Environmetrics

A diagnostic method for space-time point process is introduced and used to interpret and assess the goodness of fit of particular models to real data such as the seismic ones. The proposed method is founded on the definition of a weighted process and allows to detect second-order features of data, like long-range dependence and fractal behavior, that are not accounted for by the fitted model. Applications to earthquake data are provided. Copyright © 2008 John Wiley & Sons, Ltd.

The PROMETHEUS model is a spatially explicit, deterministic fire growth model, praised for being beneficial in various aspects of fire management. Our goal is to build on this success, applying statistical smoothing to alleviate some computational difficulties and to increase accuracy; a pleasant by-product is the opportunity to introduce stochasticity to the model using a residual-based block bootstrap. Copyright © 2008 John Wiley & Sons, Ltd.

The global sensitivity analysis of a complex numerical model often calls for the estimation of variance-based importance measures, named Sobol' indices. Metamodel-based techniques have been developed in order to replace the cpu time-expensive computer code with an inexpensive mathematical function, which predicts the computer code output. The common metamodel-based sensitivity analysis methods are well-suited for computer codes with scalar outputs. However, in the environmental domain, as in many areas of application, the numerical model outputs are often spatial maps, which may also vary with time. In this paper, we introduce an innovative method to obtain a spatial map of Sobol' indices with a minimal number of numerical model computations. It is based upon the functional decomposition of the spatial output onto a wavelet basis and the metamodeling of the wavelet coefficients by the Gaussian process. An analytical example is presented to clarify the various steps of our methodology. This technique is then applied to a real hydrogeological case: for each model input variable, a spatial map of Sobol' indices is thus obtained.

In the last two decades, increasing attention has been given to air pollution around the world, mainly because of its impact on human health and on the environment. In the Po valley (northern Italy), one of the most troublesome pollutant is PM10 (particulate matter with an aerodynamic diameter of less than 10  μm). In order to assess PM10 concentration over an entire region, environmental agencies need models to predict PM10 at unmonitored sites. To choose among possible predictive models and then meet the agencies' request, we focus on the class of Bayesian hierarchical models as they provide a flexible framework for incorporating relevant covariates as well as spatio-temporal interactions. We consider six alternative models for PM10 concentration in Piemonte region (north-western Po Valley), during the winter season October 2005–March 2006. Our aim is to choose a model that is satisfactory in terms of goodness of fit, interpretability, parsimony, prediction capability and computational costs. In order to support this choice, we propose a comparison approach based on a set of criteria summarized in a table that can be easily communicated to non-statisticians. The comparison findings allow to provide Piemonte environmental agencies with an effective statistical model for building reliable PM10 concentration maps, equipped with the corresponding uncertainty measure. Copyright © 2011 John Wiley & Sons, Ltd.

Ab s t r a c t Assessing water quality of the ex-mining ponds for its proper utilization is pertinent considering the metal pollutants and lack of proper environmental measures is associated with the mining operations. In this study, water samples from 13 man-made lakes including 8 ex-mining ponds in the Klang Valley, Malaysia were analyzed for dissolved oxygen, suspended solid, pH, electrical conductivity (EC), biological oxygen demand (BOD), ammoniacal nitrogen (AN), total dissolved solid (TDS), and metals including As, Cd, Pb, Mn, Fe, Na, Mg, and Ca. The variations in these parameters were evaluated with the chemometric techniques. The results from the principal component analysis and hierarchical cluster analysis suggested that in addition to the degree of contamination, the variations in heavy metal concentrations were mainly attributed to the ex-mining activities, whereas deviations in BOD, TDS, AN, and EC were subjected to the current domestic inputs. The linear discriminant analysis showed that water samples from the ex-mining ponds were highly associated with Mn, Cd, Ca, and As. The As and Cd levels recorded in most of the ex-mining ponds were 11.3 ± 0.4, 116 ± 2, and 42 ± 0.5 µg/L; and 12.9 ± 0.2, 12.23 ± 0.02, 12.19 ± 0.01, and 12.15 ± 0.01 µg/L, respectively. These values surpassed the reference limits, which make them unfit for domestic uses.

This paper describes a simulation tool to aid the design of nutrient monitoring programmes in coastal waters. The tool is developed by using time series of water quality data from a Smart Buoy, an in situ monitoring device. The tool models the seasonality and temporal dependence in the data and then filters out these features to leave a white noise series. New data sets are then simulated by sampling from the white noise series and re-introducing the modelled seasonality and temporal dependence. Simulating many independent realisations allows us to study the performance of different monitoring designs and assessment methods. We illustrate the approach using total oxidised nitrogen (TOxN) and chlorophyll data from Liverpool Bay, U.K. We consider assessments of whether the underlying mean concentrations of these water quality variables are sufficiently low; i.e. below specified assessment concentrations. We show that for TOxN, even when mean concentrations are at background, daily data from a Smart Buoy or multi-annual sampling from a research vessel would be needed to obtain adequate power. Copyright © 2009 Crown Copyright

The bank and open water vegetation along El-Salam Canal in north-eastern Egypt were studied in relation to the prevailing environmental factors. The hypothesis that terresterial and aquatic species would show different downstream patterns of species richness was tested by sampling species composition and environmental variables along 80 km of the canal. Species richness was highest in the first 30 km of the canal. The downstream decrease in species richness exhibits interpretable downstream patterns. Total species richness increased with increasing organic matter in the soil and decreased with both increasing soil and water salinity along the gradient.The indicator species of TWINSPAN analysis are: Azolla filiculoides, Echinochloa stagnina, Eichhornia crassipes and Saccharum spontaneum (cluster I); Ceratophyllum demersum, Ludwigia stolonifera and Typha domingensis (cluster II); Potamogeton pectinatus and Phragmites australis (cluster III); Tamarix nilotica and Suaeda vera (cluster IV).The environmental factors influencing the vegetation clusters were analysed using canonical correspondence analysis ordination (CCA). The water salinity, total nitrogen and total phosphorus appeared to be the most important factors controlling the abundance of aquatic plant distribution along the canal. The shoreline vegetation is mainly controlled by salinity, K+ and organic carbon of the soil.Water analysis indicated that the salinity of the water increases southwards and the minimum salinity of the water (0.78 mS/cm) was recorded at the intake of the canal. The maximum value (7.5 mS/cm) of water salinity was recorded near the Suez Canal. Copyright © 2001 John Wiley & Sons, Ltd.

In this article, we present an application of models with temporal and spatial components, from the Bayesian point of view, on data pollutants collected in 16 different monitoring sites located in the Metropolitan Area of Rio de Janeiro during 1999. All the models considered here assume conditionally independent observations, with a mean specified by the sum of random temporal and spatial components and a linear function of the maximum daily temperature and indicators of the day of the week. Our aim here is to analyze distinct specifications for the components, assuming different kinds of modeling that are not usually compared. The comparison is based on the posterior predictive loss function proposed by Gelfand and Ghosh (1998). The best specifications for the spatial component were the ones which considered a geostatistical approach to its correlation function. The best specification for the temporal component was the stationary autoregressive form. The pollutant concentrations were interpolated in a grid of points in the area of higher population density at a fixed period of time for the selected model. Copyright © 2003 John Wiley & Sons, Ltd.

The existence of missing observations (MO) is commonly solved by using imputation methods. There are ratio-based methods for estimating the population mean, while using simple random sampling (SRS), when MO are present. Considering the existence of MO and using of ranked set sampling, we develop a study of the estimation of a population mean using ratio-based methods. The mean square errors, bias, and gain in accuracy formulas of the suggested estimators are derived. The suggested estimators are compared with their SRS counterpart both theoretically and numerically. Copyright © 2014 John Wiley & Sons, Ltd.

This research investigates the relationship between the physicochemical levels and the drinking water quality in Kuala Kubu Bharu, Selangor, Malaysia based on three different classes of drinking water. The environmetric techniques such as the discriminant analysis (DA), the principal component analysis (PCA) and the factor analysis (FA) were applied to analyze the spatial variation of the most significant physicochemical parameters of the drinking water quality and to determine the source of pollution. Seven physicochemical variables were analyzed. The forward and backward stepwise DA managed to discriminate six and two variables, respectively from the original seven variables. PCA and FA (varimax functionality) were to identify the origin of each water quality variable based on the three different drinking water classes. This study shows that environmetric method is the ideal way into provide meaningful information on the spatial variability of sophisticated drinking water quality data.