Geospatial artificial intelligence for estimating daytime and nighttime nitrogen dioxide concentration variations in Taiwan: A spatial prediction model.

Nitrogen dioxide (NO2) is a major air pollutant primarily emitted from traffic and industrial activities, posing health risks. However, current air pollution models often underestimate exposure risks by neglecting the bimodal pattern of NO2 levels throughout the day. This study aimed to address this gap by developing ensemble mixed spatial models (EMSM) using geo-artificial intelligence (Geo-AI) to examine the spatial and temporal variations of NO2 concentrations at a high resolution of 50m. These EMSMs integrated spatial modelling methods, including kriging, land use regression, machine learning, and ensemble learning. The models utilized 26 years of observed NO2 measurements, meteorological parameters, geospatial layers, and social and season-dependent variables as representative of emission sources. Separate models were developed for daytime and nighttime periods, which achieved high reliability with adjusted R2 values of 0.92 and 0.93, respectively. The study revealed that mean NO2 concentrations were significantly higher at nighttime (9.60 ppb) compared to daytime (5.61 ppb). Additionally, winter exhibited the highest NO2 levels regardless of time period. The developed EMSMs were utilized to generate maps illustrating NO2 levels pre and during COVID restrictions in Taiwan. These findings could aid epidemiological research on exposure risks and support policy-making and environmental planning initiatives.

Concurrent assessment of personal, indoor, and outdoor PM2.5 and PM1 levels and source contributions using novel low-cost sensing devices.

The intensity, frequency, duration, and contribution of distinct PM2.5 sources in Asian households have seldom been assessed; these are evaluated in this work with concurrent personal, indoor, and outdoor PM2.5 and PM1 monitoring using novel low-cost sensing (LCS) devices, AS-LUNG. GRIMM-comparable observations were acquired by the corrected AS-LUNG readings, with R2 up to 0.998. Twenty-six non-smoking healthy adults were recruited in Taiwan in 2018 for 7-day personal, home indoor, and home outdoor PM monitoring. The results showed 5-min PM2.5 and PM1 exposures of 11.2 ± 10.9 and 10.5 ± 9.8 µg/m3 , respectively. Cooking occurred most frequently; cooking with and without solid fuel contributed to high PM2.5 increments of 76.5 and 183.8 µg/m3 (1 min), respectively. Incense burning had the highest mean PM2.5 indoor/outdoor (1.44 ± 1.44) ratios at home and on average the highest 5-min PM2.5 increments (15.0 µg/m3 ) to indoor levels, among all single sources. Certain events accounted for 14.0%-39.6% of subjects' daily exposures. With the high resolution of AS-LUNG data and detailed time-activity diaries, the impacts of sources and ventilations were assessed in detail.

Demonstrating the Applicability of Smartwatches in PM2.5 Health Impact Assessment.

Smartwatches are being increasingly used in research to monitor heart rate (HR). However, it is debatable whether the data from smartwatches are of high enough quality to be applied in assessing the health impacts of air pollutants. The objective of this study was to assess whether smartwatches are useful complements to certified medical devices for assessing PM2.5 health impacts. Smartwatches and medical devices were used to measure HR for 7 and 2 days consecutively, respectively, for 49 subjects in 2020 in Taiwan. Their associations with PM2.5 from low-cost sensing devices were assessed. Good correlations in HR were found between smartwatches and certified medical devices (rs > 0.6, except for exercise, commuting, and worshipping). The health damage coefficients obtained from smartwatches (0.282% increase per 10 µg/m3 increase in PM2.5) showed the same direction, with a difference of only 8.74% in magnitude compared to those obtained from certified medical devices. Additionally, with large sample sizes, the health impacts during high-intensity activities were assessed. Our work demonstrates that smartwatches are useful complements to certified medical devices in PM2.5 health assessment, which can be replicated in developing countries.

Application of Machine Learning for the in-Field Correction of a PM2.5 Low-Cost Sensor Network.

Many low-cost sensors (LCSs) are distributed for air monitoring without any rigorous calibrations. This work applies machine learning with PM2.5 from Taiwan monitoring stations to conduct in-field corrections on a network of 39 PM2.5 LCSs from July 2017 to December 2018. Three candidate models were evaluated: Multiple linear regression (MLR), support vector regression (SVR), and random forest regression (RFR). The model-corrected PM2.5 levels were compared with those of GRIMM-calibrated PM2.5. RFR was superior to MLR and SVR in its correction accuracy and computing efficiency. Compared to SVR, the root mean square errors (RMSEs) of RFR were 35% and 85% lower for the training and validation sets, respectively, and the computational speed was 35 times faster. An RFR with 300 decision trees was chosen as the optimal setting considering both the correction performance and the modeling time. An RFR with a nighttime pattern was established as the optimal correction model, and the RMSEs were 5.9 ± 2.0 µg/m3, reduced from 18.4 ± 6.5 µg/m3 before correction. This is the first work to correct LCSs at locations without monitoring stations, validated using laboratory-calibrated data. Similar models could be established in other countries to greatly enhance the usefulness of their PM2.5 sensor networks.

Laboratory Evaluations of Correction Equations with Multiple Choices for Seed Low-Cost Particle Sensing Devices in Sensor Networks.

To tackle the challenge of the data accuracy issues of low-cost sensors (LCSs), the objective of this work was to obtain robust correction equations to convert LCS signals into data comparable to that of research-grade instruments using side-by-side comparisons. Limited sets of seed LCS devices, after laboratory evaluations, can be installed strategically in areas of interest without official monitoring stations to enable reading adjustments of other uncalibrated LCS devices to enhance the data quality of sensor networks. The robustness of these equations for LCS devices (AS-LUNG with PMS3003 sensor) under a hood and a chamber with two different burnt materials and before and after 1.5 years of field campaigns were evaluated. Correction equations with incense or mosquito coils burning inside a chamber with segmented regressions had a high R2 of 0.999, less than 6.0% variability in the slopes, and a mean RMSE of 1.18 µg/m3 for 0.1-200 µg/m3 of PM2.5, with a slightly higher RMSE for 0.1-400 µg/m3 compared to EDM-180. Similar results were obtained for PM1, with an upper limit of 200 µg/m3. Sensor signals drifted 19-24% after 1.5 years in the field. Practical recommendations are given to obtain equations for Federal-Equivalent-Method-comparable measurements considering variability and cost.

Fusion of Environmental Sensing on PM2.5 and Deep Learning on Vehicle Detecting for Acquiring Roadside PM2.5 Concentration Increments.

Traffic emission is one of the major contributors to urban PM2.5, an important environmental health hazard. Estimating roadside PM2.5 concentration increments (above background levels) due to vehicles would assist in understanding pedestrians' actual exposures. This work combines PM2.5 sensing and vehicle detecting to acquire roadside PM2.5 concentration increments due to vehicles. An automatic traffic analysis system (YOLOv3-tiny-3l) was applied to simultaneously detect and track vehicles with deep learning and traditional optical flow techniques, respectively, from governmental cameras that have low resolutions of only 352 × 240 pixels. Evaluation with 20% of the 2439 manually labeled images from 23 cameras showed that this system has 87% and 84% of the precision and recall rates, respectively, for five types of vehicles, namely, sedan, motorcycle, bus, truck, and trailer. By fusing the research-grade observations from PM2.5 sensors installed at two roadside locations with vehicle counts from the nearby governmental cameras analyzed by YOLOv3-tiny-3l, roadside PM2.5 concentration increments due to on-road sedans were estimated to be 0.0027-0.0050 µg/m3. This practical and low-cost method can be further applied in other countries to assess the impacts of vehicles on roadside PM2.5 concentrations.

New approach to identifying proper thresholds for a heat warning system using health risk increments.

BACKGROUND: A critical adaptation strategy for reducing heat-related health risk under climate change is to establish a heat warning system with a proper threshold that requires evaluation of heat-health relationships using empirical data. OBJECTIVES: This work presents a new approach to selecting proper health-based thresholds for a heat warning system which are different from thresholds of heat-health relationship. METHODS: The proposed approach examined heat-health relationships through analyzing 15 years of health records with a modified generalized additive model (GAM), compared risk ratio increments (RRIs) of threshold candidates against a reference, assessed frequency of days above these candidates, and presented results graphically for easy communication. The candidate with the maximum RRI and proper occurring frequency is potentially the best threshold. Three heat indicators, including wet-bulb globe temperature (WBGT), temperature (T), and apparent temperature (AT), as well as three health outcomes, including all-cause mortality, heat-related hospital admissions, and heat-related emergency visits were evaluated. RESULTS: Risk ratios for all three health outcomes showed a consistent rising trend with increasing threshold candidates for all three heat indicators among different age and gender groups. WBGT had the most obvious increasing trend of RRIs with the three health outcomes. The maximum RRI was observed in heat-related emergency visits (242%), followed by heat-related hospital admissions (73%), and all-cause mortality (9%). The RRIs assessed for the three health outcomes pointed to the same thresholds, 33.0 °C, 34.0 °C, and 37.5 °C for WBGT, T, and AT, respectively. The number of days above these thresholds and for warning to be issued ranged between 0 and 7 days during 2000-2014. DISCUSSION: This study demonstrated a new approach to determining heat-warning thresholds with different heat indicators and health outcomes. The proposed approach provides a straightforward, feasible, and flexible scientific tool that assists the authorities around the world in selecting a proper threshold for a heat warning system.

"What We Breathe Impacts Our Health: Improving Understanding of the Link between Air Pollution and Health".

Air pollution contributes to the premature deaths of millions of people each year around the world, and air quality problems are growing in many developing nations. While past policy efforts have succeeded in reducing particulate matter and trace gases in North America and Europe, adverse health effects are found at even these lower levels of air pollution. Future policy actions will benefit from improved understanding of the interactions and health effects of different chemical species and source categories. Achieving this new understanding requires air pollution scientists and engineers to work increasingly closely with health scientists. In particular, research is needed to better understand the chemical and physical properties of complex air pollutant mixtures, and to use new observations provided by satellites, advanced in situ measurement techniques, and distributed micro monitoring networks, coupled with models, to better characterize air pollution exposure for epidemiological and toxicological research, and to better quantify the effects of specific source sectors and mitigation strategies.

Peaks, sources, and immediate health impacts of PM2.5 and PM1 exposure in Indonesia and Taiwan with microsensors.

BACKGROUND: Microsensors have been used for the high-resolution particulate matter (PM) monitoring. OBJECTIVES: This study applies PM and health microsensors with the objective of assessing the peak exposure, sources, and immediate health impacts of PM2.5 and PM1 in two Asian countries. METHODS: Exposure assessment and health evaluation were carried out for 50 subjects in 2018 and 2019 in Bandung, Indonesia and for 55 subjects in 2019 and 2020 in Kaohsiung, Taiwan. Calibrated AS-LUNG sets and medical-certified RootiRx® sensors were used to assess PM and heart-rate variability (HRV), respectively. RESULTS: Overall, the 5-min mean exposure of PM2.5 and PM1 was 30.4 ± 20.0 and 27.0 ± 15.7 µg/m3 in Indonesia and 14.9 ± 11.2 and 13.9 ± 9.8 µg/m3 in Taiwan, respectively. The maximum 5-min peak PM2.5 and PM1 exposures were 473.6 and 154.0 µg/m3 in Indonesia and 467.4 and 217.7 µg/m3 in Taiwan, respectively. Community factories and mosquito coil burning are the two most important exposure sources, resulting in, on average, 4.73 and 5.82 µg/m3 higher PM2.5 exposure increments for Indonesian subjects and 10.1 and 9.82 µg/m3 higher PM2.5 exposure for Taiwanese subjects compared to non-exposure periods, respectively. Moreover, agricultural waste burning and incense burning were another two important exposure sources, but only in Taiwan. Furthermore, 5-min PM2.5 and PM1 exposure had statistically significantly immediate impacts on the HRV indices and heart rates of all subjects in Taiwan and the scooter subjects in Indonesia with generalized additive mixed models. The HRV change for a 10 µg/m3 increase in PM2.5 and PM1 ranged from -0.9% to -2.5% except for ratio of low-high frequency, with greater impacts associated with PM1 than PM2.5 in both countries. IMPACT STATEMENT: This work highlights the ability of microsensors to capture high peaks of PM2.5 and PM1, to identify exposure sources through the integration of activity records, and to assess immediate changes in heart rate variability for a panel of approximately 50 subjects in Indonesia and Taiwan. This study stands out as one of the few to demonstrate the immediate health impacts of peak PM, complementing to the short-term (days or weeks) or long-term effects (months or longer) assessed in most epidemiological studies. The technology/methodology employed offer great potential for researchers in the resource-limited countries with high PM2.5 and PM1 levels.

What is the spatiotemporal pattern of benzene concentration spread over susceptible area surrounding the Hartman Park community, Houston, Texas?

The Hartman Park community in Houston, Texas-USA, is in a highly polluted area which poses significant risks to its predominantly Hispanic and lower-income residents. Surrounded by dense clustering of industrial facilities compounds health and safety hazards, exacerbating environmental and social inequalities. Such conditions emphasize the urgent need for environmental measures that focus on investigating ambient air quality. This study estimated benzene, one of the most reported pollutants in Hartman Park, using machine learning-based approaches. Benzene data was collected in residential areas in the neighborhood and analyzed using a combination of five machine-learning algorithms (i.e., XGBR, GBR, LGBMR, CBR, RFR) through a newly developed ensemble learning model. Evaluations on model robustness, overfitting tests, 10-fold cross-validation, internal and stratified validation were performed. We found that the ensemble model depicted about 98.7% spatial variability of benzene (Adj. R2 =0.987). Through rigorous validations, stability of model performance was confirmed. Several predictors that contribute to benzene were identified, including temperature, developed intensity areas, leaking petroleum storage tank, and traffic-related factors. Analyzing spatial patterns, we found high benzene spread over areas near industrial zones as well as in residential areas. Overall, our study area was exposed to high benzene levels and requires extra attention from relevant authorities.

Exploring interconnections: A comprehensive multi-country analysis of climate change, energy demand, long-term care, and health of older adults.

Challenges faced by many countries are energy insecurity, climate change, and the health and long-term care of growing numbers of older people. These challenges are increasingly intersecting with rising energy prices, aging populations, and an increased frequency and intensity of extreme climate events. This paper gives a deeper understanding of the current and predicted interconnections among these challenges through narrative-driven content and thematic analysis from workshops with a diverse group of international stakeholders from the Global North and Global South. Narratives emerged highlighting a complex nexus of interconnections and presenting critical action areas. Targeted local and global policies and interventions are needed to alleviate stress on health systems, encourage the integrated uptake of clean energy sources, and uphold social justice across all economies. Professionals can use this work to inform the design and implementation of effective interventions and increase the resilience of older adults by better preparing for systemic risks.

A machine learning-based ensemble model for estimating diurnal variations of nitrogen oxide concentrations in Taiwan.

Air pollution is inextricable from human activity patterns. This is especially true for nitrogen oxide (NOx), a pollutant that exists naturally and also as a result of anthropogenic factors. Assessing exposure by considering diurnal variation is a challenge that has not been widely studied. Incorporating 27 years of data, we attempted to estimate diurnal variations in NOx across Taiwan. We developed a machine learning-based ensemble model that integrated hybrid kriging-LUR, machine-learning, and an ensemble learning approach. Hybrid kriging-LUR was performed to select the most influential predictors, and machine-learning algorithms were applied to improve model performance. The three best machine-learning algorithms were suited and reassessed to develop ensemble learning that was designed to improve model performance. Our ensemble model resulted in estimates of daytime, nighttime, and daily NOx with high explanatory powers (Adj-R2) of 0.93, 0.98, and 0.94, respectively. These explanatory powers increased from the initial model that used only hybrid kriging-LUR. Additionally, the results depicted the temporal variation of NOx, with concentrations higher during the daytime than the nighttime. Regarding spatial variation, the highest NOx concentrations were identified in northern and western Taiwan. Model evaluations confirmed the reliability of the models. This study could serve as a reference for regional planning supporting emission control for environmental and human health.

In-depth analysis of ambient air pollution changes due to the COVID-19 pandemic in the Asian Monsoon region.

The COVID-19 pandemic has given a chance for researchers and policymakers all over the world to study the impact of lockdowns on air quality in each country. This review aims to investigate the impact of the restriction of activities during the lockdowns in the Asian Monsoon region on the main criteria air pollutants. The various types of lockdowns implemented in each country were based on the severity of the COVID-19 pandemic. The concentrations of major air pollutants, especially particulate matter (PM) and nitrogen dioxide (NO2), reduced significantly in all countries, especially in South Asia (India and Bangladesh), during periods of full lockdown. There were also indications of a significant reduction of sulfur dioxide (SO2) and carbon monoxide (CO). At the same time, there were indications of increasing trends in surface ozone (O3), presumably due to nonlinear chemistry associated with the reduction of oxides of nitrogens (NOX). The reduction in the concentration of air pollutants can also be seen in satellite images. The results of aerosol optical depth (AOD) values followed the PM concentrations in many cities. A significant reduction of NO2 was recorded by satellite images in almost all cities in the Asian Monsoon region. The major reductions in air pollutants were associated with reductions in mobility. Pakistan, Bangladesh, Myanmar, Vietnam, and Taiwan had comparatively positive gross domestic product growth indices in comparison to other Asian Monsoon nations during the COVID-19 pandemic. A positive outcome suggests that the economy of these nations, particularly in terms of industrial activity, persisted during the COVID-19 pandemic. Overall, the lockdowns implemented during COVID-19 suggest that air quality in the Asian Monsoon region can be improved by the reduction of emissions, especially those due to mobility as an indicator of traffic in major cities.

Impact of physical and social living environments on pro-environmental intentions.

The living environment might play an important role in shaping the pro-environmental intentions of the people. However, there was limited research on how the living environments influenced the pro-environmental intentions of people. The objectives of this study are to evaluate the direct effects of physical and social environments on pro-environmental intentions as well as the mediating effects of environmental attitudes and life satisfaction. Structural Equation Modeling was used with data extracted from the 2020 Taiwan Social Change Survey database (n = 1671). Results showed direct positive associations of both physical and social environments with pro-environmental intentions (ß = 0.133 and ß = 0.076, respectively) as well as indirect positive associations via the life satisfaction-mediating pathway (ß = 0.031 and ß = 0.044, respectively). The physical environment negatively influenced pro-environmental intentions through the environmental attitude pathway (ß = - 0.255) with unpleasant neighborhood enhancing the pro-environmental intentions of residents. Taken together, the overall effect of the physical environment was negative (ß = - 0.093) while that of the social environment was positive (ß = 0.109). The most important factors for the physical and social environments were disturbance and livability in north, central and south Taiwan, neighborhood pollution and interestingness in east Taiwan. Accordingly, minimizing disturbance and neighborhood pollution of the physical environment could have the highest effect on pro-environmental intentions enhancement in western and eastern Taiwan, respectively. For the social environment, improving livability in the west and interestingness in the east would have an even larger impact on pro-environmental intentions. This study emphasized the importance of neighborhood environment on the environmental intentions of the people. The study also identified the important factors for policymakers to target to achieve the best effect on improving environmental intentions.

An ensemble mixed spatial model in estimating long-term and diurnal variations of PM2.5 in Taiwan.

Meteorology, human activities, and other emission sources drive diurnal cyclic patterns of air pollution. Previous studies mainly focused on the variation of PM2.5 concentrations during daytime rather than nighttime. In addition, assessing the spatial variations of PM2.5 in large areas is a critical issue for environmental epidemiological studies to clarify the health effects from PM2.5 exposures. In terms of air pollution spatial modelling, using only a single model might lose information in capturing spatial and temporal correlation between predictors and pollutant levels. Hence, this study aimed to propose an ensemble mixed spatial model that incorporated Kriging interpolation, land-use regression (LUR), machine learning, and stacking ensemble approach to estimate long-term PM2.5 variations for nearly three decades in daytime and nighttime. Three steps of model development were applied: 1) linear based LUR and Hybrid Kriging-LUR were used to determine influential predictors; 2) machine learning algorithms were used to enhance model prediction accuracy; 3) predictions from the selected machine learning models were fitted and evaluated again to build the final ensemble mixed spatial model. The results showed that prediction performance increased from 0.514 to 0.895 for daily, 0.478 to 0.879 for daytime, and 0.523 to 0.878 for nighttime when applying the proposed ensemble mixed spatial model compared with LUR. Results of overfitting test and extrapolation ability test confirmed the robustness and reliability of the developed models. The distance to the nearest thermal power plant, density of soil and pebbles fields, and funeral facilities might affect the variation of PM2.5 levels between daytime and nighttime. The PM2.5 level was higher in daytime compared with nighttime with little difference, revealing the importance of estimating nighttime PM2.5 variations. Our findings also clarified the emission sources in daytime and nighttime, which serve as valuable information for air pollution control strategies establishment.

A pilot heat-health warning system co-designed for a subtropical city.

Significant heat-related casualties underlie the urgency of establishing a heat-health warning system (HHWS). This paper presents an evidence-based pilot HHWS developed for Taipei City, Taiwan, through a co-design process engaging stakeholders. In the co-design process, policy concerns related to biometeorology, epidemiology and public health, and risk communication aspects were identified, with knowledge gaps being filled by subsequent findings. The biometeorological results revealed that Taipei residents were exposed to wet-bulb globe temperature (WBGT) levels of health concern for at least 100 days in 2016. The hot spots and periods identified using WBGT would be missed out if using temperature, underlining the importance of adopting an appropriate heat indicator. Significant increases in heat-related emergency were found in Taipei at WBGT exceeding 36°C with reference-adjusted risk ratio (RaRR) of 2.42, taking 30°C as the reference; and residents aged 0-14 had the highest risk enhancement (RaRR = 7.70). As for risk communication, occurring frequency was evaluated to avoid too frequent warnings, which would numb the public and exhaust resources. After integrating knowledge and reconciling the different preferences and perspectives, the pilot HHWS was co-implemented in 2018 by the science team and Taipei City officials; accompanying responsive measures were formulated for execution by ten city government departments/offices. The results of this pilot served as a useful reference for establishing a nationwide heat-alert app in 2021/2022. The lessons learnt during the interactive co-design processes provide valuable insights for establishing HHWSs worldwide.

Evaluating long-term and high spatiotemporal resolution of wet-bulb globe temperature through land-use based machine learning model.

BACKGROUND: The increase in global temperature and urban warming has led to the exacerbation of heatwaves, which negatively affect human health and cause long-term loss of work productivity. Therefore, a global assessment in temperature variation is essential. OBJECTIVE: This paper is the first of its kind to propose land-use based spatial machine learning (LBSM) models for predicting highly spatial-temporal variations of wet-bulb globe temperature (WBGT), which is a heat stress indicator used to assess thermal comfort in indoor and outdoor environments, specifically for the main island of Taiwan. METHODS: To develop spatiotemporal prediction models for both the working period and noon period, we calculated the WBGT of each weather station from 2001 to 2019 using temperature, humidity, and solar radiation data. These WBGT estimations were then used as the dependent variable for developing the spatiotemporal prediction models. To enhance model performance, we used innovative approaches that combined SHapley Additive exPlanations (SHAP) values for the selection of non-linear variables, along with machine learning algorithms for model development. RESULTS: When incorporating temperature along with other land-use/land cover predictor variables, the performance of LBSM models was excellent, with an R2 value of up to 0.99. The LBSM models explained 98% and 99% of the spatial-temporal variations in WBGT for the working and noon periods, respectively, within the complete models. In the temperature-excluded models, the explained variances were 94% and 96% for the working and noon periods, respectively. IMPACT: WBGT is a common method used by many organizations to access the impact of heat stress on human beings. However, limited studies have mentioned the association between WBGT and health impacts due to the absence of spatiotemporal databases. This study develops a new approach using land-use-based spatial machine learning (LBSM) models to better predict the fine spatial-temporal WBGT levels, with a 50-m × 50-m grid resolution for both working time and noontime. Our proposed methodology could be used in future studies aimed at evaluating the potential long-term loss of work productivity due to the effects of global warming or urban heat island.

Model development and validation of personal exposure to PM2.5 among urban elders.

Indirect measurements through a combination of microenvironment concentrations and personal activity diaries provide a potentially useful alternative for PM2.5 exposure estimates. This study was to optimize a personal exposure model based on spatiotemporal model predictions for PM2.5 exposure in a sub-cohort study. Personal, home indoor, home outdoor, and ambient monitoring data of PM2.5 were conducted for an elderly population in the Taipei city of Taiwan. The proposed microenvironment exposure (ME) models incorporate PM2.5 measurements and individual time-activity information with a generalized estimating equation (GEE) analysis. We evaluated model performance with daily personal PM2.5 exposure based on the coefficient of determination, accuracy, and mean bias error. Ambient and home outdoor measures as exposure surrogates are likely to under- and overestimate personal exposure to PM2.5 in our study population, respectively. Measured and predicted indoor exposures were highly correlated with personal PM2.5 exposure. The awareness of peculiar smells is an important factor that significantly increases personal PM2.5 exposure by 46-70%. The model incorporating home indoor PM2.5 can achieve the highest agreement (R2 = 0.790) with personal exposure and the lowest measurement error. The ME model with the GEE analysis combining home outdoor PM2.5 determined by LUR model with a machine learning technique can improve the prediction (R2 = 0.592) of personal PM2.5 exposure, compared with the prediction of the traditional LUR model (R2 = 0.385).

Greenspace related to bipolar disorder in Taiwan: Quantitative benefits of saving DALY loss and increasing income.

Scientific evidence reported that surrounding greenspace could promote better mental health. Considering bipolar disorder as the health outcome, this study aimed to investigate the association between greenspace and bipolar disorder in Taiwan and quantified the benefits of greenspace on bipolar disorder adjusted for the international greenspace availability standard. By examining datasets across 348 townships, two quantitative measures (i.e., disability-adjusted life year loss and income) were used to represent the benefits. The incidence rate of bipolar disorder was obtained from Taiwan's National Health Insurance Research Database. Normalized different vegetation index (NDVI) was measured as a proxy for the greenspace availability. A generalized additive mixed model coupled with a sensitivity test were applied to evaluate the statistical association. The prevented fraction for the population (PFP) was then applied to develop a scenario for quantifying benefit. The result showed a significant negative association between greenspace and bipolar disorder in Taiwan. Compared to low greenspace, areas with medium and high greenspace may reduce the bipolar risk by 21% (RR = 0.79; 95% CI = 0.76-0.83) and 51% (RR = 0.49; 95% CI = 0.45-0.53). Calculating benefits, we found that the development of a scenario by increasing greenspace adjusted for availability indicator in township categorized as low greenspace could save in DALY loss due to bipolar disorder up to10.97% and increase in income up to 11.04% from the current situation. Lastly, this was the first study in Asia-Pacific to apply a customized greenspace increment scenario to quantify the benefits to a particular health burden such as bipolar disorder.

A Geo-AI-based ensemble mixed spatial prediction model with fine spatial-temporal resolution for estimating daytime/nighttime/daily average ozone concentrations variations in Taiwan.

High levels of ground level ozone (O3) are associated with detrimental health concerns. Most of the studies only focused on daily average and daytime trends due to the presence of sunlight that initiates its formation. However, atmospheric chemical reactions occur all day, thus, nighttime concentrations should be given equal importance. In this study, geospatial-artificial intelligence (Geo-AI) which combined kriging, land use regression (LUR), machine learning, an ensemble learning, was applied to develop ensemble mixed spatial models (EMSMs) for daily, daytime, and nighttime periods. These models were used to estimate the long-term O3 spatio-temporal variations using a two-decade worth of in-situ measurements, meteorological parameters, geospatial predictors, and social and season-dependent factors. From the traditional LUR approach, the performance of EMSMs improved by 60% (daytime), 49% (nighttime), and 57% (daily). The resulting daily, daytime, and nighttime EMSMs had a high explanatory power with and adjusted R2 of 0.91, 0.91, and 0.88, respectively. Estimation maps were produced to examine the changes before and during the implementation of nationwide COVID-19 restrictions. These results provide accurate estimates and its diurnal variation that will support pollution control measure and epidemiological studies.