Prediction of PM2.5 concentrations at unsampled points using multiscale geographically and temporally weighted regression

Spatiotemporal effects of urban micro-scale built environment on cardiovascular diseases

Cardiovascular disease (CVD) has become a significant threat to the health of urban populations, and the urban built environment, as a key determinant of cardiovascular health, affects residents through various dimensions including physical activity, urban pollution, mental health, and dietary habits. However, existing research predominantly focuses on macro-level geographic scales, with limited exploration of the potential impact of intra-urban microenvironments on CVD. This study focuses on the central area of Nanning, China, as the case study area, employing methods such as global spatial autocorrelation analysis, emerging spatiotemporal hotspot analysis, and spatiotemporal geographically weighted regression (GTWR) analysis to comprehensively examine the spatiotemporal associations between CVD and built environment elements. The results reveal that CVD and built environment elements exhibit significant spatial clustering and correlations, with all variables demonstrating spatial clustering patterns. Six built environment factors-parks and squares, transportation facilities, life services, sports and leisure, medical care, and Catering and food-are spatially associated with disease incidence. The influence of built environment factors on CVD varies and exhibits pronounced spatiotemporal heterogeneity, with the greatest coefficient fluctuation observed for parks and squares, and the smallest for catering services. Parks and squares generally contribute positively to cardiovascular health by lowering disease risk across most areas, although in the central zone, dense population and heavy traffic lead to a positive association with disease incidence. Fortunately, this adverse impact has been gradually mitigated through ongoing improvements in urban green space planning; transportation facilities increases disease risk due to associated noise and air pollution, with particularly strong effects observed in the central region. However, the implementation of green transportation initiatives has effectively mitigated this negative impact; life services show a positive association with CVD, but their diverse types and spatially balanced distribution render their impact relatively minor; sports and leisure are associated with reduced disease risk in the central part of the study area, but in the northeast and northwest, they exhibit a positive association due to population dispersion. As residents' usage habits become more consistent, the associated impacts are gradually stabilizing; medical care help reduce disease risk in the central and eastern regions, but show a positive correlation in the northern area due to patient overflow and referral patterns. With the more equitable distribution of healthcare resources, this relationship is gradually stabilizing; catering and food are positively associated with CVD, but the effect is relatively small and spatially balanced, likely due to their widespread and uniform distribution. These findings offer valuable case-based evidence for urban planning and public health policymaking, thereby contributing to the construction and advancement of healthy cities.

A spatiotemporal analysis of the association between carbon productivity, socioeconomics, medical resources and cardiovascular diseases in southeast rural China

Introduction

With China's rapid industrialization and urbanization, China has been increasing its carbon productivity annually. Understanding the association between carbon productivity, socioeconomics, and medical resources with cardiovascular diseases (CVDs) may help reduce CVDs burden. However, relevant studies are limited.

Objectives

The study aimed to describe the temporal and spatial distribution pattern of CVDs hospitalization in southeast rural China and to explore its influencing factors.

Methods

In this study, 1,925,129 hospitalization records of rural residents in southeast China with CVDs were analyzed from the New Rural Cooperative Medical Scheme (NRCMS). The spatial distribution patterns were explored using Global Moran's I and Local Indicators of Spatial Association (LISA). The relationships with influencing factors were detected using both a geographically and temporally weighted regression model (GTWR) and multiscale geographically weighted regression (MGWR).

Results

In southeast China, rural inpatients with CVDs increased by 95.29% from 2010 to 2016. The main groups affected were elderly and women, with essential hypertension (26.06%), cerebral infarction (17.97%), and chronic ischemic heart disease (13.81%) being the leading CVD subtypes. The results of LISA shows that central and midwestern counties, including Meilie, Sanyuan, Mingxi, Jiangle, and Shaxian, showed a high-high cluster pattern of CVDs hospitalization rates. Negative associations were observed between CVDs hospitalization rates and carbon productivity, and positive associations with per capita GDP and hospital beds in most counties (p < 0.05). The association between CVDs hospitalization rates and carbon productivity and per capita GDP was stronger in central and midwestern counties, while the relationship with hospital bed resources was stronger in northern counties.

Conclusion

Rural hospitalizations for CVDs have increased dramatically, with spatial heterogeneity observed in hospitalization rates. Negative associations were found with carbon productivity, and positive associations with socioeconomic status and medical resources. Based on our findings, we recommend low-carbon development, use of carbon productivity as an environmental health metric, and rational allocation of medical resources in rural China.

Non-Iterative Multiscale Estimation for Spatial Autoregressive Geographically Weighted Regression Models

Multiscale estimation for geographically weighted regression (GWR) and the related models has attracted much attention due to their superiority. This kind of estimation method will not only improve the accuracy of the coefficient estimators but also reveal the underlying spatial scale of each explanatory variable. However, most of the existing multiscale estimation approaches are backfitting-based iterative procedures that are very time-consuming. To alleviate the computation complexity, we propose in this paper a non-iterative multiscale estimation method and its simplified scenario for spatial autoregressive geographically weighted regression (SARGWR) models, a kind of important GWR-related model that simultaneously takes into account spatial autocorrelation in the response variable and spatial heterogeneity in the regression relationship. In the proposed multiscale estimation methods, the two-stage least-squares (2SLS) based GWR and the local-linear GWR estimators of the regression coefficients with a shrunk bandwidth size are respectively taken to be the initial estimators to obtain the final multiscale estimators of the coefficients without iteration. A simulation study is conducted to assess the performance of the proposed multiscale estimation methods, and the results show that the proposed methods are much more efficient than the backfitting-based estimation procedure. In addition, the proposed methods can also yield accurate coefficient estimators and such variable-specific optimal bandwidth sizes that correctly reflect the underlying spatial scales of the explanatory variables. A real-life example is further provided to demonstrate the applicability of the proposed multiscale estimation methods.

Full Coverage Hourly PM2.5 Concentrations' Estimation Using Himawari-8 and MERRA-2 AODs in China

(1) Background: Recognising the full spatial and temporal distribution of PM2.5 is important in order to understand the formation, evolution and impact of pollutants. The high temporal resolution satellite, Himawari-8, providing an hourly AOD dataset, has been used to predict real-time hourly PM2.5 concentrations in China in previous studies. However, the low observation frequency of the AOD due to long-term cloud/snow cover or high surface reflectance may produce high uncertainty in characterizing diurnal variation in PM2.5. (2) Methods: We fill the missing Himawari-8 AOD with MERRA-2 AOD, and drive the random forest model with the gap-filled AOD (AODH+M) and Himawari-8 AOD (AODH) to estimate hourly PM2.5 concentrations, respectively. Then we compare AODH+M-derived PM2.5 with AODH-derived PM2.5 in detail. (3) Results: Overall, the non-random missing information of the Himawari-8 AOD will bring large biases to the diurnal variations in regions with both a high polluted level and a low polluted level. (4) Conclusions: Filling the gap with the MERRA-2 AOD can provide reliable, full spatial and temporal PM2.5 predictions, and greatly reduce errors in PM2.5 estimation. This is very useful for dynamic monitoring of the evolution of PM2.5 in China.

Improved Daily Spatial Precipitation Estimation by Merging Multi-Source Precipitation Data Based on the Geographically Weighted Regression Method: A Case Study of Taihu Lake Basin, China

Accurately estimating the spatial and temporal distribution of precipitation is crucial for hydrological modeling. However, precipitation products based on a single source have their advantages and disadvantages. How to effectively combine the advantages of different precipitation datasets has become an important topic in developing high-quality precipitation products internationally in recent years. This paper uses the measured precipitation data of Multi-Source Weighted-Ensemble Precipitation (MSWEP) and in situ rainfall observation in the Taihu Lake Basin, as well as the longitude, latitude, elevation, slope, aspect, surface roughness, distance to the coastline, and land use and land cover data, and adopts a two-step method to achieve precipitation fusion: (1) downscaling the MSWEP source precipitation field using the bilinear interpolation method and (2) using the geographically weighted regression (GWR) method and tri-cube function weighting method to achieve fusion. Considering geographical and human activities factors, the spatial and temporal distribution of precipitation errors in MSWEP is detected. The fusion of MSWEP and gauge observation precipitation is realized. The results show that the method in this paper significantly improves the spatial resolution and accuracy of precipitation data in the Taihu Lake Basin.

Prediction of Air Pollutant Concentrations via RANDOM Forest Regressor Coupled with Uncertainty Analysis—A Case Study in Ningxia

Air pollution has not received much attention until recent years when people started to understand its dreadful impacts on human health. According to air pollution and the meteorological monitoring data from 1 January 2016 to 31 December 2017 in Ningxia, we analyzed the impact of ground surface temperature, air temperature, relative humidity and the power of wind on air pollutant concentrations. Meanwhile, we analyze the relationships between air pollutant concentrations and meteorological variables by using the mathematical model of decision tree regressor (DTR), feedforward artificial neural network with back-propagation algorithm (FFANN-BP) and random forest regressor (RFR) according to air-monitoring station data. For all pollutants, the RFR increases R2 of FFANN-BP and DTR by up to 0.53 and 0.42 respectively, reduces root mean square error (RMSE) by up to 68.7 and 41.2, and MAE by up to 25.2 and 17. The empirical results show that the proposed RFR displays the best forecasting performance and could provide local authorities with reliable and precise predictions of air pollutant concentrations. The RFR effectively establishes the relationships between the influential factors and air pollutant concentrations, and well suppresses the overfitting problem and improves the accuracy of prediction. Besides, the limitation of machine learning for single site prediction is also overcame.

Understanding the distribution and drivers of PM2.5 concentrations in the Yangtze River Delta from 2015 to 2020 using Random Forest Regression

Understanding the drivers of PM_2.5 is critical for the establishment of PM_2.5 prediction models and the prevention and control of regional air pollution. In this study, the Yangtze River Delta is taken as the research object. Spatial cluster and outlier method was used to analyze the temporal and spatial distribution and variation of surface PM_2.5 in the Yangtze River Delta from 2015 to 2020, and Random Forest was utilized to analyze the drivers of PM_2.5 in this area. The results indicated that (1) based on the spatial cluster distribution of PM_2.5, the northwest and north of Yangtze River Delta region were mostly highly concentrated and surrounded by high concentrations of PM_2.5, while lowly concentrated and surrounded by low concentrations areas were distributed in the southern; (2) the relationship between PM_2.5 concentrations and drivers in the Yangtze River Delta was modeled well and the explanatory rate of drivers to PM_2.5 were more than 0.9; (3) temperature, precipitation, and wind speed were the main driving forces of PM_2.5 emission in the Yangtze River Delta. It should be noted that the repercussion of wildfire on PM_2.5 was gradually prominent. When formulating air pollution control measures, the local government normally considers the impact of weather and traffic conditions. In order to reduce PM_2.5 pollution caused by biomass combustion, the influence of wildfire should also be taken into account, especially in the fire season. Meanwhile, high leaf area was conducive to improving air quality, and the increasing green area will help reduce air pollutants.

Spatio-Temporal Evolution and Spatial Heterogeneity of Influencing Factors of SO2 Emissions in Chinese Cities: Fresh Evidence from MGWR

In this study, based on the multi-source nature and humanities data of 270 Chinese cities from 2007 to2018, the spatio-temporal evolution characteristics of SO2 emissions are revealed by using Moran’s I, a hot spot analysis, kernel density, and standard deviation ellipse models. The spatial scale heterogeneity of influencing factors is explored by using the multiscale geographically weighted regression model to make the regression results more accurate and reliable. The results show that (1) SO2 emissions showed spatial clustering characteristics during the study period, decreased by 85.12% through pollution governance, and exhibited spatial heterogeneity of differentiation. (2) The spatial distribution direction of SO2 emissions’ standard deviation ellipse in cities was “northeast–southwest”. The gravity center of the SO2 emissions shifted to the northeast, from Zhumadian City to Zhoukou City in Henan Province. The results of hot spots showed a polarization trend of “clustering hot spots in the north and dispersing cold spots in the south”. (3) The MGWR model is more accurate than the OLS and classical GWR regressions. The different spatial bandwidths have a different effect on the identification of influencing factors. There were several main influencing factors on urban SO2 emissions: the regional innovation and entrepreneurship level, government intervention, and urban precipitation; important factors: population intensity, financial development, and foreign direct investment; secondary factors: industrial structure upgrading and road construction. Based on the above conclusions, this paper explores the spatial heterogeneity of urban SO2 emissions and their influencing factors, and provides empirical evidence and reference for the precise management of SO2 emission reduction in “one city, one policy”.