Random Fourier feature kernel recursive maximum mixture correntropy algorithm for online time series prediction.

In the paper, a novel kernel recursive least-squares (KRLS) algorithm named random Fourier feature kernel recursive maximum mixture correntropy (RFF-RMMC) algorithm is proposed, which improves the prediction efficiency and robustness of the KRLS algorithm. Random Fourier feature (RFF) method as well as maximum mixture correntropy criterion (MMCC) are combined and applied into KRLS algorithm afterwards. Using RFF to approximate the kernel function in KRLS with a fixed cost can greatly reduce the computational complexity and simultaneously improve the prediction efficiency. In addition, the MMCC maintains the robustness like the maximum correntropy criterion (MCC). More importantly, it can enhance the accuracy of the similarity measurement between predicted and true values by more flexible parameter settings, and then make up for the loss of prediction accuracy caused by RFF to a certain extent. The performance of the RFF-RMMC algorithm for online time series prediction is verified by the simulation results based on three datasets.

Multitask Air-Quality Prediction Based on LSTM-Autoencoder Model.

With the development of the data-driven modeling techniques, using the neural network to simulate the transport process of atmospheric pollutants and constructing PM2.5 time-series prediction model have become a hot topic. The existing data-driven approaches often ignore the dynamical relationships among multiple sites in urban areas, which results in nonideal prediction accuracy. In response to this problem, this article proposes a long short-term memory (LSTM) autoencoder multitask learning model to predict PM2.5 time series in multiple locations city wide. The model could implicitly and automatically excavate the intrinsic relevance among the pollutants in different stations. And the meteorological information from the monitoring stations is fully utilized, which is beneficial for the performance of the proposed model. Specifically, multilayer LSTM networks can simulate the spatiotemporal characteristics of urban air pollution particles. And using the stacked autoencoder to encode the key evolution pattern of urban meteorological systems could provide important auxiliary information for PM2.5 time-series prediction. In addition, multitask learning could automatically discover the dynamical relationship between multiple key pollution time series and solve the problem of insufficient use of multisite information in the modeling process of the traditional data-driven methods. The simulation results of PM2.5 prediction in Beijing indicate the effectiveness of the proposed method.

Estimation of ground-level PM2.5 concentration using MODIS AOD and corrected regression model over Beijing, China.

To establish a new model for estimating ground-level PM2.5 concentration over Beijing, China, the relationship between aerosol optical depth (AOD) and ground-level PM2.5 concentration was derived and analysed firstly. Boundary layer height (BLH) and relative humidity (RH) were shown to be two major factors influencing the relationship between AOD and ground-level PM2.5 concentration. Thus, they are used to correct MODIS AOD to enhance the correlation between MODIS AOD and PM2.5. When using corrected MODIS AOD for modelling, the correlation between MODIS AOD and PM2.5 was improved significantly. Then, normalized difference vegetation index (NDVI), surface temperature (ST) and surface wind speed (SPD) were introduced as auxiliary variables to further improve the performance of the corrected regression model. The seasonal and annual average distribution of PM2.5 concentration over Beijing from 2014 to 2016 were mapped for intuitively analysing. Those can be regarded as important references for monitoring the ground-level PM2.5 concentration distribution. It is obviously that the PM2.5 concentration distribution over Beijing revealed the trend of "southeast high and northwest low", and showed a significant decrease in annual average PM2.5 concentration from 2014 to 2016.

Air quality co-benefits from climate mitigation for human health in South Korea.

Climate change mitigation efforts to reduce greenhouse gas (GHG) emissions have associated costs, but there are also potential benefits from improved air quality, such as public health improvements and the associated cost savings. A multidisciplinary modeling approach can better assess the co-benefits from climate mitigation for human health and provide a justifiable basis for establishment of adequate climate change mitigation policies and public health actions. An integrated research framework was adopted by combining a computable general equilibrium model, an air quality model, and a health impact assessment model, to explore the long-term economic impacts of climate change mitigation in South Korea through 2050. Mitigation costs were further compared with health-related economic benefits under different socioeconomic and climate change mitigation scenarios. Achieving ambitious targets (i.e., stabilization of the radiative forcing level at 3.4 W/m2) would cost 1.3-8.5 billion USD in 2050, depending on varying carbon prices from different integrated assessment models. By contrast, achieving these same targets would reduce costs by 23 billion USD from the valuation of avoided premature mortality, 0.14 billion USD from health expenditures, and 0.38 billion USD from reduced lost work hours, demonstrating that health benefits alone noticeably offset the costs of cutting GHG emissions in South Korea.

Co-benefits of climate mitigation on air quality and human health in Asian countries.

Climate change mitigation involves reducing fossil fuel consumption and greenhouse gas emissions, which is expensive, particularly under stringent mitigation targets. The co-benefits of reducing air pollutants and improving human health are often ignored, but can play significant roles in decision-making. In this study, we quantified the co-benefits of climate change mitigation on ambient air quality and human health in both physical and monetary terms with a particular focus on Asia, where air quality will likely be degraded in the next few decades if mitigation measures are not undertaken. We used an integrated assessment framework that incorporated economic, air chemistry transport, and health assessment models. Air pollution reduction through climate change mitigation under the 2 °C goal could reduce premature deaths in Asia by 0.79 million (95% confidence interval: 0.75-1.8 million) by 2050. This co-benefit is equivalent to a life value savings of approximately 2.8 trillion United States dollars (USD) (6% of the gross domestic product [GDP]), which is decidedly more than the climate mitigation cost (840 billion USD, 2% of GDP). At the national level, India has the highest potential net benefit of 1.4 trillion USD, followed by China (330 billion USD) and Japan (68 billion USD). Furthermore, in most Asian countries, per capita GDP gain and life value savings would increase with per capita GDP increasing. We robustly confirmed this qualitative conclusion under several socioeconomic and exposure-response function assumptions.