Search

Globally all countries encounter air pollution problems along their development path. As a significant indicator of air quality, PM 2.5 concentration has long been proven to be affecting the population's death rate. Machine learning algorithms proven to outperform traditional statistical approaches are widely used in air pollution prediction. However research on the model selection discussion and environmental interpretation of model prediction results is still scarce and urgently needed to lead the policy making on air pollution control. Our research compared four types of machine learning algorisms LinearSVR, K-Nearest Neighbor, Lasso regression, Gradient boosting by looking into their performance in predicting PM 2.5 concentrations among different cities and seasons. The results show that the machine learning model is able to forecast the next day PM 2.5 concentration based on the previous five days' data with better accuracy. The comparative experiments show that based on city level the Gradient Boosting prediction model has better prediction performance with mean absolute error (MAE) of 9 ug/m 3 and root mean square error (RMSE) of 10.25-16.76 ug/m 3 , lower compared with the other three models, and based on season level four models have the best prediction performances in winter time and the worst in summer time. And more importantly the demonstration of models' different performances in each city and each season is of great significance in environmental policy implications., Competing Interests: The authors declare no conflict of interest., (© 2022 The Author(s).)

Food supply and consumption are critical for sustaining urban system functions, and are key determinants of the quantity and pathways of nutrient flow in cities. Nutrient elements from urban food consumption are becoming major pollutant sources in urban environments. Therefore, understanding flow magnitude and pathways, the role of a growing population, and changing dietary structure and technology in future nutrient metabolism are essential to understand cities as ecosystems and urban environmental management. Taking the city of Xiamen, a rapid urbanizing area of Southeast China as a case study, we simulated urban metabolism of three major food-sourced nutrient elements (carbon, nitrogen, and phosphorus or CNP) over 1991-2010 and environmental emissions. Impacts of future population growth, dietary habit change, and waste treatment improvement on various environments were forecast by scenario analysis. A sensitivity analysis was conducted to test how different waste treatment technologies affect environmental emissions from food-sourced nutrients. Our results show that the food-sourced CNP had various metabolic fluxes through urban systems, with carbon mostly emitted into the air and nitrogen and phosphorus mostly discharged into landfills and water. Population growth and dietary structure change will accelerate increases of nutrient emissions to the environment, whereas enhancing current waste treatment technology can just alter emissions to different environments. Based on the results, we discuss how food-sourced nutrient metabolism can be better managed, to enhance connectivity between cities and their hinterlands and maintain environmental emissions within the carrying capacity of the cities., (Copyright © 2016. Published by Elsevier Ltd.)

For most of its history, China has supported a growing population through food systems which have been mutually inclusive of people and their locality. This trajectory has required adequate ecosystem maintenance or humanised reformulation and a high degree of recyclable nutrient flow. The 'tipping point' in habitat sustainability has come with the size and demographic structure of China's population to one that is ageing, with modernisation of its infrastructure and increased expectations of better livelihoods, standards of living and health. In order to meet these expectations, China has embarked on rapid urbanisation for upwards of 300 million people over the next 15-20 years and to do so taking account of the environmental limitations. The process will radically change rural as well as urban China and the systems which connect them. Chief among these will be ecosystems in number and type along with the food and health systems integral to them. To minimise ecological damage and optimise the benefits to people and place, describing, monitoring and managing the process will be paramount. The present paper is a situational analysis of health as it may be ecologically favoured or disordered (Ecosystem Health Disorders) and of the food systems on which the environment and health depend. An effort is made to enumerate the current situation in China in a way that might enable the optimisation of humanised ecosystems.

Background and Objectives: Health outcomes such as survival, minimal disability and well-being are presumptively dependent on food and ecosystems. An integral measure of the critical urban food system linkages to health problems is needed. Much of the current health change in cities could be attributed to short-comings in food systems which can pose threats to food security and food safety. Health problems have needed a reconceptualisation of present medical and nutritional constructs., Methods and Study Design: The present study is based on a situational analysis of food and the related ecosystems presumptively affected by rapid urbanisation in China. With an ecological information matrix, an Urban Food System Index with ten indicators which could influence food system outcomes and promote health and well-being has been developed. It uses sixteen data sets from the National Bureau of Statistics for all 31 provinces in China. The indicators were Locality, Climate, Biodiversity, Infrastructure, Transport, Population structure, Livelihood, Recreation and Socialisation, Personal security and Communication. The indicators for each province, scored between 1 (severe) and 5 (best), were used to predict life expectancy for China as a whole by multivariable regression analysis., Results: The best model explained 70% of the variance and had significant beta coefficients for population structure (proportion of juveniles) (-0.52, p<0.0001) and livelihood (food expenditure) (0.31, p<0.05)., Conclusions: Population characteristics and livelihoods related to food systems can account for much of life expectancy as a health outcome. An index which captured this in-formation is provided and could evaluate concurrently as well as prospectively food system-related health with urbanisation.