variables most associated with ozone and found it works best to use the top seven variables with the highest contribution. The CSEM includes three base models: random forest, extreme gradient boosting tree, and LSTM, learning the parameters of the model under the integrated training of cross-stacking. The cross-stacked integrated training method enables the second-layer learner of the ensemble model to make full use of the learning results of the base models as training data, thereby improving the prediction performance of the model. The model predicted the hourly ozone concentration with R2 of 0.94, 0.97, and 0.96 for mild, moderate, and severe pollution cases, respectively; mean absolute error (MAE) of 4.48 µg/m3, 5.01 µg/m3, and 8.71 µg/m3, respectively. The model predicted ozone concentrations under different NOx and VOCs reduction scenarios, and the results show that with a 20 % reduction in VOCs and no change in NOx in the study area, 75.28 % of cases achieved reduction and 15.73 % of cases got below 200 µg/m3. In addition, a comprehensive evaluation index of the prediction model is proposed in this paper, which can be extended to any prediction model performance comparison and analysis. For practical application, machine learning feature selection and cross-stacked ensemble models can be jointly applied in ozone real-time prediction and emission reduction strategy analysis.

Literature Review on Power Battery Echelon Reuse and Recycling from a Circular Economy Perspective.

Developing new energy vehicles (NEVs) is necessary to grow the low-carbon vehicle industry. Many concentrated end-of-life (EoL) power batteries will cause large-scale environmental pollution and safety accidents when the time comes to replace the first generation of batteries if improper recycling and disposal methods are utilized. Significant negative externalities will result for the environment and other economic entities. When recycling EoL power batteries, some countries need to solve problems about lower recycling rates, unclear division of echelon utilization scenarios, and incomplete recycling systems. Therefore, this paper first analyzes representative countries' power battery recycling policies and finds out the reasons for the low recycling rate in some countries. It is also found that echelon utilization is the critical link to EoL power battery recycling. Secondly, this paper summarizes the existing recycling models and systems to form a complete closed-loop recycling process from the two stages of consumer recycling and corporate disposal of batteries. The policies and recycling technologies are highly concerned with echelon utilization, but few studies focus on analyzing application scenarios of echelon utilization. Therefore, this paper combines cases to delineate the echelon utilization scenarios clearly. Based on this, the 4R EoL power battery recycling system is proposed, which improves the existing recycling system and can recycle EoL power batteries efficiently. Finally, this paper analyzes the existing policy problems and existing technical challenges. Based on the actual situation and future development trends, we propose development suggestions from the government, enterprises, and consumers to achieve the maximum reused of EoL power batteries.

The positive role of trade openness in industrial green total factor productivity-provincial evidence from China.

The sustainable development of the economy is a key issue of global concern. Green total factor productivity (GTFP) combining economic growth with resources and the environment can evaluate the quality of economic development comprehensively and accurately. In this paper, super slack-based measure (Super-SBM) model and Malmquist-Luenberger (ML) index were used to calculate GTFP. The trend of industrial GTFP in China's 30 provinces from 2006-2015 was analyzed. Furtherly, a dynamic panel model was used to discuss the impact of trade openness on GTFP. The results showed that (1) the growth rate of GTFP rose from 2007 to 2011 and declined significantly from 2011 to 2015, and GTFP only achieved positive growth in 2011; (2) the growth rate of GTFP in the eastern region was higher than that in the central and western regions; (3) the trend of technical progress change (MLTECH) index was highly consistent with that of ML index. That was, technical progress played a major role in the variation of GTFP; (4) trade openness could significantly improve China's GTFP. Every 1% increase in trade openness could increase GTFP by 0.097% on average. It is advisable to implement differentiated economic development and environmental policies in different regions. Meanwhile, relevant measures can be taken to promote import and export trade, such as encouraging companies to increase investment in green technology research and development, optimizing the trade environment.

Resident risk attitude analysis in the decision-making management of waste incineration construction.

Environmental pollutants generated by waste incineration plants, such as heavy metals and dioxin, make surrounding residents very sensitive to the construction of such facilities. This sensitivity and anxiety of residents may induce group events, which further leads to the emergence of social risks. Based on risk perception theory, a total of 320 questionnaires was designed and handed out to residents neighboring to Jiangqiao Waste Incineration Plant in Shanghai, China to detect the factors affecting risk attitude toward such plants. Using ordered logit model, it is found that there are four decisive factors including impact on health, information cognitive, objective characteristics, and the attitude of the neighbors. These factors have different influence on resident risk attitudes, in which the attitude of the neighbors is of most significance, followed by the economic-geography characteristics of residents, the information cognitive has minimal impact.

Is the finer the better for municipal solid waste (MSW) classification in view of recyclable constituents? A comprehensive social, economic and environmental analysis.

With the accelerating pace of urbanization, the continuous increase of municipal solid waste (MSW) has become a major obstacle to China's economic development. Therefore, China recently regards MSW classification scenario as an important strategy for national ecological civilization. However, published references have not focused on MSW classification in view of environmental, economic and social acceptation simultaneously. This research proposes a new Decision Support System (DSS) model considering all three aspects to analyze the comprehensive benefit of the four MSW classification scenarios in Pudong (Shanghai, China) using cost benefit analysis (CBA), life cycle assessment (LCA) and analytical hierarchy process (AHP). Among them, there is an important boundary factor in the life cycle assessment. This work mainly focuses on the net energy consumption, namely the air and water emission of different substances. The results show that the classification scenario II, dividing MSW into toxic and hazardous waste, recyclable, kitchen waste and combustible waste, is the best option. Although scenario III (MSW is divided into toxic and hazardous waste, recyclable waste (paper, plastic, scrap metal, waste glass and other small class), kitchen waste and combustible wastes) and IV (recyclable waste in Scenario II is further classified, for example, paper is subdivided into newspapers, books, cardboard, etc.) further refine the MSW classification, the DSS model analysis results indicate that neither of these are the most feasible scenario. Therefore, finer classification is not always the better if we consider all three pillars of sustainability.