Cross-validated R2 Research Articles

Physical habitat modeling for river macroinvertebrate communities

Habitat models rarely consider macroinvertebrate communities as ecological targets in rivers. Available approaches mainly focus on single macroinvertebrate species, not addressing the ecological needs and functionality of the whole community.This research aimed at providing an approach to model the habitat of the macroinvertebrate communities. The study was carried out in three rivers, located in Italy and characterized by a braiding morphology, gravel riverbeds, and low flows during the summer period. The approach is based on the recently developed Flow-T index, together with a Random Forest (RF) regression, which is employed to apply the Flow-T index at the mesohabitat scale. Using different datasets gathered from field data collection and 2D hydrodynamic simulations, the model was calibrated in the Trebbia River (2019 field campaign) and validated in the Trebbia, Taro, and Enza rivers (2020 field campaign).The RF model selected 12 mesohabitat descriptors as important for the macroinvertebrate community. These descriptors belong to different frequency classes of water depth, flow velocity, substrate grain size, and connectivity to the main river channel. The cross-validation R2 coefficient (R2cv) of the training dataset was 0.71, whereas the R2 coefficient (R2test) for the validation dataset was 0.63. The agreement between the simulated results and the experimental data shows sufficient accuracy and reliability. The outcomes of the study reveal that the model can identify the ecological response of the macroinvertebrate community to possible flow regime alterations and river morphological modifications.Lastly, the proposed approach allowed to extend the MesoHABSIM methodology, widely used for the fish habitat assessment, to a different ecological target community. Further applications of the approach can be related to ecological flows design in both perennial and non-perennial rivers, including river reaches in which fish fauna is absent.

Towards accurate spatial prediction of Glossina pallidipes relative densities at country-scale in Kenya

Vector-borne diseases, like those transmitted by tsetse flies, pose a significant global public health threat. Reducing vector populations is a promising strategy for disease control, especially in the case of tsetse-transmitted African trypanosomiasis. However, the cost-effective implementation of large-scale vector surveillance and control measures face challenges due to the lack of spatially explicit and reliable maps identifying vector hotspots. In this study, we assessed the accuracy of predicting Glossina pallidipes relative densities across Kenya by linking constrained in-situ tsetse catch data from 660 traps across three Kenyan regions with readily available gridded satellite information (human population, land cover, soil properties, elevation, precipitation, and land surface temperature) using a classical random forest algorithm. To enhance predictive performance, we employed two feature elimination techniques specifically designed for machine learning algorithms, i.e., Recursive Feature Elimination (RFE) and Variable Selection Using Random Forests (VSURF). For each set of retained variables, we trained a Random Forest model using a spatial cross-validation technique. Our findings showed that tsetse fly relative densities decreased with mean annual precipitation, and soil moisture, and conversely increased with higher tree cover. Based on the cross-validated R2, 41% of the spatial variability in relative densities of tsetse flies could be explained. For spatial extrapolation, only the set of predictors retained by VSURF closely matched known tsetse fly distributions in Kenya. This more accurate performance of VSURF may be attributed to its approach of assessing variables for both importance and their contribution to reducing prediction error. Our study demonstrates the potential of using a random forest method to upscale tsetse relative abundance predictions to the national level. However, the reliability of the current extrapolated map remains uncertain. We recommend: 1) increasing tsetse fly sampling efforts, particularly in the data-limited northern and eastern regions of Kenya, and 2) developing a more precise and accurate land cover map with classes that directly associate with known habitat characteristics of the target tsetse species.

Spatiotemporal Patterns of Air Pollutants over the Epidemic Course: A National Study in China

Air pollution has been standing as one of the most pressing global challenges. The changing patterns of air pollutants at different spatial and temporal scales have been substantially studied all over the world, which, however, were intricately disturbed by COVID-19 and subsequent containment measures. Understanding fine-scale changing patterns of air pollutants at different stages over the epidemic’s course is necessary for better identifying region-specific drivers of air pollution and preparing for environmental decision making during future epidemics. Taking China as an example, this study developed a multi-output LightGBM approach to estimate monthly concentrations of the six major air pollutants (i.e., PM2.5, PM10, NO2, SO2, O3, and CO) in China and revealed distinct spatiotemporal patterns for each pollutant over the epidemic’s course. The 5-year period of 2019–2023 was selected to observe changes in the concentrations of air pollutants from the pre-COVID-19 era to the lifting of all containment measures. The performance of our model, assessed by cross-validation R2, demonstrated high accuracy with values of 0.92 for PM2.5, 0.95 for PM10, 0.95 for O3, 0.90 for NO2, 0.79 for SO2, and 0.82 for CO. Notably, there was an improvement in the concentrations of particulate matter, particularly for PM2.5, although PM10 exhibited a rebound in northern regions. The concentrations of SO2 and CO consistently declined across the country over the epidemic’s course (p < 0.001 and p < 0.05, respectively), while O3 concentrations in southern regions experienced a notable increase. Concentrations of air pollutants in the Beijing–Tianjin–Hebei region were effectively controlled and mitigated. The findings of this study provide critical insights into changing trends of air quality during public health emergencies, help guide the development of targeted interventions, and inform policy making aimed at reducing disease burdens associated with air pollution.

Estimation of PM2.5 concentrations in North China with high spatiotemporal resolution using the ERA5 dataset and machine learning models

Previous studies have predominantly focused on developing high spatiotemporal resolution PM2.5 models utilizing moderate-resolution imaging spectroradiometer (MODIS) aerosol optical depth (AOD) products alongside certain meteorological factors. However, MODIS AOD is not continuous, and there is a problem of missing data, which is not conducive to the study of PM2.5 in areas without AOD. This study proposes a new method for estimating PM2.5 concentration in North China, which not only simplifies the complex process associated with the use of AOD, but also partially solves the issue of missing AOD data. This study proposes a machine learning (random forest, RF; back propagation neural network, BPNN) based method for estimating PM2.5 using meteorological parameters obtained from the fifth-generation reanalysis (ERA5) dataset released by the European Centre for Medium-Range Weather Forecasts and considering the effects of land cover type, digital elevation model, vegetation index and population data. The model performed well, with 10-fold cross-validation (coefficient of determination) R2 and (root-mean-square error) RMSE of 0.79/0.95 and 26.10/13.22 µg/m3, respectively, for BPNN and RF. The estimated hourly performance of the RF model in winter (00:00 to 23:00 BST) with an R2 ranging from 0.92 to 0.96, an RMSE of 11.45 to 16.70 µg/m3. RF model with the best performance and ERA5 were selected to build a high-resolution (0.25°×0.25°) hourly PM2.5 map (PMM), and the PMM was compared with CHAP, with R2 and RMSE of 0.75 and 20.62 µg/m3, respectively. This study further investigates the impacts of land cover types, digital elevation model, and land surface characteristics on the spatial distribution of PM2.5 in North China.

Revisiting methotrexate and phototrexate Zinc15 library-based derivatives using deep learning in-silico drug design approach.

Introduction: Cancer is the second most prevalent cause of mortality in the world, despite the availability of several medications for cancer treatment. Therefore, the cancer research community emphasized on computational techniques to speed up the discovery of novel anticancer drugs. Methods: In the current study, QSAR-based virtual screening was performed on the Zinc15 compound library (271 derivatives of methotrexate (MTX) and phototrexate (PTX)) to predict their inhibitory activity against dihydrofolate reductase (DHFR), a potential anticancer drug target. The deep learning-based ADMET parameters were employed to generate a 2D QSAR model using the multiple linear regression (MPL) methods with Leave-one-out cross-validated (LOO-CV) Q2 and correlation coefficient R2 values as high as 0.77 and 0.81, respectively. Results: From the QSAR model and virtual screening analysis, the top hits (09, 27, 41, 68, 74, 85, 99, 180) exhibited pIC50 ranging from 5.85 to 7.20 with a minimum binding score of -11.6 to -11.0 kcal/mol and were subjected to further investigation. The ADMET attributes using the message-passing neural network (MPNN) model demonstrated the potential of selected hits as an oral medication based on lipophilic profile Log P (0.19-2.69) and bioavailability (76.30% to 78.46%). The clinical toxicity score was 31.24% to 35.30%, with the least toxicity score (8.30%) observed with compound 180. The DFT calculations were carried out to determine the stability, physicochemical parameters and chemical reactivity of selected compounds. The docking results were further validated by 100ns molecular dynamic simulation analysis. Conclusion: The promising lead compounds found endorsed compared to standard reference drugs MTX and PTX that are best for anticancer activity and can lead to novel therapies after experimental validations. Furthermore, it is suggested to unveil the inhibitory potential of identified hits via in-vitro and in-vivo approaches.

The association between DNA methylation and human height and a prospective model of DNA methylation-based height prediction.

As a vital anthropometric characteristic, human height information not only helps to understand overall developmental status and genetic risk factors, but is also important for forensic DNA phenotyping. We utilized linear regression analysis to test the association between each CpG probe and the height phenotype. Next, we designed a methylation sequencing panel targeting 959 CpGs and subsequent height inference models were constructed for the Chinese population. A total of 11,730 height-associated sites were identified. By employing KPCA and deep neural networks, a prediction model was developed, of which the cross-validation RMSE, MAE and R2 were 5.62cm, 4.45cm and 0.64, respectively. Genetic factors could explain 39.4% of the methylation level variance of sites used in the height inference models. Collectively, we demonstrated an association between height and DNA methylation status through an EWAS analysis. Targeted methylation sequencing of only 959 CpGs combined with deep learning techniques could provide a model to estimate human height with higher accuracy than SNP-based prediction models.

Integrating traffic pollution dispersion into spatiotemporal NO2 prediction

Accurately predicting ambient NO2 concentrations has great public health importance, as traffic-related air pollution is of major concern in urban areas. In this study, we present a novel approach incorporating traffic contribution to NO2 prediction in a fine-scale spatiotemporal model. We used nationally available traffic estimate dataset in a scalable dispersion model, Research LINE source dispersion model (RLINE). RLINE estimates then served as an additional input for a validated spatiotemporal pollution modeling approach. Our analysis uses measurement data collected by the Multi-Ethnic Study of Atherosclerosis and Air Pollution in the greater Los Angeles area between 2006 and 2009. We predicted road-type-specific annual average daily traffic (AADT) on road segments via national-level spatial regression models with nearest-neighbor Gaussian processes (spNNGP); the spNNGP models were trained based on over half a million point-level traffic volume measurements nationwide. AADT estimates on all highways were combined with meteorological data in RLINE models. We evaluated two strategies to integrate RLINE estimates into spatiotemporal NO2 models: 1) incorporating RLINE estimates as a space-only covariate and, 2) as a spatiotemporal covariate. The results showed that integrating the RLINE estimates as a space-only covariate improved overall cross-validation R2 from 0.83 to 0.84, and root mean squared error (RMSE) from 3.58 to 3.48 ppb. Incorporating the estimates as a spatiotemporal covariate resulted in similar model improvement. The improvement of our spatiotemporal model was more profound in roadside monitors alongside highways, with R2 increasing from 0.56 to 0.66 and RMSE decreasing from 3.52 to 3.11 ppb. The observed improvement indicates that the RLINE estimates enhanced the model's predictive capabilities for roadside NO2 concentration gradients even after considering a comprehensive list of geographic covariates including the distance to roads. Our proposed modeling framework can be generalized to improve high-resolution prediction of NO2 exposure – especially near major roads in the U.S.

Predicting Personal Exposure to PM2.5 Using Different Determinants and Machine Learning Algorithms in Two Megacities, China

The primary aim of this study is to explore the utility of machine learning algorithms for predicting personal PM2.5 exposures of elderly participants and to evaluate the effect of individual variables on model performance. Personal PM2.5 was measured on five consecutive days across seasons in 66 retired adults in Beijing (BJ) and Nanjing (NJ), China. The potential predictors were extracted from routine monitoring data (ambient PM2.5 concentrations and meteorological factors), basic questionnaires (personal and household characteristics), and time-activity diary (TAD). Prediction models were developed based on either traditional multiple linear regression (MLR) or five advanced machine learning methods. Our results revealed that personal PM2.5 exposures were well predicted by both MLR and machine learning models with predictors extracted from routine monitoring data, which was indicated by the high nested cross-validation (CV) R2 ranging from 0.76 to 0.88. The addition of predictors from either the questionnaire or TAD did not improve predictive accuracy for all algorithms. The ambient PM2.5 concentrations were the most important predictor. Overall, the random forest, support vector machine, and extreme gradient boosting algorithms outperformed the reference MLR method. Compared with the traditional MLR approach, the CV R2 of the RF model increased up to 7% (from 0.82±0.13 to 0.88±0.10), while the RMSE reduced up to 18% (from 19.8±5.4 to 16.3±4.5) in BJ.

Predicting protein retention in ion-exchange chromatography using an open source QSPR workflow.

Protein-based biopharmaceuticals require high purity before final formulation to ensure product safety, making process development time consuming. Implementation of computational approaches at the initial stages of process development offers a significant reduction in development efforts. By preselecting process conditions, experimental screening can be limited to only a subset. One such computational selection approach is the application of Quantitative Structure Property Relationship (QSPR) models that describe the properties exploited during purification. This work presents a novel open-source Python tool capable of extracting a range of features from protein 3D models on a local computer allowing total transparency of the calculations. As open-source tool, it also impacts initial investments in constructing a QSPR workflow for protein property prediction for third parties, making it widely applicable within the field of bioprocess development. The focus of current calculated molecular features is projection onto the protein surface by constructing surface grid representations. Linear regression models were trained with the calculated features to predict chromatographic retention times/volumes. Model validation shows a high accuracy for anion and cation exchange chromatography data (cross-validated R2 of 0.87 and 0.95). Hence, these models demonstrate the potential of the use of QSPR to accelerate process design.

Harnessing AI to unmask Copenhagen's invisible air pollutants: A study on three ultrafine particle metrics

Ultrafine particles (UFPs) are airborne particles with a diameter of less than 100 nm. They are emitted from various sources, such as traffic, combustion, and industrial processes, and can have adverse effects on human health. Long-term mean ambient average particle size (APS) in the UFP range varies over space within cities, with locations near UFP sources having typically smaller APS. Spatial models for lung deposited surface area (LDSA) within urban areas are limited and currently there is no model for APS in any European city. We collected particle number concentration (PNC), LDSA, and APS data over one-year monitoring campaign from May 2021 to May 2022 across 27 locations and estimated annual mean in Copenhagen, Denmark, and obtained additionally annual mean PNC data from 6 state-owned continuous monitors. We developed 94 predictor variables, and machine learning models (random forest and bagged tree) were developed for PNC, LDSA, and APS. The annual mean PNC, LDSA, and APS were, respectively, 5523 pt/cm3, 12.0 μm2/cm3, and 46.1 nm. The final R2 values by random forest (RF) model were 0.93 for PNC, 0.88 for LDSA, and 0.85 for APS. The 10-fold, repeated 10-times cross-validation R2 values were 0.65, 0.67, and 0.60 for PNC, LDSA, and APS, respectively. The root mean square error for final RF models were 296 pt/cm3, 0.48 μm2/cm3, and 1.60 nm for PNC, LDSA, and APS, respectively. Traffic-related variables, such as length of major roads within buffers 100–150 m and distance to streets with various speed limits were amongst the highly-ranked predictors for our models. Overall, our ML models achieved high R2 values and low errors, providing insights into UFP exposure in a European city where average PNC is quite low. These hyperlocal predictions can be used to study health effects of UFPs in the Danish Capital.

Application of near-infrared spectroscopy for hay evaluation at different degrees of sample preparation.

A study was conducted to quantify the performance differences of the nearinfrared spectroscopy (NIRS) calibration models developed with different degrees of hay sample preparations. A total of 227 imported alfalfa (Medicago sativa L.) and another 360 imported timothy (Phleum pratense L.) hay samples were used to develop calibration models for nutrient value parameters such as moisture, neutral detergent fiber, acid detergent fiber, crude protein, and in vitro dry matter digestibility. Spectral data of hay samples prepared by milling into 1-mm particle size or unground were separately regressed against the wet chemistry results of the abovementioned parameters. The performance of the developed NIRS calibration models was evaluated based on R2, standard error, and ratio percentage deviation (RPD). The models developed with ground hay were more robust and accurate than those with unground hay based on calibration model performance indexes such as R2 (coefficient of determination), standard error, and RPD. Although the R2 of calibration models was mainly greater than 0.90 across the feed value indexes, the R2 of cross-validations was much lower. The R2 of cross-validation varies depending on feed value indexes, which ranged from 0.61 to 0.81 in alfalfa, and from 0.62 to 0.95 in timothy. Estimation of feed values in imported hay can be achievable by the calibrated NIRS. However, the NIRS calibration models must be improved by including a broader range of imported hay samples in the modeling. Although the analysis accuracy of NIRS was substantially higher when calibration models were developed with ground samples, less sample preparation will be more advantageous for achieving rapid delivery of hay sample analysis results. Therefore, further research warrants investigating the level of sample preparations compromising analysis accuracy by NIRS.

MonteCat: A Basin-Hopping-Inspired Catalyst Descriptor Search Algorithm for Machine Learning Models.

Proposing relevant catalyst descriptors that can relate the information on a catalyst's composition to its actual performance is an ongoing area in catalyst informatics, as it is a necessary step to improve our understanding on the target reactions. Herein, a small descriptor-engineered data set containing 3289 descriptor variables and the performance of 200 catalysts for the oxidative coupling of methane (OCM) is analyzed, and a descriptor search algorithm based on the workflow of the Basin-hopping optimization methodology is proposed to select the descriptors that better fit a predictive model. The algorithm, which can be considered wrapper in nature, consists of the successive generation of random-based modifications to the descriptor subset used in a regression model and adopting them depending on their effect on the model's score. The results are presented after being tested on linear and Support Vector Regression models with average cross-validation r2 scores of 0.8268 and 0.6875, respectively.

Development of an integrated model framework for multi-air-pollutant exposure assessments in high-density cities

Abstract. Exposure models for some criteria of air pollutants have been intensively developed in past research; multi-air-pollutant exposure models, especially for particulate chemical species, have been however overlooked in Asia. Lack of an integrated model framework to calculate multi-air-pollutant exposure has hindered the combined exposure assessment and the corresponding health assessment. This work applied the land-use regression (LUR) approach to develop an integrated model framework to estimate 2017 annual-average exposure of multiple air pollutants in a typical high-rise and high-density Asian city (Hong Kong, China) including four criteria of gaseous air pollutants (particulate matter with an aerodynamic diameter equal to or less than 10 µm (PM10) and 2.5 µm (PM2.5), nitrogen dioxide (NO2), and ozone (O3)), as well as four major PM10 chemical species. Our integrated multi-air-pollutant exposure model framework is capable of explaining 91 %–97 % of the variability of measured gaseous air pollutant concentration, with the leave-one-out cross-validation R2 values ranging from 0.73 to 0.93. Using the model framework, the spatial distribution of the concentration of various air pollutants at a spatial resolution of 500 m was generated. The LUR model-derived spatial distribution maps revealed weak-to-moderate spatial correlations between the PM10 chemical species and the criteria of air pollutants, which may help to distinguish their independent chronic health effects. In addition, further improvements in the development of air pollution exposure models are discussed. This study proposed an integrated model framework for estimating multi-air-pollutant exposure in high-density and high-rise urban areas, serving an important tool for multi-air-pollutant exposure assessment in epidemiological studies.

Particulate matters (PM2.5, PM10) and the risk of depression among middle-aged and older population: analysis of the Korean Longitudinal Study of Aging (KLoSA), 2016–2020 in South Korea

BackgroundThere is a growing concern that particulate matter (PM) such as PM2.5 and PM10 has contributed to exacerbating psychological disorders, particularly depression. However, little is known about the roles of these air pollutants on depression in elderly. Therefore, this study aimed to examine the association between PM2.5 and PM10, and depression in the elderly population in South Korea.MethodsWe used panel survey data, the Korean Longitudinal Study of Aging (KLoSA), administered by the Labor Institute during the study period of 2016, 2018, and 2020 covering 217 districts in South Korea (n = 7674). Annual district-specific PM2.5 and PM10 concentrations were calculated for the study period from the monthly prediction concentrations produced by a machine-learning-based ensemble model (cross-validated R2: 0.87), then linked to the people matching with year and their residential district. We constructed a generalized estimating equation (GEE) model with a logit link to identify the associations between each of the long-term PM2.5 and PM10 exposures and depression (CES-D 10) after adjusting for individual and regional factors as confounders.ResultsIn single-pollutant models, we found that long-term 10 mathrm{mu g}/{m}^{3} increments in PM2.5 (OR 1.36, 95% CI 1.20–1.56) and PM10 (OR 1.19, 95% CI 1.10–1.29) were associated with an increased risk of depression in the elderly. Associations were consistent after adjusting for other air pollutants (NO2 and O3) in two-pollutant models. In addition, the impacts substantially differed by regions grouped by the tertile of the population density, for which the risks of particulate matters on depression were substantial in the middle- or high-population-density areas in contrast to the low-population-density areas.ConclusionsLong-term exposure to PM2.5 and PM10 was associated with a higher risk of developing depression in elderly people. The impact was modified by the population density level of the region where they reside.

High-Spatiotemporal-Resolution Estimation of Ground-Level Ozone in China Based on Machine Learning

High concentrations of ground-level ozone (O3) pose a significant threat to human health. Obtaining high-spatiotemporal-resolution information about ground-level O3 is of paramount importance for O3 pollution control. However, the current monitoring methods have a lot of limitations. Ground-based monitoring falls short in providing extensive coverage, and remote sensing based on satellites is constrained by specific spectral bands, lacking sensitivity to ground-level O3. To address this issue, we combined brightness temperature data from the Himawari-8 satellite with meteorological data and ground-based station data to train four machine learning models to obtain high-spatiotemporal-resolution information about ground-level O3, including Categorical Boosting (CatBoost), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LGBM), and Random Forest (RF). Among these, the CatBoost model exhibited superior performance, achieving a ten-fold cross-validation R2 of 0.8534, an RMSE of 17.735 μg/m3, and an MAE of 12.6594 μg/m3. Furthermore, all the selected feature variables in our study positively influenced the model. Subsequently, we employed the CatBoost model to estimate averaged hourly ground-level O3 concentrations at a 2 km resolution. The estimation results indicate a close relationship between ground-level O3 concentrations and human activities and solar radiation.

Large-scale spatiotemporal deep learning predicting urban residential indoor PM2.5 concentration

Indoor PM2.5 pollution is one of the leading causes of death and disease worldwide. As monitoring indoor PM2.5 concentrations on a large scale is challenging, it is urgent to assess population-level exposure and related health risks to develop an easy-to-use and generalized model to predict indoor PM2.5 concentrations and spatiotemporal variations at the global level. Existing machine learning models of indoor PM2.5 are prone to deliver single-point predictions, and their input strategies are not widely applicable. Here, we developed a Bayesian neural network (BNN) model for predicting the distribution of daily average urban residential PM2.5 concentration based on multiple data sources available from nationwide comprehensive sensor-monitoring records in China. The BNN model showed good performance with a 10-fold cross-validation R2 of 0.70, mean-absolute-error of 9.45 μg/m3, root-mean-square error of 13.3 μg/m3, and 95 % prediction interval coverage of 85 %. To demonstrate the application process, this model was applied to predict indoor PM2.5 concentrations on a large spatiotemporal scale. Our modeled population-weighted annual indoor PM2.5 concentration for China in 2019 was 22.8 μg/m3, far exceeding the WHO standard. The validity of the model at the population level can be further bolstered, making it valuable for assessing and managing indoor air pollution-related health risks.

Addressing Biases in Ambient PM2.5 Exposure and Associated Health Burden Estimates by Filling Satellite AOD Retrieval Gaps over India.

Ambient PM2.5 exposure statistics in countries with limited ground monitors are derived from satellite aerosol optical depth (AOD) products that have spatial gaps. Here, we quantified the biases in PM2.5 exposure and associated health burden in India due to the sampling gaps in AOD retrieved by a Moderate Resolution Imaging Spectroradiometer. We filled the sampling gaps and derived PM2.5 in recent years (2017-2022) over India, which showed fivefold cross-validation R2 of 0.92 and root mean square error (RMSE) of 11.8 μg m-3 on an annual scale against ground-based measurements. If the missing AOD values are not accounted for, the exposure would be overestimated by 19.1%, translating to an overestimation in the mortality burden by 93,986 (95% confidence interval: 78,638-110,597) during these years. With the gap-filled data, we found that the rising ambient PM2.5 trend in India has started showing a sign of stabilization in recent years. However, a reduction in population-weighted exposure balanced out the effect of the increasing population and maintained the mortality burden attributable to ambient PM2.5 for 2022 (991,058:798,220-1,183,896) comparable to the 2017 level (1,014,766:812,186-1,217,346). Therefore, a decline in exposure alone is not sufficient to significantly reduce the health burden attributable to ambient PM2.5 in India.

High spatial resolution estimates of major PM2.5 components and their associated health risks in Hong Kong using a coupled land use regression and health risk assessment approach

Few studies have focused on the spatial distribution of the typical components and source tracers of PM2.5 and their associated health risks, despite the fact that the chemical components of PM2.5 pose potentially significant and independent risks to human health. The main objective of this study was to evaluate the spatial distribution of major PM2.5 components and their associated health risks in Hong Kong using a coupled land use regression and health risk assessment modeling approach. The established land use regression models of the major PM2.5 components and source tracers achieved a relatively high statistical performance, with training and leave-one-out cross-validation R2 values of 0.85–0.96 and 0.62–0.88, respectively. The high spatial resolution (500 m × 500 m) distribution patterns of the chemical components of PM2.5 showed the heterogeneity of population exposure to different components and the related potential health risks, as evidenced by the weak spatial correlations between the mass of PM2.5 and some components. Elemental carbon, nickel, arsenic, and chromium from PM2.5 made major contributions to the total health risk and should therefore be reduced further. Our results will enable researchers to determine independent associations between exposure to the various components of PM2.5 and health endpoints in epidemiological studies.

Full-coverage mapping high-resolution atmospheric CO2 concentrations in China from 2015 to 2020: Spatiotemporal variations and coupled trends with particulate pollution

Understanding the spatiotemporal dynamics of atmospheric carbon dioxide (CO2) is crucial for achieving carbon neutrality and safeguarding planetary well-being. Satellite-based carbon monitoring is increasingly instrumental in studying atmospheric CO2 changes, offering a broad spatial view. However, current research lacks a comprehensive exploration of both day-to-day variations in atmospheric CO2 at a finer-resolution grid and its coupled relationship with particulate pollution, owing to a substantial number of missing values in satellite-retrieved CO2 data. To address these issues, this study presents an enhanced regression-based machine learning model, reconstructing full-coverage daily atmospheric CO2 concentrations in China from 2015 to 2020 at a 0.01° spatial resolution. Utilizing spatiotemporal high-resolution column-averaged dry-air mole fraction of CO2 (XCO2) data from the Orbiting Carbon Observatory 2 (OCO-2) as the dependent variable and multi-source environmental factors as independent variables, we achieved overall, spatial, and temporal cross-validation R2 [RMSE] results of 0.98 [0.74 ppm], 0.95 [1.15 ppm], and 0.93 [1.44 ppm], respectively. The resulting full-coverage estimates revealed significant spatial heterogeneity over time, with the highest CO2 levels primarily in spring in the North China Plain, and the lowest in summer in northern China and autumn in the Qinghai-Tibet Plateau and the south. National weekend averages of mean symmetrized residuals in XCO2 surpassed weekday averages. Within megacities such as Shanghai and Wuhan, industry-intensive areas exhibited higher XCO2 values compared to other urban areas within the same cities. Despite spatial and seasonal fluctuations, the country-average XCO2 increased from 2015 to 2020 but has decelerated recently. A moderate correlation was observed between the spatial pattern of long-term CO2 concentrations and particulate aerosols, viewed from the total atmospheric column perspective, with some regional discrepancies. The present modeling method advances carbon monitoring techniques, and the predictive data foster an enriched understanding of the carbon cycle, climate change, and sustainable development.

Investigating correlations between physical properties and fire suppression performance of fluorinated and fluorine-free foams using a novel firefighting foam database

Aqueous film-forming foams (AFFF) contain fluorinated surfactants, a class of perfluoroalkyl substances (PFAS) which have been shown to cause damage to the environment and human health. This has necessitated their replacement on military sites by the year 2024. But to date, no fluorine-free replacement firefighting formulation has showed comparable performance to AFFF. Fire extinction performance is measured in tandem with formulation physical properties, but whether various physical properties and fire suppression are correlated is poorly understood. Herein, we present the curation of a large amount of physical property and fire suppression data collected in-house. Chemometric regression was used to ascertain correlations between the critical micelle concentration (CMC) of both individual surfactant solutions and multi-component formulations and their corresponding (1) solution surface tension, (2) interfacial tension with heptane, and (3) fuel-induced foam degradation using heptane and (4) gasoline. After evaluating several algorithms, promising correlations are found between CMC and foam degradation on heptane and gasoline using locally weighted regression (LWR), as indicated by a large R2 of cross-validation (R2CV) from ∼0.6–0.9. Solutions with CMCs from ∼0.01–0.1 wt percent (%) exhibit the longest degradation times, whereas solutions with CMCs outside of this range had considerably faster degradation. This correlation is new but explains only 90% or less of the variation in the data partly because foam degradation is induced by fuel, which the CMC does not consider. However, this work will serve as a basis for future machine learning endeavors to predict fire suppression performance based on chemical structure.