Cross-validated R2 Research Articles

Estimating PM2.5 in Southern California using satellite data: factors that affect model performance

Background: Studies of PM2.5 health effects are influenced by the spatiotemporal coverage and accuracy of exposure estimates. The use of satellite remote sensing data such as aerosol optical depth (AOD) in PM2.5 exposure modeling has increased recently in the US and elsewhere in the world. However, few studies have addressed this issue in southern California due to challenges with reflective surfaces and complex terrain.Methods: We examined the factors affecting the associations with satellite AOD using a two-stage spatial statistical model. The first stage estimated the temporal PM2.5/AOD relationships using a linear mixed effects model at 1 km resolution. The second stage accounted for spatial variation using geographically weighted regression. Goodness of fit for the final model was evaluated by comparing the daily PM2.5 concentrations generated by cross-validation (CV) with observations. These methods were applied to a region of southern California spanning from Los Angeles to San Diego.Results: Mean predicted PM2.5 concentration for the study domain was 8.84 µg m−3. Linear regression between CV predicted PM2.5 concentrations and observations had an R2 of 0.80 and RMSE 2.25 µg m−3. The ratio of PM2.5 to PM10 proved an important variable in modifying the AOD/PM2.5 relationship (β = 14.79, p ≤ 0.001). Including this ratio improved model performance significantly (a 0.10 increase in CV R2 and a 0.56 µg m−3 decrease in CV RMSE).Discussion: Utilizing the high-resolution MAIAC AOD, fine-resolution PM2.5 concentrations can be estimated where measurements are sparse. This study adds to the current literature using remote sensing data to achieve better exposure data in the understudied region of Southern California. Overall, we demonstrate the usefulness of MAIAC AOD and the importance of considering coarser particles in dust prone areas.

Assessment for personal PM2.5 exposure with a modeling method: A panel study in Wuhan, China

The adverse health effects from fine particulate matter (PM2.5) exposure have attracted much attention. However, the method to evaluate individual PM2.5 exposure levels in large populations has always been a challenging task. We conducted this study to explore the relationships of ambient PM2.5, meteorological conditions and personal lifestyles with personal PM2.5 exposure and establish an estimated model for personal PM2.5 exposure among community residents in Wuhan. Participants were extracted from Wuhan-Zhuhai cohort and a total of 191 24-h personal PM2.5 measurements were conducted using personal PM2.5 samplers in Spring, 2014, 2017. Ambient PM2.5 concentration, meteorological conditions and personal lifestyles were collected from the nearest fixed air monitoring station, meteorological station and face-to-face investigation, respectively. The average concentration of daily personal PM2.5 exposure was 156.85 μg/m3 with a range of 14.85–443.21 μg/m3 in this study, which was almost twice as high as the ambient PM2.5 concentrations (average 71.16 μg/m3). After stepwise selection and linear mixed model fitting, ambient PM2.5, cigarette consumption, passive smoking, pressure difference, temperature, relative humidity, and wind speed were selected into the final model. Marginal R2 and conditional R2 of this model were 0.604 and 0.635, respectively. R2 of 10-fold cross validation was 0.654. This study provided an estimated model with relatively comprehensive consideration of sources for personal PM2.5 exposure in Wuhan.

Predicting outdoor ultrafine particle number concentrations, particle size, and noise using street-level images and audio data

Outdoor ultrafine particles (UFPs) (<0.1 µm) may have an important impact on public health but exposure assessment remains a challenge in epidemiological studies. We developed a novel method of estimating spatiotemporal variations in outdoor UFP number concentrations and particle diameters using street-level images and audio data in Montreal, Canada. As a secondary aim, we also developed models for noise. Convolutional neural networks were first trained to predict 10-second average UFP/noise parameters using a large database of images and audio spectrogram data paired with measurements collected between April 2019 and February 2020. Final multivariable linear regression and generalized additive models were developed to predict 5-minute average UFP/noise parameters including covariates from deep learning models based on image and audio data along with outdoor temperature and wind speed. The best performing final models had mean cross-validation R2 values of 0.677 and 0.523 for UFP number concentrations and 0.825 and 0.735 for UFP size using two different test sets. Audio predictions from deep learning models were stronger predictors of spatiotemporal variations in UFP parameters than predictions based on street-level images; this was not explained only by noise levels captured in the audio signal. All final noise models had R2 values above 0.90. Collectively, our findings suggest that street-level images and audio data can be used to estimate spatiotemporal variations in outdoor UFPs and noise. This approach may be useful in developing exposure models over broad spatial scales and such models can be regularly updated to expand generalizability as more measurements become available.

Remote Sensing Estimation of Regional NO2 via Space-Time Neural Networks

Nitrogen dioxide (NO2) is an essential air pollutant related to adverse health effects. A space-time neural network model is developed for the estimation of ground-level NO2 in this study by integrating ground NO2 station measurements, satellite NO2 products, simulation data, and other auxiliary data. Specifically, a geographically and temporally weighted generalized regression neural network (GTW-GRNN) model is used with the advantage to consider the spatiotemporal variations of the relationship between NO2 and influencing factors in a nonlinear neural network framework. The case study across the Wuhan urban agglomeration (WUA), China, indicates that the GTW-GRNN model outperforms the widely used geographically and temporally weighted regression (GTWR), with the site-based cross-validation R2 value increasing by 0.08 (from 0.61 to 0.69). Besides, the comparison between the GTW-GRNN and original global GRNN models shows that considering the spatiotemporal variations in GRNN modeling can boost estimation accuracy. All these results demonstrate that the GTW-GRNN based NO2 estimation framework will be of great use for remote sensing of ground-level NO2 concentrations.

ASSESSMENT OF EXPOSURE TO AMBIENT PM2.5 BASED ON GAP-FILLED AEROSOL OPTICAL DEPTH AT URBAN SCALE

Abstract. Air pollution has been a crucial issue affecting human health and has drawn more and more attention in the world. The assessment of exposure to PM2.5 of urban residents based on remote sensing is challenging because of the data deficiency in aerosol optical depth (AOD) and the low spatial resolution. This article is devoted to adopt an approach with 2 gradient boosting decision tree (GBDT) models to fill the gaps in AOD and derive continuous PM2.5 distribution at urban scale. Then, the assessment of exposure to PM2.5 in Beijing was conducted. First, Simplified High Resolution MODIS Aerosol Retrieval Algorithm (SARA) was employed to obtain daily AOD from September 2016 to February 2017 at 500m resolution. Then we used the first GBDT to derive the gap-filled SARA AOD and the second GBDT to estimate PM2.5 spatial distribution based on multi-source data. Furthermore, population weighted exposure (PWE) levels of PM2.5 and population proportion exposed to PM2.5 concentration were estimated by PM2.5 distribution and population density data. The result demonstrates that both two GBDT models performed well with cross validation (CV) R2 of 0.86 and 0.85 on AOD gap-filling and PM2.5 concentration estimation respectively. The areas with high PM2.5 concentration are mainly distributed in the east and south of the city but the areas with higher PM2.5 exposure are mainly distributed in the urban centre. Moreover, it is found that over 80% people in Beijing are affected by PM2.5 pollution in autumn and winter. Overall, the approach this article applied and the analysis results are very useful for epidemiological investigation and air pollution control policy formulation.

Predicting ambient PM2.5 concentrations in Ulaanbaatar, Mongolia with machine learning approaches.

Accurately assessing individual ambient air pollution exposure is a crucial part of epidemiological studies looking at the adverse health effect of poor air quality. This is particularly challenging in developing countries with high levels of air pollution, mostly due to sparse monitoring networks with a lack of consistent data. We evaluated the performance of six different machine learning algorithms in predicting fine particulate matter (PM2.5) concentrations in Ulaanbaatar, Mongolia using data between 2010 and 2018. We found that the algorithms produce robust results based on performance metrics. Random forest (RF) and gradient boosting models performed the best with leave-one-location-out cross-validated R2 of 0.82 for when using data from the entire study period. After applying tuned models on the hold-out test set, R2 increased to 0.96 for the RF and 0.90 for the gradient boosting model. We also predicted PM2.5 concentrations for each administrative area (khoroo) of the city using RF and maps of predictions show spatiotemporal variations that are in line with the location of the high-emission area (ger district), city center, and population density. Our results provide evidence of the advantage and feasibility of machine learning approaches in predicting ambient PM2.5 levels in a setting with limited resources and extreme air pollution levels.

Geographically and temporally weighted neural networks for satellite-based mapping of ground-level PM2.5

The integration of satellite-derived aerosol optical depth (AOD) and station-measured PM2.5 (particulate matter with an aerodynamic diameter of less than 2.5 μm) provides a promising approach for the monitoring of PM2.5. Previous models have generally only considered either the spatiotemporal heterogeneities of the AOD-PM2.5 relationship or the nonlinear relationship between AOD and PM2.5. In this paper, to simultaneously allow for the nonlinearity and spatiotemporal heterogeneities of the AOD-PM2.5 relationship, the geographically and temporally weighted neural network (GTWNN) model is proposed for the satellite-based estimation of ground-level PM2.5. The GTWNN model represents the nonlinear AOD-PM2.5 relationship via a generalized regression neural network, and is separately established for individual locations and times, to address the spatiotemporal heterogeneities of the AOD-PM2.5 relationship. Meanwhile, a spatiotemporal weighting scheme is incorporated in the GTWNN model to capture the local relations of samples for the training of the AOD-PM2.5 relationship. By the use of the Moderate Resolution Imaging Spectroradiometer (MODIS) AOD product, meteorological data, and MODIS normalized difference vegetation index (NDVI) data as input, the GTWNN model was verified using ground station PM2.5 measurements from China in 2015. The GTWNN model achieved sample-based cross-validation (CV) and site-based CV R2 values of 0.80 and 0.79, respectively, and it outperformed the geographically and temporally weighted regression model (CV R2: 0.75 and 0.73) and the daily geographically weighted regression model (CV R2: 0.72 and 0.72). The proposed model implements the combination of geographical law and a neural network, and will be of great use for remote sensing retrieval of environmental variables.

Prediction of PM2.5 concentrations at the locations of monitoring sites measuring PM10 and NOx, using generalized additive models and machine learning methods: A case study in London

Abstract The adverse health effects of air pollutants, especially those of PM2.5, are well documented. However, a lack of adequate monitoring and weaknesses in modelling approaches do not allow a good assessment of health effects in many areas of the World. Advances in computational methods and the availability of new data sets, e.g. satellite remote observations, have enlarged the possibilities of modelling for application in large scale health effects studies. However, PM2.5 monitoring is very recent in most of the World and more limited compared to other pollutants, and understanding how to use PM10 monitors to estimate PM2.5 exposure is therefore important. Since interest in these methods is relatively recent, there is a need for testing their performance against ambient measurements, but long term PM2.5 datasets are less readily available than PM10 in many regions. In the present study we report the methodology and results of using regression modelling and a machine learning method (Random Forest-RF), as well as a combination of the two, to enhance a PM2.5 measurement data base in London using PM10 and NOx measurements as well as other predictors and compare the relative performance of each method. We found that the combination of predictions by the regression model and the RF performs best and we obtain a cross-validation R2 of 99.29% and 98.22% for the 5-year periods 2004–2008 and 2009–2013, respectively, and a Mean Square Error near 1. Our enhanced data base for PM2.5 is available for use by other researchers.

Estimation of hourly full-coverage PM2.5 concentrations at 1-km resolution in China using a two-stage random forest model

Fine particulate matter such as PM2.5 has been the focus of increasing public concerns because of its adverse effect on environment and health risks. However, existing efforts of mapping PM2.5 concentrations are always limited by coarse spatial resolutions and temporal frequencies. Addressing this shortcoming, here we explicitly estimated hourly PM2.5 concentrations at 1-km spatial resolution in China from March 2018 to February 2019 using a two-stage random forest model. In the first stage, we used a gap-filling method to generate full-coverage Aerosol Optical Depth (AOD) by fusing AOD data from satellite (Himawari-8 and MODIS) and weather forecast model (CAMS), and additional meteorological and geographical variables. Gap-filled AOD was subsequently used to estimate hourly PM2.5 in the Stage II. Results showed that our model achieved accurate and robust estimations of PM2.5 concentrations, with an overall cross-validated R2 of 0.85, root mean squared error of 11.02 μg/m3, and mean absolute error of 6.73 μg/m3. CAMS-simulated PM2.5, elevation, and gap-filled AOD were identified to be important variables contributing to the model performance of PM2.5 estimation. The model performance varied over the daily temporal scale. Specifically, daily estimation model performed better in spring and winter but worse in summer and autumn. We provide an alternative to generate spatially and temporally explicit mapping of PM2.5 concentrations with fine resolutions, making it possible to achieve real-time monitoring of air pollutions. The detailed spatial heterogeneity and diurnal variability of PM2.5 concentrations will also be valuable for environmental exposure assessments.

Estimating daily ground-level PM2.5 in China with random-forest-based spatiotemporal kriging

Ambient fine particulate matter (PM2.5) plays an important role in cardiovascular- and respiratory-related death. Empirical statistical models have been widely applied to estimate ambient PM2.5 concentrations with correlated variables. However, empirical statistical models ignore the nonlinear relationship between PM2.5 and covariates and assume that residuals are independent and identically distributed random variables. Here, a hybrid approach, which integrates random forest (RF) model and spatiotemporal kriging, is proposed to estimate the daily PM2.5 concentration. The proposed RF-based spatiotemporal kriging (RFSTK) model effectively captures nonlinear interactions among different predictors and accounts for the detailed spatiotemporal dependence of the PM2.5 concentration. The RFSTK model performs well in predicting the daily PM2.5 concentration. The 10-fold overall cross-validation R2 value is 0.881, the mean absolute error (MAE) is 6.89 μg/m3 and the root-mean-square error (RMSE) is 11.48 μg/m3, indicating better performance than the original RF model (R2 = 0.848, MAE = 7.88 μg/m3 and RMSE = 13.26 μg/m3). The spatiotemporal prediction of the PM2.5 concentration shows that approximately 90.04% of China had a daily exposure to PM2.5 in 2018 that was below the nation's air quality standard of 75 μg/m3. The proposed hybrid method is entirely general and can be applied to map the ambient PM2.5 concentration over a large spatiotemporal domain.

Simulated lesions representative of metastatic disease predict proximal femur failure strength more accurately than idealized lesions

Metastatic disease in bone is characterized by highly amorphous and variable lesion geometry, with increased fracture risk. Assumptions of idealized lesion geometry made in previous finite element (FE) studies of metastatic disease in the proximal femur may not sufficiently capture effects of local stress/strain concentrations on predicted failure strength. The goal of this study was to develop and validate a FE failure model of the proximal femur incorporating artificial defects representative of physiologic metastatic disease. Data from 11 cadaveric femur specimens were randomly divided into either a training set (n = 5) or a test set (n = 6). Clinically representative artificial defects were created, and the femurs were loaded to failure under offset torsion. Voxel-based FE models replicating the experimental setup were created from the training set pre-fracture computed tomography data. Failure loads from the linear model with maximum principal strain failure criterion correlated best with the experimental data (R2 = 0.86, p = 0.024). The developed model was found to be reliable when applied to the test dataset with a relatively low RMSE of 46.9 N, mean absolute percent error of 12.7 ± 17.1%, and cross-validation R2 = 0.88 (p < 0.001). Models simulating realistic lesion geometry explained an additional 26% of the variance in experimental failure load compared to idealized lesion models (R2 = 0.62, p = 0.062). Our validated automated FE model representative of physiologic metastatic disease may improve clinical fracture risk prediction and facilitate research studies of fracture risk during functional activities and with treatment interventions.

High temporal resolution prediction of street-level PM2.5 and NOx concentrations using machine learning approach

Accurate and high temporal resolution predictions of fine particulate matter (PM2.5) and nitrogen oxides (NOx) concentrations are crucial for pollution control, air pollutant exposure and epidemiological studies. This study aimed to develop machine learning-based models for predicting hourly street-level PM2.5 and NOx concentrations at three roadside stations in Hong Kong. We comprehensively evaluated and compared the performance of six common machine learning algorithms (MLAs) including Random Forest (RF), Boosted Regression Trees (BRT), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Generalized Additive Model (GAM), and Cubist and hence applied the most suitable MLAs to apportion the contributions from emission and non-emission factors to hourly street-level PM2.5 and NOx concentrations. The results show that RF outperformed other MLAs with ten-fold cross validation (CV) R2 values higher than 0.81 and 0.62 for PM2.5 and NOx predictions, respectively. BRT, XGBoost and Cubist presented comparable predictive performances, with CV R2 of 0.79–0.83 (for PM2.5 predictions) and 0.59–0.71 (for NOx predictions). SVM and GAM had worse predictions than other MLAs. The external validation R2 values for RF and BRT models were more than 0.62 and 0.51 for PM2.5 and NOx concentration predictions, respectively. Non-emission factors contributed 84% and 65% to the predictions of street-level PM2.5 and NOx concentrations, respectively. Non-local pollution and temperature were the major non-emission factors, whereas private cars were the major emission contributor. This study highlights the capability of MLAs to produce high temporal resolution air pollution predictions, which can supplement traditional methods (e.g., land use regression) in generating accurate and high-temporal-resolution estimations of air pollution concentration.

In silico studies of novel pyrazole-furan and pyrazole-pyrrole carboxamide as fungicides against Sclerotinia sclerotiorum

BackgroundPyrazole-furan and pyrazole-pyrrole moiety are among the molecular structures that were found to have an extensive range of applications in the field of medicine and agrochemical due to their wide spectrum of biological activities. These include antimicrobial activity, anti-glaucoma activity, ocular hypertension activity, and antifungal activity.ResultsAn in silico study was carried out on 37 compounds of pyrazole-furan and pyrazole-pyrrole carboxamide derivatives against Sclerotinia sclerotiorum. Using Spartan 14 software, optimization of the compounds was performed at the DFT/B3LYP/6-31G* quantum mechanical method. PaDEL descriptor software was used to calculate the molecular descriptors, and a Generic Function Approximation (GFA) was employed to generate the model. Out of four models generated, model 1 was found to be the optimal and has the following statistical parameters; R2 = 0.83485, R2adj = 0.793563, cross-validated R2 = 0.74037, and external R2 = 0.58479. Molecular docking study was carried out between the antifungal compounds, and the binding site of S. sclerotiorum (PDB CODE 2X2S) in which compound 7 was identified to have the highest binding energy of − 7.5kcal/mol. This compound “7” has a strong affinity with the macromolecular target point of the S. sclerotiorum (2x2s), producing H-bond and as well as the hydrophobic interaction at target point of the amino acid residue. Considering compound 7 as our scaffold, four (4) more potent compounds (7a, 7b, 7c, and 7d) were designed using optimization method of structure-based designed which have the following docking score, − 7.7, − 7.8, − 7.7, and − 7.7kcal/mol.ConclusionStatistical analyses including variance inflation factor (VIF), mean effect (ME), and applicability domain were conducted on the model. Considering an interpretation of the descriptors given in the discussion, the QSAR model provided an idea of ligand-based design while the molecular docking gave an insight on structure-based design of the new compounds with better activity against S. sclerotiorum in which four (4) compounds 7a, 7b, 7c, and 7d were designed and discovered to be of high quality and have greater binding affinity compared to the one obtained from the literature (compound 7).

Not so robust: Robusta coffee production is highly sensitive to temperature.

Coffea canephora (robusta coffee) is the most heat-tolerant and 'robust' coffee species and therefore considered more resistant to climate change than other types of coffee production. However, the optimum production range of robusta has never been quantified, with current estimates of its optimal mean annual temperature range (22-30°C) based solely on the climatic conditions of its native range in the Congo basin, Central Africa. Using 10years of yield observations from 798 farms across South East Asia coupled with high-resolution precipitation and temperature data, we used hierarchical Bayesian modeling to quantify robusta's optimal temperature range for production. Our climate-based models explained yield variation well across the study area with a cross-validated mean R2 =.51. We demonstrate that robusta has an optimal temperature below 20.5°C (or a mean minimum/maximum of ≤16.2/24.1°C), which is markedly lower, by 1.5-9°C than current estimates. In the middle of robusta's currently assumed optimal range (mean annual temperatures over 25.1°C), coffee yields are 50% lower compared to the optimal mean of ≤20.5°C found here. During the growing season, every 1°C increase in mean minimum/maximum temperatures above 16.2/24.1°C corresponded to yield declines of ~14% or 350-460kg/ha (95% credible interval). Our results suggest that robusta coffee is far more sensitive to temperature than previously thought. Current assessments, based on robusta having an optimal temperature range over 22°C, are likely overestimating its suitable production range and its ability to contribute to coffee production as temperatures increase under climate change. Robusta supplies 40% of the world's coffee, but its production potential could decline considerably as temperatures increase under climate change, jeopardizing a multi-billion dollar coffee industry and the livelihoods of millions of farmers.

QSAR and molecular docking studies of novel 2,5-distributed-1,3,4-thiadiazole derivatives containing 5-phenyl-2-furan as fungicides against Phythophthora infestans

BackgroundThe 1,3,4-thiadiazoles are among the structural moieties that were found to be of utmost importance in the fields of pharmacy and agrochemicals because of their widespread biological activity that includes anti-tumor, antibacterial, anti-inflammatory, antihypertensive, anti-tuberculosis, anticonvulsant, and antimicrobial, among others.ResultsQSAR and molecular docking studies were carried out on thirty-two (32) derivatives of 2,5-disubstituted-1,3,4-thiadiazoles for their antifungal activities toward Phytophthora infestans. Using the “graphical user interface” of Spartan14 software, the structure of the compounds of the dataset is drawn and then optimized at DFT/B3LYP/6-31G* quantum mechanical method of the software. Molecular descriptors of the optimized compounds were calculated and later on divided into the training set and test sets (at a ratio of 3:1). The training set was used for model generation and the test set was for external validation of the generated model. Four models were generated by the employment of genetic function approximation (GFA) in which the optimal model (4) turned out to have the following statistical parameters: R2 = 0.798318, R2adj = 0.750864, cross-validation R2(Q2cv) = 0.662654, and external validation R2pred = 0.624008. On the molecular docking study of thiadiazole compounds with the target protein of Phytophthora infestans effector site (PDB ID: 2NAR ), compound 13 shows the highest binding affinity with − 9.3 kcal/mol docking score and composes hydrophobic as well as H-bond interactions with the target protein (2NAR).ConclusionThe result of the QSAR study signifies the stability and robustness of the built model by considering the validation parameters and this gave an idea of template/ligand-based design while the molecular docking study revealed the binding interaction between the ligand and the protein site which gave an insight toward an “optimization method” of the structure-based design for the discovery of more potent compounds with better activity against Phytophthora infestans using the approach of computer-aided drug design (CADD) in plant pathology.

Spatial modelling of particulate matter air pollution sensor measurements collected by community scientists while cycling, land use regression with spatial cross-validation, and applications of machine learning for data correction

Abstract Fine particulate matter air pollution is a global issue; cycling is a global activity. In our paper, particulate matter less than 2.5 μm (PM2.5) air pollution data obtained by community scientists while cycling is used to develop high-resolution spatial air pollution maps. Mapping is completed using a land use regression model for Charlotte, North Carolina. The air pollution observations were obtained with a low-cost sensor. We evaluated the accuracy of the sensor through a collocation study for 3203 h, which identified the sensor had a mean bias of 7.25 μg/m3 and a correlation of r = 0.77 with an US EPA Federal Equivalent Monitor. A machine learning model was developed to adjust the sensor observations, which demonstrated their highest errors during periods of high humidity. The adjustment was able to reduce the root mean squared error from 12 μg/m3 to 3.8 μg/m3, and the mean bias was reduced to −0.5 μg/m3. Cycling times were not balanced throughout the day nor the year. We applied a temporal adjustment algorithm to account for this imbalance in observation periods with the intention of producing long-term estimates representing the sampling period of 2016 and 2017. The long-term air pollution surface for the city was generated with a land use regression model. Both linear regression and machine learning approaches were applied. The linear regression model performed poorly with a training R2 of 0.15 and a cross-validation R2 of 0.15. A stacked ensemble model was developed using machine learning, which had a training 5-fold cross-validation mean residual deviance of 3.82 μg/m3, a root mean squared error of 1.95 μg/m3, and a mean absolute error of 0.95 μg/m3. Performance remained strong during cross-validation, which included both a random sample approach (RMSE = 1.52 μg/m3) and a spatial blocking cross-validation method (RMSE = 2.8 μg/m3).

Nuclear Magnetic Resonance to Detect Rumen Metabolites Associated with Enteric Methane Emissions from Beef Cattle

This study presents the application of metabolomics to evaluate changes in the rumen metabolites of beef cattle fed with three different diet types: forage-rich, mixed and concentrate-rich. Rumen fluid samples were analysed by 1H-NMR spectroscopy and the resulting spectra were used to characterise and compare metabolomic profiles between diet types and assess the potential for NMR metabolite signals to be used as proxies of methane emissions (CH4 in g/kg DMI). The dataset available consisted of 128 measurements taken from 4 experiments with CH4 measurements taken in respiration chambers. Predictive modelling of CH4 was conducted by partial least squares (PLS) regression, fitting calibration models either using metabolite signals only as predictors or using metabolite signals as well as other diet and animal covariates (DMI, ME, weight, BW0.75, DMI/BW0.75). Cross-validated R2 were 0.57 and 0.70 for the two models respectively. The cattle offered the concentrate-rich diet showed increases in alanine, valerate, propionate, glucose, tyrosine, proline and isoleucine. Lower methane yield was associated with the concentrate-rich diet (p < 0.001). The results provided new insight into the relationship between rumen metabolites, CH4 production and diets, as well as showing that metabolites alone have an acceptable association with the variation in CH4 production from beef cattle.

QSAR, molecular docking, and design of novel 4-(N,N-diarylmethyl amines) Furan-2(5H)-one derivatives as insecticides against Aphis craccivora

BackgroundAphis craccivora has many plant hosts, though it seemingly forechoice to groups of bean family. Other plants it hosts are families of Solanaceae, Rosaceae, Malvaceae, Chenopodiaceae, Caryophyllaceae, Ranunculaceae, Cucurbitaceae, Brassicaceae, and Asteraceae.ResultA computational study was carried out on a series of twenty compounds of novel 4-(N,N-diarylmethylamines) furan-2(5H)-one derivatives against Aphis craccivora insect. Optimization of the compounds was performed with the aid of Spartan 14 software using DFT/B3LYP/6-31G** quantum mechanical method. Using PaDel descriptor software to calculate the descriptors, Generic Function Approximation (GFA) was employed to generate the model. Model 1 found to be the optimal out of four models generated which has the following statistical parameters; R2 = 0.871489, R2adj = 0.83644, cross-validated R2 = 0.790821, and external R2 = 0.550768. Molecular docking study occurred between the compounds and the complex crystal structure of the acetylcholine (protein AChBP) (PDB CODE 2zju) in which compound 13 was identified to have the highest binding energy of − 8.4 kcalmol−1. Statistical analyses, such as variance inflation factor, mean effect, and the applicability domain, were conducted on the model. This compound has a strong affinity with the macromolecular target point of the A. craccivora (2zju) producing H-bond and as well the hydrophobic interaction at the target point of amino acid residue. Molecular docking gave an insight into the structure-based design of the new compounds with better activity against A. craccivora in which three compounds A, B, and C were designed and discovered to be of high quality and have greater binding affinity compared to the one obtained from the literature.ConclusionThe QSAR model was generated by the employment of Genetic Function Approximation (GFA). The model was found to be robust and possessed a good statistical parameter. Furthermore, a molecular docking study was performed to get an idea for structure-based design in which three (3) compounds A, B, and C were designed and were found to be more active than the template (compound 13, i.e., the one with highest docking score). QSAR model was developed to give an insight into the ligand/template-based design of computer-aided drug design.

A multi-city air pollution population exposure study: Combined use of chemical-transport and random-Forest models with dynamic population data

Cities are severely affected by air pollution. Local emissions and urban structures can produce large spatial heterogeneities. We aim to improve the estimation of NO2, O3, PM2.5 and PM10 concentrations in 6 Italian metropolitan areas, using chemical-transport and machine learning models, and to assess the effect on population exposure by using information on urban population mobility. Three years (2013–2015) of simulations were performed by the Chemical-Transport Model (CTM) FARM, at 1 km resolution, fed by boundary conditions provided by national-scale simulations, local emission inventories and meteorological fields. A downscaling of daily air pollutants at higher resolution (200 m) was then carried out by means of a machine learning Random-Forest (RF) model, considering CTM and spatial-temporal predictors, such as population, land-use, surface greenness and vehicular traffic, as input. RF achieved mean cross-validation (CV) R2 of 0.59, 0.72, 0.76 and 0.75 for NO2, PM10, PM2.5 and O3, respectively, improving results from CTM alone. Mean concentration fields exhibited clear geographical gradients caused by climate conditions, local emission sources and photochemical processes. Time series of population weighted exposure (PWE) were estimated for two months of the year 2015 and for five cities, by combining population mobility data (derived from mobile phone traffic volumes data), and concentration levels from the RF model. PWE_RF metric better approximated the observed concentrations compared with the predictions from either CTM alone or CTM and RF combined, especially for pollutants exhibiting strong spatial gradients, such as NO2. 50% of the population was estimated to be exposed to NO2 concentrations between 12 and 38 μg/m3 and PM10 between 20 and 35 μg/m3. This work supports the potential of machine learning methods in predicting air pollutant levels in urban areas at high spatial and temporal resolutions.

Estimating high-resolution PM1 concentration from Himawari-8 combining extreme gradient boosting-geographically and temporally weighted regression (XGBoost-GTWR)

Abstract As a much finer particle, particulate matter less than 1 μm (PM1) plays an important role on the haze formation and human health. However, the capability of mapping PM1 concentration is severely impaired by coarse temporal resolution and low estimation accuracy, largely due to the neglect of spatial or temporal autocorrelation of PM1. In order to improve the estimation of high-resolution PM1, here we developed a novel spatiotemporal model named extreme gradient boosting (XGBoost)-geographically and temporally weighted regression (GTWR) using Himawari-8 aerosol optical depth (AOD), meteorological factors, and geographical covariates. The estimation of PM1 over Zhejiang province showed that XGBoost-GTWR method was characterized by greater predictive ability (10-fold cross-validation R2 = 0.83, root mean squared error (RMSE) = 10.72 μg/m3) compared with other 11 models. Additionally, the extrapolation test was performed to validate the robustness of the hybrid model and the result demonstrated that XGBoost-GTWR can accurately predict the out-of-band PM1 concentration (R2 = 0.75 (0.60), RMSE = 12.71 (12.58) μg/m3). The PM1 concentration displayed pronounced spatial heterogeneity, with the highest value in Quzhou (34.72 ± 1.77 μg/m3) and the lowest in Zhoushan (26.39 ± 1.56 μg/m3), respectively. In terms of the seasonality, the highest PM1 concentration was observed in winter (39.06 ± 3.08 μg/m3), followed by those in spring (32.54 ± 3.09 μg/m3) and autumn (30.97 ± 4.50 μg/m3), and the lowest one in summer (25.57 ± 5.22 μg/m3). The high aerosol emission and adverse meteorological conditions (e.g., low boundary layer height and lack of precipitation) were key factors accounting for the peak PM1 concentration observed in winter. Also, the PM1 concentration exhibited significant diurnal variation, peaking at 1500 local solar time (LST) but reaching the lowest value at 1000 LST. This method enhances our capability of estimating hourly PM1 from space, and lays a solid data foundation for improving the assessment of the fine particle-related health effect.