Groundwater Quality Monitoring Using In-Situ Measurements and Hybrid Machine Learning with Empirical Bayesian Kriging Interpolation Method

This article discusses the assessment of groundwater quality using a hybrid technique that would aid in the convenience of groundwater (GW) quality monitoring. Twenty eight (28) GW samples representing 62 barangays in Calapan City, Oriental Mindoro, Philippines were analyzed for their physicochemical characteristics and heavy metal (HM) concentrations. The 28 GW samples were collected at suburban sites identified by the coordinates produced by Global Positioning System Montana 680. The analysis of heavy metal concentrations was conducted onsite using portable handheld X-Ray Fluorescence (pXRF) Spectrometry. Hybrid machine learning—geostatistical interpolation (MLGI) method, specific to neural network particle swarm optimization with Empirical Bayesian Kriging (NN-PSO+EBK), was employed for data integration, GW quality spatial assessment and monitoring. Spatial map of metals concentration was produced using the NN-PSO-EBK. Another, spot map was created for observed metals concentration and was compared to the spatial maps. Results showed that the created maps recorded significant results based on its MSEs with values such as 1.404 × 10−4, 5.42 × 10−5, 6.26 × 10−4, 3.7 × 10−6, 4.141 × 10−4 for Ba, Cu, Fe, Mn, Zn, respectively. Also, cross-validation of the observed and predicted values resulted to R values range within 0.934–0.994 which means almost accurate. Based on these results, it can be stated that the technique is efficient for groundwater quality monitoring. Utilization of this technique could be useful in regular and efficient GW quality monitoring.

Using Bayesian Kriging for spatial smoothing of trends in non-normal yield densities

PurposeThe purpose of this paper is to estimate crop yield densities considering time trends in the first three moments and spatially varying coefficients.Design/methodology/approachYield density parameters are assumed to be spatially correlated, through a Gaussian spatial process. This study spatially smooth multiple parameters using Bayesian Kriging.FindingsAssuming that county yields follow skew normal distributions, the location parameter increased faster in the eastern and northwestern counties of Iowa, while the scale increased faster in southern counties and the shape parameter increased more (implying less left skewness) in southwestern counties. Over time, the mean has increased sharply, while the variance and left skewness increased modestly.Originality/valueBayesian Kriging can smooth time-varying yield distributions, handle unbalanced panel data and provide estimates when data are missing. Most past models used a two-stage estimation procedure, while our procedure estimates parameters jointly.

Ingestion of GNSS-Derived ZTD and PWV for Spatial Interpolation of PM2.5 Concentration in Central and Southern China

With the increasing application of global navigation satellite system (GNSS) technology in the field of meteorology, satellite-derived zenith tropospheric delay (ZTD) and precipitable water vapor (PWV) data have been used to explore the spatial coverage pattern of PM2.5 concentrations. In this study, the PM2.5 concentration data obtained from 340 PM2.5 ground stations in south-central China were used to analyze the variation patterns of PM2.5 in south-central China at different time periods, and six PM2.5 interpolation models were developed in the region. The spatial and temporal PM2.5 variation patterns in central and southern China were analyzed from the perspectives of time series variations and spatial distribution characteristics, and six types of interpolation models were established in central and southern China. (1) Through correlation analysis, and exploratory regression and geographical detector methods, the correlation analysis of PM2.5-related variables showed that the GNSS-derived PWV and ZTD were negatively correlated with PM2.5, and that their significances and contributions to the spatial analysis were good. (2) Three types of suitable variable combinations were selected for modeling through a collinearity diagnosis, and six types of models (geographically weighted regression (GWR), geographically weighted regression kriging (GWRK), geographically weighted regression—empirical bayesian kriging (GWR-EBK), multiscale geographically weighted regression (MGWR), multiscale geographically weighted regression kriging (MGWRK), and multiscale geographically weighted regression—empirical bayesian kriging (MGWR-EBK)) were constructed. The overall R2 of the GWR-EBK model construction was the best (annual: 0.962, winter: 0.966, spring: 0.926, summer: 0.873, and autumn: 0.908), and the interpolation accuracy of the GWR-EBK model constructed by inputting ZTD was the best overall, with an average RMSE of 3.22 μg/m3 recorded, while the GWR-EBK model constructed by inputting PWV had the highest interpolation accuracy in winter, with an RMSE of 4.5 μg/m3 recorded; these values were 2.17% and 4.26% higher than the RMSE values of the other two types of models (ZTD and temperature) in winter, respectively. (3) The introduction of the empirical Bayesian kriging method to interpolate the residuals of the models (GWR and MGWR) and to then correct the original interpolation results of the models was the most effective, and the accuracy improvement percentage was better than that of the ordinary kriging method. The average improvement ratios of the GWRK and GWR-EBK models compared with that of the GWR model were 5.04% and 14.74%, respectively, and the average improvement ratios of the MGWRK and MGWR-EBK models compared with that of the MGWR model were 2.79% and 12.66%, respectively. (4) Elevation intervals and provinces were classified, and the influence of the elevation and the spatial distribution of the plane on the accuracy of the PM2.5 regional model was discussed. The experiments showed that the accuracy of the constructed regional model decreased as the elevation increased. The accuracies of the models in representing Henan, Hubei and Hunan provinces were lower than those of the models in representing Guangdong and Guangxi provinces.

Prediction of Nickel Concentrations in Urban and Peri-Urban Soils: Application of a Hybridized Empirical Bayesian Kriging and Support Vector Machine Regression Approach

Soil pollution is a big issue caused by anthropogenic activities. The spatial distribution of potentially toxic elements (PTEs) varies in most urban and peri-urban areas. As a result, spatially predicting the PTEs content in such soil is difficult. A total number of 115 samples were obtained from Frydek Mistek in the Czech Republic. Calcium(Ca), magnesium(Mg), potassium(K), and nickel (Ni) concentrations were determined using Inductively Coupled Plasma Optical Emission Spectroscopy. The correlation matrix between the response variable and the predictors revealed a satisfactory correlation between the elements. The prediction results indicated that support vector machine regression (SVMR) performed well although its estimated root mean square error (RMSE) (235.974) and mean absolute error (MAE) (166.946) were higher when compared with the other methods applied. Conversely, the hybridized model of empirical bayesian kriging -multiple linear regression (EBK-MLR) performed poorly as indicated by the measured coefficient of determination value below 0.1. The empirical bayesian kriging-support vector machine regression (EBK-SVMR) model was the best model, with low RMSE (95.479) and MAE (77.368) values and a high coefficient of determination (R2 = 0.637). EBK-SVMR modeling technique was visualized using self-organizing map. The clustered neurons of the hybridized model CakMg -EBK-SVMR component plane showed a diverse color pattern predicting the concentration of Ni in the urban and peri urban soil. The results proved that combining EBK and SVMR is an effective technique for predicting Ni concentrations in urban and peri-urban soil.

Correction of P/S Amplitude Ratios for Low-Magnitude Seismic Events Based on Bayesian Kriging Method

ABSTRACT Classification of low-magnitude seismic events is a challenging issue for the Comprehensive Nuclear-Test-Ban Treaty. Path correction of the P/S amplitude ratio is the key to identifying earthquakes and explosions. In this article, the Bayesian Kriging interpolation method is used to conduct the path correction of P/S amplitude ratios and recognition of low-magnitude seismic events. Based on a total of 5677 small earthquakes and 1769 explosions in Beijing and its adjacent areas, the Bayesian Kriging method is used to establish the path correction surface and uncertainty surface of Pg/Lg amplitude ratios measured within different frequency bands at five seismic stations, and path correction of amplitude ratios is conducted for all events. The results show that the correction surface is consistent with the observed amplitude ratios, which can reflect the differences in their propagation paths to a certain extent. The root mean square variation of the amplitude ratio is reduced by a maximum of 30% and the misclassification probability is reduced by a maximum of 8.5% after the Kriging correction. The high-frequency Pg/Lg amplitude ratios can effectively classify low-magnitude events, and the misclassification probability at each station is less than 15% and 10% based on high-frequency Pg/Lg of >7 and >9 Hz, respectively. Of the five stations, BJT (Baijiatuan, Beijing) has the best recognition, with the misclassification probability being lower than 5% after Kriging correction based on high-frequency Pg/Lg (>9 Hz). The classification ability of high-frequency amplitude ratios (>15 Hz) is weakened due to high-frequency noises. Bayesian Kriging correction can reduce the variance in the amplitude ratio of low-magnitude seismic events and hence effectively improve the ability to classify small-magnitude events, which has an important reference value for regional seismic monitoring and identification.

Geospatial Situation Analysis for the Prediction of Possible Cases of Suicide Using EBK

This research presents the application of Empirical Bayesian Kriging, a geostatistical interpolation method. The case study is about suicide prevention. The dataset is composed of more than one million records, obtained from the report database of the Emergency Service 911 of the Mexican State of Aguascalientes. The purpose is to get prediction surfaces, probability, and standard error prediction for completed suicide cases. Here, the variations in the environment of suicide cases are relative to and dependent on economic, social, and cultural phenomena.

Bayesian Spatial and Trend Analysis on Ozone Extreme Data in South Korea: 1991–2015

Background. Extreme events like flooding, extreme temperature, and ozone depletion are happening in every corner of the world. Thus, the need to model such rare events having enormous damage has been getting priorities in most countries of the world. Methods. The dataset contains the ozone data from 29 representative air monitoring sites in South Korea collected from 1991 to 2015. Spatial generalized extreme value (GEV) using maximum likelihood estimation (MLE) and two max-stable and Bayesian kriging models are the statistical models used for analysis. Moreover, predictive performances of these statistical models are compared using measures like root-mean-squared error (RMSE), mean absolute error (MAE), relative bias (rBIAS), and relative mean separation (rMSEP) have been utilized. Results. From the time plot of ozone data, extreme ozone concentration is increasing linearly within the specified period. The return level of ozone concentration after 10, 25, 50, and 100 years have been forecasted and showed that there was an increasing trend in ozone extremes. High spatial variability of ozone extreme was observed, and those areas around the territories were having extreme ozone concentration than the centers. Moreover, Bayesian Kriging brought about relatively the minimum RMSE compared to the other models. Conclusion. The extreme ozone concentration has clearly showed a positive trend and spatial variation. Moreover, among the models considered in the paper, the Bayesian Kriging has been chosen as the better model.