Lijian Han

Comparing Machine Learning Classifiers for Object-Based Land Cover Classification Using Very High Resolution Imagery

This study evaluates and compares the performance of four machine learning classifiers—support vector machine (SVM), normal Bayes (NB), classification and regression tree (CART) and K nearest neighbor (KNN)—to classify very high resolution images, using an object-based classification procedure. In particular, we investigated how tuning parameters affect the classification accuracy with different training sample sizes. We found that: (1) SVM and NB were superior to CART and KNN, and both could achieve high classification accuracy (>90%); (2) the setting of tuning parameters greatly affected classification accuracy, particularly for the most commonly-used SVM classifier; the optimal values of tuning parameters might vary slightly with the size of training samples; (3) the size of training sample also greatly affected the classification accuracy, when the size of training sample was less than 125. Increasing the size of training samples generally led to the increase of classification accuracies for all four classifiers. In addition, NB and KNN were more sensitive to the sample sizes. This research provides insights into the selection of classifiers and the size of training samples. It also highlights the importance of the appropriate setting of tuning parameters for different machine learning classifiers and provides useful information for optimizing these parameters.

Increasing impact of urban fine particles (PM2.5) on areas surrounding Chinese cities

The negative impacts of rapid urbanization in developing countries have led to a deterioration in urban air quality, which brings increasing negative impact to its surrounding areas (e.g. in China). However, to date there has been rare quantitative estimation of the urban air pollution to its surrounding areas in China.We thus evaluated the impact of air pollution on the surrounding environment under rapid urbanization in Chinese prefectures during 1999 – 2011. We found that: (1) the urban environment generated increasing negative impact on the surrounding areas, and the PM2.5 concentration difference between urban and rural areas was particularly high in large cities. (2) Nearly half of the Chinese prefectures (156 out of 350) showed increased impact of urban PM2.5 pollution on its surrounding areas. Those prefectures were mainly located along two belts: one from northeast China to Sichuan province, the other from Shanghai to Guangxi province. Our study demonstrates the deterioration in urban air quality and its potential impacts on its surrounding areas in China. We hope that the results presented here will encourage different approaches to urbanization to mitigate the negative impact caused by urban air pollution, both in China and other rapidly developing countries.

Earlier-Season Vegetation Has Greater Temperature Sensitivity of Spring Phenology in Northern Hemisphere

In recent decades, satellite-derived start of vegetation growing season (SOS) has advanced in many northern temperate and boreal regions. Both the magnitude of temperature increase and the sensitivity of the greenness phenology to temperature–the phenological change per unit temperature–can contribute the advancement. To determine the temperature-sensitivity, we examined the satellite-derived SOS and the potentially effective pre-season temperature (T eff) from 1982 to 2008 for vegetated land between 30°N and 80°N. Earlier season vegetation types, i.e., the vegetation types with earlier SOSmean (mean SOS for 1982–2008), showed greater advancement of SOS during 1982–2008. The advancing rate of SOS against year was also greater in the vegetation with earlier SOSmean even the T eff increase was the same. These results suggest that the spring phenology of vegetation may have high temperature sensitivity in a warmer area. Therefore it is important to consider temperature-sensitivity in assessing broad-scale phenological responses to climatic warming. Further studies are needed to explore the mechanisms and ecological consequences of the temperature-sensitivity of start of growing season in a warming climate.

Fine particulate (PM2.5) dynamics during rapid urbanization in Beijing, 1973-2013.

PM2.5 has been given special concern in recent years when the air quality monitoring station started recording. However, long-term PM2.5 concentration dynamic analysis cannot be taken with the limited observations. We therefore estimated the PM2.5 concentration using meteorological visibility data in Beijing. We found that 71 ± 17% of PM10 were PM2.5, which contributed to visibility impairment (y = 332.26e−0.232x; R2 = 0.75, P < 0.05). We then reconstructed a time series of annual PM2.5 from 1973 to 2013, and examined its relationship with urbanization by indicators of population, gross domestic production (GDP), energy consumption, and number of vehicles. Concluded that 1) Meteorological conditions were not the major cause of PM2.5 increase from 1973 to 2013; 2) With population and GDP growth, PM2.5 increased significantly (R2 = 0.5917, P < 0.05; R2 = 0.5426, P < 0.05); 3) Intensive human activity could change air quality in a short period, as observed changes in the correlations of PM2.5 concentration with energy consumption and number of vehicles before and after 2004, respectively. The success of this research provides an easy way in reconstructing long-term PM2.5 concentration with limited PM2.5 observation and meteorological visibility, and insight the impact of urbanization on air quality.

Meteorological and urban landscape factors on severe air pollution in Beijing

Air pollution gained special attention with the rapid development in Beijing. In January 2013, Beijing experienced extreme air pollution, which was not well examined. We thus examine the magnitude of air quality in the particular month by applying the air quality index (AQI), which is based on the newly upgraded Chinese environmental standard. Our finding revealed that (1) air quality has distinct spatial heterogeneity and relatively better air quality was observed in the northwest while worse quality happened in the southeast part of the city; (2) the wind speed is the main determinant of air quality in the city—when wind speed is greater than 4 m/sec, air quality can be significantly improved; and (3) urban impervious surface makes a contribution to the severity of air pollution—that is, with an increase in the fraction of impervious surface in a given area, air pollution is more severe. The results from our study demonstrated the severe pollution in Beijing and its meteorological and landscape factors. Also, the results of this work suggest that very strict air quality management should be conducted when wind speed less than 4 m/sec, especially at places with a large fraction of urban impervious surface. Implications: Prevention of air pollution is rare among methods with controls on meteorological and urban landscape conditions. We present research that utilizes the latest air quality index (AQI) to compare air pollution with meteorological and landscape conditions. We found that wind is the major meteorological factor that determines the air quality. For a given wind speed greater than 4 m/sec, the air quality improved significantly. Urban impervious surface also contributes to the severe air pollution: that is, when the fraction of impervious surface increases, there is more severe air pollution. These results suggest that air quality management should be conducted when wind speed is less than 4 m/sec, especially at places with a larger fraction of urban impervious surface.

An enhanced dust index for Asian dust detection with MODIS images

An enhanced dust index (EDI) for Moderate Resolution Imaging Spectroradiometer (MODIS) solar reflectance bands is proposed that provides a means to detect the dust status of the atmosphere. The EDI utilizes only solar reflectance channels and may therefore be applied consistently to the entire MODIS time series records (1999 to present) for daytime dust observation, producing a higher spatial resolution (500 m) dust result than that from thermal-infrared records (1000 m), which were developed previously and are currently being used. The index introduces dust optical density (α), which can be simply estimated by spectral unmixing, into the normalized difference between reflectance at near-infrared (2.13 μm) and blue (0.469 μm). Dust severity can thus be rated from weak to severe within a standard range of –1 to 1. The index was applied to 11 typical dust events during 2000–2010 in East Asia, where it showed good coherence with meteorological station-observed visibility (R 2 = 0.7909, p < 0.05) and standardized visibility (R 2 = 0.7128, p < 0.05). Further comparison with the commonly used normalized difference dust index (NDDI) and brightness temperature difference (BTD) between MODIS bands 31 and 32 also indicated a better performance of the EDI in identifying the spatial and density distributions of dust. Previously applied satellite-based dust indices, particularly for the visible and near-infrared, can therefore be improved for a better quantification of dust aerosols.

Spatial-Temporal Variations of Water Quality and Its Relationship to Land Use and Land Cover in Beijing, China.

Rapid urbanization with intense land use and land cover (LULC) change and explosive population growth has a great impact on water quality. The relationship between LULC characteristics and water quality provides important information for non-point sources (NPS) pollution management. In this study, we first quantified the spatial-temporal patterns of five water quality variables in four watersheds with different levels of urbanization in Beijing, China. We then examined the effects of LULC on water quality across different scales, using Pearson correlation analysis, redundancy analysis, and multiple regressions. The results showed that water quality was improved over the sampled years but with no significant difference (p > 0.05). However, water quality was significantly different among nonurban and both exurban and urban sites (p < 0.05). Forest land was positively correlated with water quality and affected water quality significantly (p < 0.05) within a 200 m buffer zone. Impervious surfaces, water, and crop land were negatively correlated with water quality. Crop land and impervious surfaces, however, affected water quality significantly (p < 0.05) for buffer sizes greater than 800 m. Grass land had different effects on water quality with the scales. The results provide important insights into the relationship between LULC and water quality, and thus for controlling NPS pollution in urban areas.

More than 500 million Chinese urban residents (14% of the global urban population) are imperiled by fine particulate hazard

Chinas urbanization and the subsequent public vulnerability to degenerated environment is important to global public health. Among the environmental problems, fine particulate (PM2.5) pollution has become a serious hazard in rapidly urbanizing China. However, quantitative information remains inadequate. We thus collected PM2.5 concentrations and population census records, to illustrate the spatial patterns and changes in the PM2.5 hazard levels in China, and to quantify public vulnerability to the hazard during 2000-2010, following the air quality standards of World Health Organization. We found that 28% (2.72 million km2) of Chinas territory, including 78% of cities (154 cities) with a population of >1 million, was exposed to PM2.5 hazard in 2010; a 15% increase (1.47 million km2) from 2000 to 2010. The hazards potentially impacted the health of 72% of the total population (942 million) in 2010, including 70% of the young (206 million) and 76% of the old (71 million). This was a significant increase from the 42% of total the population (279 million) exposed in 2000. Of the total urban residents, 76% (501 million) were affected in 2010. Along with PM2.5 concentration increase, massive number of rural to urban migration also contributed greatly to Chinas urban public health vulnerability.

Land Use Significantly Affects the Distribution of Urban Green Space: Case Study of Shanghai, China

AbstractUrban green space distribution has been extensively investigated; however, few studies have examined how these distributions are linked to anthropogenic activities at very fine scales. Here, the authors investigated the spatial variations of green space among different land-use categories within the city of Shanghai at the city, inner-outer ring road, and district scales. Land-use patches were delineated from aerial photos, and green coverage was derived from advanced land observation satellite (ALOS) imagery. Green space composition and configuration were then calculated for each land-use polygon. New residential, old residential, villa residential, industrial, and institutional were the five dominant land-use types. At the city level, green space coverage and configuration varied significantly among different land-use types. Villa residential had the highest green space coverage (67.63%), followed by institutional (38.81%), new residential (27.64%), industrial (27.54%), and old residential (16.7...

Quantifying the characteristics of particulate matters captured by urban plants using an automatic approach

It is widely accepted that urban plant leaves can capture airborne particles. Previous studies on the particle capture capacity of plant leaves have mostly focused on particle mass and/or size distribution. Fewer studies, however, have examined the particle density, and the size and shape characteristics of particles, which may have important implications for evaluating the particle capture efficiency of plants, and identifying the particle sources. In addition, the role of different vegetation types is as yet unclear. Here, we chose three species of different vegetation types, and firstly applied an object-based classification approach to automatically identify the particles from scanning electron microscope (SEM) micrographs. We then quantified the particle capture efficiency, and the major sources of particles were identified. We found (1) Rosa xanthina Lindl (shrub species) had greater retention efficiency than Broussonetia papyrifera (broadleaf species) and Pinus bungeana Zucc. (coniferous species), in terms of particle number and particle area cover. (2) 97.9% of the identified particles had diameter ≤10 μm, and 67.1% of them had diameter ≤2.5 μm. 89.8% of the particles had smooth boundaries, with 23.4% of them being nearly spherical. (3) 32.4%-74.1% of the particles were generated from bare soil and construction activities, and 15.5%-23.0% were mainly from vehicle exhaust and cooking fumes.