The urban agglomeration of Yangtze River Delta (YRD) is emblematic of China's rapid urbanization during the past decades. Based on homogenized daily maximum and minimum temperature data, the contributions of urbanization to trends of summer extreme temperature indices (ETIs) in YRD are evaluated. Dynamically classifying the observational stations into urban and rural, this study presents unexplored changes in temperature extremes during the past four decades in YRD and quantifies the amplification of the positive trends in ETIs by the urban heat island effect. Overall, urbanization contributes to more than one third of the increase of intensity of extreme heat events in the region, which is comparable to the contribution of greenhouse gases. Compared to rural stations, more notable shifts to the right in the probability distribution of temperature and ETIs are found in urban stations. The rapid urbanization in YRD has resulted in large increases in the risk of heat extremes.

The robust estimate and forecast capability of random forests (RF) has been widely recognized, however this ensemble machine learning method has not been widely used in mosquito-borne disease forecasting. In this study, two sets of RF models were developed at the national (pooled department-level data) and department level in Colombia to predict weekly dengue cases for 12-weeks ahead. A pooled national model based on artificial neural networks (ANN) was also developed and used as a comparator to the RF models. The various predictors included historic dengue cases, satellite-derived estimates for vegetation, precipitation, and air temperature, as well as population counts, income inequality, and education. Our RF model trained on the pooled national data was more accurate for department-specific weekly dengue cases estimation compared to a local model trained only on the department’s data. Additionally, the forecast errors of the national RF model were smaller to those of the national pooled ANN model and were increased with the forecast horizon increasing from one-week-ahead (mean absolute error, MAE: 9.32) to 12-weeks ahead (MAE: 24.56). There was considerable variation in the relative importance of predictors dependent on forecast horizon. The environmental and meteorological predictors were relatively important for short-term dengue forecast horizons while socio-demographic predictors were relevant for longer-term forecast horizons. This study demonstrates the potential of RF in dengue forecasting with a feasible approach of using a national pooled model to forecast at finer spatial scales. Furthermore, including sociodemographic predictors is likely to be helpful in capturing longer-term dengue trends. Dengue virus has the highest disease burden of all mosquito-borne viral diseases, infecting 390 million people annually in 128 countries. Forecasting is an important warning mechanism that can help with proactive planning and response for clinical and public health services. In this study, we compare two different machine learning approaches to dengue forecasting: random forest (RF) and artificial neural networks (ANN). National (pooling across all departments) and local (department-specific) models were compared and used to predict future dengue cases in Colombia. In Colombia, the departments are administrative divisions formed by a grouping of municipalities. The results demonstrated that the counts of future dengue cases were more accurately estimated by RF than by ANN. It was also shown that environmental and meteorological predictors were more important for forecast accuracy for shorter-term forecasts while socio-demographic predictors were more important for longer-term forecasts. Finally, the national pooled model applied to local data was more accurate in dengue forecasting compared to the department-specific model. This research contributes to the field of disease forecasting and highlights different considerations for future forecasting studies.

There is increasing interest in the health effects of air pollution. However, the relationships between ozone exposure and mortality attributable to neurological diseases remain unclear. To assess associations of long-term exposure to ozone with death from Parkinson's disease, dementia, stroke, and multiple sclerosis. Our analyses were based on the 2001 Canadian Census Health and Environment Cohort. Census participants were linked with vital statistics records through 2016, resulting in a cohort of 3.5 million adults/51,045,700 person-years, with 8,500/51,300/43,300/1,300 deaths from Parkinson's/dementia/stroke/multiple sclerosis, respectively. Ten-year average ozone concentrations estimated by chemical transport models and adjusted by ground measurements were assigned to subjects based on postal codes. Cox proportional hazards models were used to calculate hazard ratios (HRs) for deaths from the four neurological diseases, adjusting for eight common demographic and socioeconomic factors, seven environmental indexes, and six contextual covariates. The fully adjusted HRs for Parkinson's, dementia, stroke, and multiple sclerosis mortalities related to one interquartile range increase in ozone (10.1 ppb), were 1.09 (95% confidence interval 1.04-1.14), 1.08 (1.06-1.10), 1.06 (1.04-1.09), and 1.35 (1.20-1.51), respectively. The covariates did not influence significance of the ozone-mortality associations, except airshed (i.e., broad region of Canada). During the period of 2001-2016, 5.66%/5.01%/ 3.77%/19.11% of deaths from Parkinson's/dementia/stroke/multiple sclerosis, respectively, were attributable to ozone exposure. We found positive associations between ozone exposure and mortality due to Parkinson's, dementia, stroke, and multiple sclerosis.

Fine-resolution population distribution mapping is necessary for many purposes, which cannot be met by aggregated census data due to privacy. Many approaches utilize ancillary data that are related to population density, such as nighttime light imagery and land use, to redistribute the population from census to finer-scale units. However, most of the ancillary data used in the previous studies of population modeling are environmental data, which can only provide a limited capacity to aid population redistribution. Social sensing data with geographic information, such as point-of-interest (POI), are emerging as a new type of ancillary data for urban studies. This study, as a nascent attempt, combined POI and multisensor remote sensing data into new ancillary data to aid population redistribution from census to grid cells at a resolution of 250 m in Zhejiang, China. The accuracy of the results was assessed by comparing them with WorldPop. Results showed that our approach redistributed the population with fewer errors than WorldPop, especially at the extremes of population density. The approach developed in this study—incorporating POI with multisensor remotely sensed data in redistributing the population onto finer-scale spatial units—possessed considerable potential in the era of big data, where a substantial volume of social sensing data is increasingly being collected and becoming available.

Background: Exposure to ambient fine particulate matter with an aerodynamic diameter <2.5 μg·m⁻³(PM_2.5) is a risk factor for pulmonary and systemic autoimmune diseases; however, evidence on which PM_2.5chemical components are more harmful is still scant. Our goal is to investigate potential associations between major PM_2.5components and interstitial lung disease (ILD) onset in rheumatoid arthritis (RA).Methods: New-onset RA subjects identified from a US healthcare insurance database (MarketScan) were followed for new onset of RA-associated ILD (RA-ILD) from 2011 to 2018. Annual concentrations of ambient PM_2.5chemical components (i.e.sulfate, nitrate, ammonium, organic matter, black carbon, mineral dust and sea salt) were estimated by combining satellite retrievals with chemical transport modelling and refined by geographically weighted regression. Exposures from 2006 up to 1 year before ILD onset or end of study were assigned to subjects based on their core-based statistical area or metropolitan division codes. A novel time-to-event quantile-based g (generalised)-computation approach was used to estimate potential associations between RA-ILD onset and the exposure mixture of all seven PM_2.5chemical components adjusting for age, sex and prior chronic obstructive pulmonary disease (as a proxy for smoking).Results: We followed 280 516 new-onset RA patients and detected 2194 RA-ILD cases across 1 394 385 person-years. The adjusted hazard ratio for RA-ILD onset was 1.54 (95% CI 1.47–1.63) per every decile increase in all seven exposures. Ammonium, mineral dust and black carbon contributed more to ILD risk than the other PM_2.5components.Conclusion: Exposure to components of PM_2.5, particularly ammonium, increases ILD risk in RA.