Forecasting air pollution PM2.5 in Beijing using weather data and multiple kernel learning

PM_2.5 mass concentration prediction is an important research issue because of the increasing impact of air pollution on the urban environment. In this paper, a PM_2.5 forecasting framework incorporating meteorological factors based on multiple kernel learning (MKL) is proposed to forecast the near future PM_2.5. In addition, we develop a novel two-step algorithm for solving the primal MKL problem. Compared with most existing MKL 2-step algorithms, the proposed algorithm does not require the optimal step size for updating kernel combination coefficients by linear search. To demonstrate the performance of the proposed forecasting framework, its performance is compared to single kernel-based support vector regression (SVR). Data sets of an inland city Beijing acquired from UCI are used to train and validate both of two methods. Experiments show that our proposed method outperforms the SVR.     

A new PM2.5 concentration forecasting system based on AdaBoost-ensemble system with deep learning approach

A reliable and efficient forecasting system can be used to warn the general public against the increasing PM_2.5 concentration. This paper proposes a novel AdaBoost-ensemble technique based on a hybrid data preprocessing-analysis strategy, with the following contributions: (i) a new decomposition strategy is proposed based on the hybrid data preprocessing-analysis strategy, which combines the merits of two popular decomposition algorithms and has been proven to be a promising decomposition strategy; (ii) the long short-term memory (LSTM), as a powerful deep learning forecasting algorithm, is applied to individually forecast the decomposed components, which can effectively capture the long-short patterns of complex time series; and (iii) a novel AdaBoost-LSTM ensemble technique is then developed to integrate the individual forecasting results into the final forecasting results, which provides significant improvement to the forecasting performance. To evaluate the proposed model, a comprehensive and scientific assessment system with several evaluation criteria, comparison models, and experiments is designed. The experimental results indicate that our developed hybrid model considerably surpasses the compared models in terms of forecasting precision and statistical testing and that its excellent forecasting performance can guide in developing effective control measures to decrease environmental contamination and prevent the health issues caused by a high PM_2.5 concentration.     

A deep residual compensation extreme learning machine and applications

The extreme learning machine (ELM) is a type of machine learning algorithm for training a single hidden layer feedforward neural network. Randomly initializing the weight between the input layer and the hidden layer and the threshold of each hidden layer neuron, the weight matrix of the hidden layer can be calculated by the least squares method. The efficient learning ability in ELM makes it widely applicable in classification, regression, and more. However, owing to some unutilized information in the residual, there are relatively huge prediction errors involving ELM. In this paper, a deep residual compensation extreme learning machine model (DRC-ELM) of multilayer structures applied to regression is presented. The first layer is the basic ELM layer, which helps in obtaining an approximation of the objective function by learning the characteristics of the sample. The other layers are the residual compensation layers in which the learned residual is corrected layer by layer to the predicted value obtained in the previous layer by constructing a feature mapping between the input layer and the output of the upper layer. This model is applied to two practical problems: gold price forecasting and airfoil self-noise prediction. We used the DRC-ELM with 50, 100, and 200 residual compensation layers respectively for experiments, which show that DRC-ELM does better in generalization and robustness than classical ELM, improved ELM models such as GA-RELM and OS-ELM, and other traditional machine learning algorithms such as support vector machine (SVM) and back-propagation neural network (BPNN).     

基于RS GA ELM的矿井瓦斯涌出量预测

为了对煤矿井下瓦斯涌出量进行预测,采用粗糙集与改进极限学习机相结合的方法,在样本数据的筛选上吸取粗糙集数据约简的优点,充分利用极限学习机训练速度快、具有良好泛化性能的特点,并结合遗传算法选择最优的输入权值矩阵和隐含层偏差,避免随机产生所造成的误差。利用编写程序确定隐含层神经元个数,比依靠经验更为准确。在实际应用中选取煤层瓦斯含量、煤层埋藏深度、煤层厚度、煤层间距、工作面日产量五个因素作为预测的影响参数。研究结果表明:该预测模型预测的最大相对误差为5687 1%,最小相对误差为0,平均相对误差为2582 7%,相比改进前的预测模型具有更强的泛化能力和更高的预测精度。     

The buzz on caffeine in invertebrates: effects on behavior and molecular mechanisms

A number of recent studies from as diverse fields as plant–pollinator interactions, analyses of caffeine as an environmental pollutant, and the ability of caffeine to provide protection against neurodegenerative diseases have generated interest in understanding the actions of caffeine in invertebrates. This review summarizes what is currently known about the effects of caffeine on behavior and its molecular mechanisms in invertebrates. Caffeine appears to have similar effects on locomotion and sleep in both invertebrates and mammals. Furthermore, as in mammals, caffeine appears to have complex effects on learning and memory. However, the underlying mechanisms for these effects may differ between invertebrates and vertebrates. While caffeine’s ability to cause release of intracellular calcium stores via ryanodine receptors and its actions as a phosphodiesterase inhibitor have been clearly established in invertebrates, its ability to interact with invertebrate adenosine receptors remains an important open question. Initial studies in insects and mollusks suggest an interaction between caffeine and the dopamine signaling pathway; more work needs to be done to understand the mechanisms by which caffeine influences signaling via biogenic amines. As of yet, little is known about whether other actions of caffeine in vertebrates, such as its effects on GABA_A and glycine receptors, are conserved. Furthermore, the pharmacokinetics of caffeine remains to be elucidated. Overall behavioral responses to caffeine appear to be conserved amongst organisms; however, we are just beginning to understand the mechanisms underlying its effects across animal phyla.     

Effects of atmospheric pollution on human health

Most air pollutants do not lead to specific diseases. Depending on the pollutant, the concentration and the duration of exposure, some organs are more affected than others. The most frequent disorders are those caused by irritant gases and particulates on the mucous membranes and respiratory organs. The consequences are eye, nose and throat inflammations, diminished lung function, increased susceptability to respiratory infection and a higher incidence of chronic bronchitis. These disorders and diseases are, of course, influenced by other factors as well, such as immune deficiency, allergies, occupational exposure to pollutants, and particularly smoking. The effects of air pollutants are, therefore, multifactorially conditioned and nonspecific disorders are placed in the foreground. Evidence for an association of air pollution with adverse effects on human health is drawn from three sources: animal experiments, experimental human exposures, and epidemiologic studies of exposed human populations. The burden of atmospheric pollution must be reduced to protect human health by an adequate safety margin. In particular, the increased sensitivity of sick and aged people as well as children should be taken into account. In defining the maximum emmission levels, preventive aspects should have priority so as to keep the risk of damage to health and the harmful influences on the environment to a minimum.This article Effects of atmospheric pollution on human health by H. U. Wanner is a revised version of the same article that was first published in the Proceedings of the 1990 European Aerosol Conference; special issue of the J. Aerosol Sci., Vol. 21, Suppl. 1 (1990) 389–396.Reprinted with kind permission from Pergamon Press Ltd, Headington Hill Hall, Oxford OX3 0BW, Great Britain.     

环渤海地区环境污染问题演化及其对策

环渤海地区是我国经济增长的第三极。随着该地区工农业生产的迅速发展和新型产业的崛起,其环境污染问题日益突出。本文从环渤海地区水体污染、大气污染和土壤环境污染三个角度,对该地区环境污染问题的演化进行了宏观意义上的分析和预测,并据此提出了解决该地区环境污染问题的对策措施。     

Ex post and ex ante prediction of unobserved multivariate time series: a structural‐model based approach

A methodology for estimating high‐frequency values of an unobserved multivariate time series from low‐frequency values of and related information to it is presented in this paper. This is an optimal solution, in the multivariate setting, to the problem of ex post prediction, disaggregation, benchmarking or signal extraction of an unobservable stochastic process. Also, the problem of extrapolation or ex ante prediction is optimally solved and, in this context, statistical tests are developed for checking online the ocurrence of extreme values of the unobserved time series and consistency of future benchmarks with the present and past observed information. The procedure is based on structural or unobserved component models, whose assumptions and specification are validated with the data alone. Copyright © 2007 John Wiley & Sons, Ltd.     

Forecasting the Dubai financial market with a combination of momentum effect with a deep belief network

Applying recent advances in machine learning techniques, we propose a hybrid model to forecast the Dubai financial market general index. Particularly, we exploit a deep belief networks model that applies a restricted Boltzmann machine as its main component in combination with momentum effects. We also introduce an innovative way of selecting the inputs by using momentum effects. With this hybrid methodology we generate a prediction model along with a comparison of three different linear models. The results obtained from the hybrid model are better and more stable than the three linear models. The findings support that the hybrid model we applied will find their way into finance because of their reliability and good performance.     

中国城市化进程中的环境抗争

城市化是经济社会发展的必然选择。然而,随着中国城市化飞速发展,也产生了城市水、大气、固体废弃物和噪声污染等一系列生态环境问题。同时,随着环境意识的增强,人们对居住环境质量的要求不断提高,致使城市化过程中环境抗争事件不断涌现。本文回顾了已有研究文献,以国外环境抗争、国内农村环境抗争与城市环境抗争作对比,突出城市环境抗争的特点;从抗争的情感基础、精英力量、弱组织化和互动过程四个方面对城市的环境抗争进行建构;从抗争力量、制度化因素、发展观念和社会力量四个方面分析当前环境抗争所面临的一系列困境。培育公民社会、更新地方政府的发展观念、加强社会科学与自然科学和管理科学之间的交叉研究等是应对当前困境最根本的出路。     

The COVID-19 pandemic and global environmental change: Emerging research needs

The outbreak of COVID-19 raised numerous questions on the interactions between the occurrence of new infections, the environment, climate and health. The European Union requested the H2020 HERA project which aims at setting priorities in research on environment, climate and health, to identify relevant research needs regarding Covid-19. The emergence and spread of SARS-CoV-2 appears to be related to urbanization, habitat destruction, live animal trade, intensive livestock farming and global travel. The contribution of climate and air pollution requires additional studies. Importantly, the severity of COVID-19 depends on the interactions between the viral infection, ageing and chronic diseases such as metabolic, respiratory and cardiovascular diseases and obesity which are themselves influenced by environmental stressors. The mechanisms of these interactions deserve additional scrutiny. Both the pandemic and the social response to the disease have elicited an array of behavioural and societal changes that may remain long after the pandemic and that may have long term health effects including on mental health. Recovery plans are currently being discussed or implemented and the environmental and health impacts of those plans are not clearly foreseen. Clearly, COVID-19 will have a long-lasting impact on the environmental health field and will open new research perspectives and policy needs.     

The COVID-19 pandemic and global environmental change: Emerging research needs

The outbreak of COVID-19 raised numerous questions on the interactions between the occurrence of new infections, the environment, climate and health. The European Union requested the H2020 HERA project which aims at setting priorities in research on environment, climate and health, to identify relevant research needs regarding Covid-19. The emergence and spread of SARS-CoV-2 appears to be related to urbanization, habitat destruction, live animal trade, intensive livestock farming and global travel. The contribution of climate and air pollution requires additional studies. Importantly, the severity of COVID-19 depends on the interactions between the viral infection, ageing and chronic diseases such as metabolic, respiratory and cardiovascular diseases and obesity which are themselves influenced by environmental stressors. The mechanisms of these interactions deserve additional scrutiny. Both the pandemic and the social response to the disease have elicited an array of behavioural and societal changes that may remain long after the pandemic and that may have long term health effects including on mental health. Recovery plans are currently being discussed or implemented and the environmental and health impacts of those plans are not clearly foreseen. Clearly, COVID-19 will have a long-lasting impact on the environmental health field and will open new research perspectives and policy needs.     

The influence of N2-fixation on the carbon balance of leguminous plants

Biological dinitrogen fixation by legume-rhizobia symbiosis is very important both from the economic and from the ecological point of view. Theoretically, the reduction of the N₂-molecule to ammonia requires at least 16 ATP and 1.5 mg C per mg N fixed (N_fix). These values are difficult to determine in situ as this necessitates the determination of that part of root respiration which drives N₂-fixation. New approaches to such determinations and the results obtained are described. The values vary, depending on the plant species studied, the developmental stage of the plants and the genetic variability of macro- (and micro-?) symbionts. The values range between 1.5 and 4 mg C/mg N_fix. In some species (e.g.Vicia faba L. cv. Fribo), the apparent CO₂ assimilation is enhanced in order to meet this high energy need. In others (e.g.Pisum sativum L. cv. Grapis), root growth is restricted. Physiological criteria are discussed which allow an early diagnosis of the energetic efficiency of various combinations of macro-and microsymbionts as a basis for a selection in plant breeding.     

Cadmium in foods and the diet

Information on the sources of cadmium in food are presented and the effects of raised environmental levels of cadmium on the concentration of cadmium in plant based foods, fish and shellfish, meat and offals, and dairy produce are discussed. Information is also presented on normal dietary intakes of cadmium and how these intakes may be elevated by environmental pollution or atypical dietary habits. The estimation of dietary intakes of cadmium using data about extreme intakes of specific foods is described.     

Experimental data on the energetic flux during glycolytic oscillations in yeast extracts

Calorimetric experiments were performed on yeast extracts in which glycolytic oscillations were occurring. High metabolic fluxes coincided with low amplitudes and with high frequencies in a temperature range from 283 to 303 K, yielding an activation energy ofE _a=76.8 kJ mol^–1 and a mean Q₁₀ value of 2.5±0.4. The calorimetrically determined reaction enthalpy _fH^0, of the glycolytic catabolism of glucose revealed two distinct groups of extract preparations, with no intermediate values. The values were –107.5±28.7 kJ mol^–1 and –30.8±5.7 kJmol^–1, respectively, while –100.0 kJ mol^–1 was predicted from theoretical calculations. Kreuzberg and Betz⁶ predicted rate limiting effects of GAPDH in oscillating extracts. However, when possible effects of GAPDH on frequency, number of oscillations or total heat production were examined, no influence of increasing or reducing the initial GAPDH concentration could be found. The results are discussed with reference to existing models of glycolytic oscillations.     

What is the environment in environmental health research? Perspectives from the ethics of science

Environmental health research produces scientific knowledge about environmental hazards crucial for public health and environmental justice movements that seek to prevent or reduce exposure to these hazards. The environment in environmental health research is conceptualized as the range of possible social, biological, chemical, and/or physical hazards or risks to human health, some of which merit study due to factors such as their probability and severity, the feasibility of their remediation, and injustice in their distribution. This paper explores the ethics of identifying the relevant environment for environmental health research, as judgments involved in defining an environmental hazard or risk, judgments of that hazard or risk's probability, severity, and/or injustice, as well as the feasibility of its remediation, all ought to appeal to non-epistemic as well as epistemic values. I illustrate by discussing the case of environmental lead, a housing-related hazard that remains unjustly distributed by race and class and is particularly dangerous to children. Examining a controversy in environmental health research ethics where researchers tested multiple levels of lead abatement in lead-contaminated households, I argue that the broader perspective on the ethics of environmental health research provided in the first part of this paper may have helped prevent this controversy.     

The atmospheric environment—an introduction

The atmosphere is part of the environment with which the human organism is permanently confronted. Epidemiological research investigates the occurrence of effects on morbidity and mortality due to heat, cold, air pollution and changes in the weather. Concentrating on aspects of the environment relevant for medical questions, three major complexes of effects can be discriminated: the complex conditions of heat exchange, the direct biological effects of solar radiation, and air pollution. Biometeorological knowledge can serve to assess the atmospheric environment, and can also be of help in the field of preventive planning, to conserve and develop the climate as a natural resource with regard to man's health, well-being and performance.     

Estimating and Predicting the General Random Effects Model

This paper extends the ‘remarkable property’ of Breusch (Journal of Econometrics 1987; 36 : 383–389) and Baltagi and Li (Journal of Econometrics 1992; 53 : 45–51) to the three‐way random components framework. Indeed, like its one‐way and two‐way counterparts, the three‐way random effects model maximum likelihood estimation can be obtained as an iterated generalized least squares procedure through an appropriate algorithm of monotonic sequences of some variance components ratios, θ_i (i = 2, 3, 4). More specifically, a search over θ_iwhile iterating on the regression coefficients estimates β and the other θ_jwill guard against the possibility of multiple local maxima of the likelihood function. In addition, the derivations of related prediction functions are obtained based on complete as well as incomplete panels. Finally, an application to international trade issues modeling is presented. Copyright © 2014 John Wiley & Sons, Ltd.     

Cadmium in foods and the diet

Summary Information on the sources of cadmium in food are presented and the effects of raised environmental levels of cadmium on the concentration of cadmium in plant based foods, fish and shellfish, meat and offals, and dairy produce are discussed. Information is also presented on normal dietary intakes of cadmium and how these intakes may be elevated by environmental pollution or atypical dietary habits. The estimation of dietary intakes of cadmium using data about extreme intakes of specific foods is described.The author wishes to thank the Ministry of Agriculture, Fisheries and Food for permission to publish this paper.     

Assessment of agricultural energy consumption of Turkey by MLR and Bayesian optimized SVR and GPR models

Agricultural productivity highly depends on the cost of energy required for cultivation. Thus prior knowledge of energy consumption is an important step for energy planning and policy development in agriculture. The aim of the present study is to evaluate the application potential of multiple linear regression (MLR) and machine learning tools such as support vector regression (SVR) and Gaussian process regression (GPR) to forecast the agricultural energy consumption of Turkey. In the development of the models, widespread indicators such as agricultural value-added, total arable land, gross domestic product share of agriculture, and population data were used as input parameters. Twenty-eight-year historical data from 1990 to 2017 were utilized for the training and testing stages of the models. A Bayesian optimization method was applied to improve the prediction capability of SVR and GPR models. The performance of the models was measured by various statistical tools. The results indicated that the Bayesian optimized GPR (BGPR) model with exponential kernel function showed a superior prediction capability over MLR and Bayesian optimized SVR model. The root mean square error, mean absolute deviation, mean absolute percentage error, and coefficient of determination (R²) values for the BGPR model were determined as 0.0022, 0.0005, 0.2041, and 0.9999 in the training phase and 0.0452, 0.0310, 7.7152, and 0.9677 in the testing phase, respectively. As a result, it can be concluded that the proposed BGPR model is an efficient technique and has the potential to predict agricultural energy consumption with high accuracy.