Shisir Ruwali

We processed life expectancy data of an age group less than 1 years old from the Institute for Health Metrics and Evaluation (IHME) in the contiguous USA, as well as a set of 33 environmental variables (or features) from the European Center for Medium-Range Weather Forecasts (ECMWF) from the years 2003 through 2019. Visualizing the IHME data, we identified a massive disparity in life expectancy of the age group less than 1 years old in the contiguous USA, where counties in southern states have relatively lower life expectancies compared to counties in northern states. Our use of machine learning to estimate the life expectancy of the sub-1-year-old age group is moderately accurate, as the coefficient of determination (R²) and Root Mean Square Error (RMSE) between the true and estimated values was found to be 0.81 and 1.06 years, respectively, in an independent test set using only a set of five environmental variables. Our key finding shows that apart from well-known pollutants, such as particulate matter (PM), ozone, and carbon monoxide, a reduction in pollutants such as formaldehyde, sulphate aerosols, and dust aerosols; an increase in vegetation areas; and good environmental conditions, such as lower wet-bulb temperature, could potentially increase life expectancy in the US. Future work may include socio-economic variables such as household income, poverty rate, and other relevant features to create a comprehensive set of variables to improve the results and individuals’ quality of life.

Cardiovascular disease (CVD) is the leading cause of mortality in the United States, yet the role of atmospheric exposures as independent predictors of county-level CVD mortality remains poorly characterized. We integrated satellite-derived atmospheric data alongside socioeconomic, demographic, and livestock predictors across 24,487 county-year observations in the contiguous United States (2012–2019) and applied an XGBoost model with SHAP-based interpretability to identify the leading predictors of county-level CVD mortality (Test R² = 0.706, RMSE = 29.55 per 100,000 persons). Four of the top ten predictors came from CAMS/ERA5. Ambient formaldehyde exposure frequency ranked second among all 43 predictors, exceeded only by educational attainment and surpassing poverty rate. Wet-bulb temperature ranked third, Leaf Area Index for High Vegetation ranked seventh, and sulphate aerosol mixing ratio ranked eighth. These variables added county-level prediction information beyond socioeconomic covariates. Integrating atmospheric exposure monitoring into county-level CVD surveillance alongside socioeconomic indicators may improve the identification of high-risk geographies.

Satellite-derived environmental features can predict county-level life expectancy (LE) across the contiguous United States with a mean absolute error of 1.08 years over two decades, without using any census or sociodemographic inputs. We assembled 61,680 county-year observations across 3,084 counties from 2000–2019, integrating features from 11 satellite and gridded data streams. The data streams include the Moderate Resolution Imaging Spectroradiometer (MODIS) land surface temperature and vegetation indices, Sentinel-1 synthetic aperture radar, Sentinel-2 and Landsat optical imagery, the United States Department of Agriculture (USDA) Cropland Data Layer, the European Commission Joint Research Centre (JRC) Global Surface Water layer, the Copernicus Digital Elevation Model, the European Space Agency Climate Change Initiative (ESA CCI) soil moisture record, and the Food and Agriculture Organization (FAO) gridded livestock densities. After a supervised pruning step that removed low-importance variables, a Random Forest regressor was trained and evaluated using 5-fold cross-validation grouped by county. The grouping places all 20 years of each county exclusively in either the training set or the test set, which prevents spatial information leakage between folds. Coefficient of determination, mean absolute error, and root mean squared error are reported as R² = 0.631 ± 0.013, MAE = 1.08 ± 0.02 years, and RMSE = 1.48 ± 0.04 years. Moran's I, a measure of residual spatial autocorrelation, is 0.0988 (p = 0.001), which supports geographic generalisation. Multimodal fusion reduces unexplained variance by approximately one-third relative to the strongest single-modality baseline (MODIS land surface temperature alone, R² = 0.442). TreeSHAP attribution analysis reveals a feature hierarchy in which nighttime land surface temperature features carry roughly 6.16× the cumulative attribution weight of all daytime channels combined. The model response shows a protective inflection near a minimum overnight temperature of about 7.5°C. Because all input streams are globally available, the framework is extensible to regions where civil registration and vital statistics systems are incomplete, and supports satellite-based monitoring of United Nations Sustainable Development Goal (UN SDG) Target 3.9.

Life expectancy in the United States varies significantly by region, a gap often explained by socioeconomic factors like income and education. However, the relative contribution of atmospheric exposures is less understood. We identify formaldehyde exposure and wet-bulb temperature as leading predictors of county-level life expectancy. Our analysis of 22,540 county-year observations (2012–2019) shows that formaldehyde ranked as the second-strongest predictor, surpassed only by educational attainment. Wet-bulb temperature, a physiological measure of heat stress, ranked sixth and was the leading meteorological predictor. We identified these patterns using XGBoost with SHAP analysis, integrating atmospheric exposures, livestock density, socioeconomic conditions, and smoking prevalence within an external exposome framework. These results suggest that air pollutants and heat stress provide predictive information beyond traditional socioeconomic indicators.

We processed the life expectancy data of age group less than 1 year old from the Institute for Health Metrics and Evaluation (IHME) in contiguous USA and a set of 33 environmental variables (or features ) from the European Centre for Medium-Range Forecasts (ECMWF) from the years 2003 through 2019. Visualizing the IHME data we identified the massive disparity in life expectancy in contiguous USA where counties in southern states have relatively less life expectancy compared to counties in northern states. We made use of machine learning to estimate the life expectancy and obtained moderate accuracy as coefficient of determination (R2) and Root Mean Square Error (RMSE) between the true and estimated values were found to be 0.77 and 1.18 year respectively in an independent test set using only a set of 5 environmental variables. Our key finding shows that apart from well-known pollutants such as particulate matter (PM), ozone, carbonmonoxide, it is essential to reduce pollutants such as formaldehyde, sulphate aerosols, dust aerosols; increase vegetation areas, and good working condition such as lower wet-bulb temperature can potentially increase life expectancy in the US. Future work can include socio-economic variables such as household income, poverty rate and other relevant features to create a comprehensive set of variables to improve the results and livelihood of people.

Life expectancy in the United States varies significantly by region, a gap often explained by socioeconomic factors like income and education. However, the relative contribution of atmospheric exposures is less understood. We identify formaldehyde exposure and wet-bulb temperature as leading predictors of county-level life expectancy. Our analysis of over 24,000 county-year observations (2012–2019) reveals that formaldehyde consistently ranks as the second-strongest predictor of life expectancy, surpassed only by educational attainment. Wet-bulb temperature, a physiological measure of heat stress, emerges as a top-five predictor. We identified these patterns using XGBoost with SHAP analysis, integrating atmospheric, livestock, and socioeconomic data within an external exposome framework. These results suggest that air pollutants and heat stress capture health-relevant information beyond traditional socioeconomic indicators.

Cardiovascular disease (CVD) is the leading cause of mortality in the United States, yet the role of atmospheric exposures as independent predictors of county-level CVD mortality remains poorly characterized. We integrated satellite-derived atmospheric data alongside socioeconomic, demographic, and livestock predictors across 24,487 county-year observations in the contiguous United States (2012–2019) and applied an XGBoost model with SHAP-based interpretability to identify the leading predictors of county-level CVD mortality (Test R² = 0.712, RMSE = 29.26 per 100,000). Three of the top ten predictors were atmospheric variables. Ambient formaldehyde exposure frequency ranked second among all 43 predictors, exceeded only by educational attainment and surpassing poverty rate. Wet-bulb temperature, which captures the combined physiological burden of heat and humidity, ranked third. Sulphate aerosol mixing ratio ranked seventh. These atmospheric predictors contributed independently of socioeconomic covariates, indicating that atmospheric exposure carries information about county-level CVD mortality risk not captured by income or education alone. Integrating atmospheric exposure monitoring into county-level CVD surveillance alongside socioeconomic indicators may improve the identification of high-risk geographies.

The air we breathe consists of contaminants such as particulate matter (PM), carbon dioxide (CO2), nitrogen dioxide (NO2), nitric oxide (NO) which when inhaled brings about several changes in the autonomous responses of our body. Our previous work showed that we can use the human body as a sensor by making use of autonomous responses (or biometrics) such as changes in electrical activity in the brain measured using electroencephalogram (EEG) and physiological changes such as skin temperature, Galvanic Skin Response (GSR), blood oxygen saturation (SpO2) and few others can be used to estimate pollutants, in particular, PM1 and CO2 with high degree of accuracy using machine learning. In this study, we introduce a novel approach to obtain the power spectral density (PSD) from the timeseries of EEG developed by Astrapi called the Astrapi Spectrum Analyzer (ASA). The physiological responses of a participant cycling outdoors is measured using a biometric suite and ambient CO2, NO2 and NO is measured simultaneously. We made use of physiological responses and combined it with the PSD from an EEG timeseries using Welch Method (WM) and then with the PSD using ASA to estimate the inhaled concentration of CO2, NO2 and NO. This work shows that, indeed the PSD obtained from ASA combined with other physiological responses provides much better result (RMSE=9.28 ppm in an independent test set) in estimating inhaled CO2 compared to making use of the same physiological responses and PSD from WM (RMSE=17.55 ppm in an independent test set). Small improvements are also seen in the estimation of NO2 and NO when using physiological responses and PSD from ASA, which can be further confirmed by making use of large number of data collection.