Continuous Bayesian networks for probabilistic environmental risk mapping

Bayesian networks (BNs) are being increasingly applied to environmental research. Nonetheless, most of the literature related to environmental sciences use discrete or discretized data, which entails a loss of information. We propose a novel methodology based on continuous BNs to predict the probability that surface waters do not meet the standards, in relation to nitrate concentration, established by the European Water Framework Directive. In order to achieve our purpose, a Tree Augmented Naive Bayes (TAN), was developed and applied to estimate and map the risk of failing to meet the European standards established. The TAN models were tested by means of the k-fold cross validation method. The results revealed that the TAN model performed proper risk maps and suggested that poor water quality is highly probable in watersheds dominated by irrigated herbaceous crops. On the contrary, “good surface water status” is more likely to occur in areas where forest is notably present.     

Comparison of sparse‐grid geometric and random sampling methods in nonlinear inverse solution uncertainty estimation

A new uncertainty estimation method, which we recently introduced in the literature, allows for the comprehensive search of model posterior space while maintaining a high degree of computational efficiency. The method starts with an optimal solution to an inverse problem, performs a parameter reduction step and then searches the resulting feasible model space using prior parameter bounds and sparse‐grid polynomial interpolation methods. After misfit rejection, the resulting model ensemble represents the equivalent model space and can be used to estimate inverse solution uncertainty. While parameter reduction introduces a posterior bias, it also allows for scaling this method to higher dimensional problems. The use of Smolyak sparse‐grid interpolation also dramatically increases sampling efficiency for large stochastic dimensions. Unlike Bayesian inference, which treats the posterior sampling problem as a random process, this geometric sampling method exploits the structure and smoothness in posterior distributions by solving a polynomial interpolation problem and then resampling from the resulting interpolant. The two questions we address in this paper are 1) whether our results are generally compatible with established Bayesian inference methods and 2) how does our method compare in terms of posterior sampling efficiency. We accomplish this by comparing our method for two electromagnetic problems from the literature with two commonly used Bayesian sampling schemes: Gibbs’ and Metropolis‐Hastings. While both the sparse‐grid and Bayesian samplers produce compatible results, in both examples, the sparse‐grid approach has a much higher sampling efficiency, requiring an order of magnitude fewer samples, suggesting that sparse‐grid methods can significantly improve the tractability of inference solutions for problems in high dimensions or with more costly forward physics.     

Comparison of parameter uncertainty analysis techniques for a TOPMODEL application

Parameter uncertainty in hydrologic modeling is crucial to the flood simulation and forecasting. The Bayesian approach allows one to estimate parameters according to prior expert knowledge as well as observational data about model parameter values. This study assesses the performance of two popular uncertainty analysis (UA) techniques, i.e., generalized likelihood uncertainty estimation (GLUE) and Bayesian method implemented with the Markov chain Monte Carlo sampling algorithm, in evaluating model parameter uncertainty in flood simulations. These two methods were applied to the semi-distributed Topographic hydrologic model (TOPMODEL) that includes five parameters. A case study was carried out for a small humid catchment in the southeastern China. The performance assessment of the GLUE and Bayesian methods were conducted with advanced tools suited for probabilistic simulations of continuous variables such as streamflow. Graphical tools and scalar metrics were used to test several attributes of the simulation quality of selected flood events: deterministic accuracy and the accuracy of 95 % prediction probability uncertainty band (95PPU). Sensitivity analysis was conducted to identify sensitive parameters that largely affect the model output results. Subsequently, the GLUE and Bayesian methods were used to analyze the uncertainty of sensitive parameters and further to produce their posterior distributions. Based on their posterior parameter samples, TOPMODEL’s simulations and the corresponding UA results were conducted. Results show that the form of exponential decline in conductivity and the overland flow routing velocity were sensitive parameters in TOPMODEL in our case. Small changes in these two parameters would lead to large differences in flood simulation results. Results also suggest that, for both UA techniques, most of streamflow observations were bracketed by 95PPU with the containing ratio value larger than 80 %. In comparison, GLUE gave narrower prediction uncertainty bands than the Bayesian method. It was found that the mode estimates of parameter posterior distributions are suitable to result in better performance of deterministic outputs than the 50 % percentiles for both the GLUE and Bayesian analyses. In addition, the simulation results calibrated with Rosenbrock optimization algorithm show a better agreement with the observations than the UA’s 50 % percentiles but slightly worse than the hydrographs from the mode estimates. The results clearly emphasize the importance of using model uncertainty diagnostic approaches in flood simulations.     

Generalized likelihood uncertainty estimation (GLUE) using adaptive Markov Chain Monte Carlo sampling

In the last few decades hydrologists have made tremendous progress in using dynamic simulation models for the analysis and understanding of hydrologic systems. However, predictions with these models are often deterministic and as such they focus on the most probable forecast, without an explicit estimate of the associated uncertainty. This uncertainty arises from incomplete process representation, uncertainty in initial conditions, input, output and parameter error. The generalized likelihood uncertainty estimation (GLUE) framework was one of the first attempts to represent prediction uncertainty within the context of Monte Carlo (MC) analysis coupled with Bayesian estimation and propagation of uncertainty. Because of its flexibility, ease of implementation and its suitability for parallel implementation on distributed computer systems, the GLUE method has been used in a wide variety of applications. However, the MC based sampling strategy of the prior parameter space typically utilized in GLUE is not particularly efficient in finding behavioral simulations. This becomes especially problematic for high-dimensional parameter estimation problems, and in the case of complex simulation models that require significant computational time to run and produce the desired output. In this paper we improve the computational efficiency of GLUE by sampling the prior parameter space using an adaptive Markov Chain Monte Carlo scheme (the Shuffled Complex Evolution Metropolis (SCEM-UA) algorithm). Moreover, we propose an alternative strategy to determine the value of the cutoff threshold based on the appropriate coverage of the resulting uncertainty bounds. We demonstrate the superiority of this revised GLUE method with three different conceptual watershed models of increasing complexity, using both synthetic and real-world streamflow data from two catchments with different hydrologic regimes.     

Stochastic delineation of capture zones: classical versus Bayesian approach

A Bayesian approach to characterize the predictive uncertainty in the delineation of time-related well capture zones in heterogeneous formations is presented and compared with the classical or non-Bayesian approach. The transmissivity field is modelled as a random space function and conditioned on distributed measurements of the transmissivity. In conventional geostatistical methods the mean value of the log transmissivity and the functional form of the covariance and its parameters are estimated from the available measurements, and then entered into the prediction equations as if they are the true values. However, this classical approach accounts only for the uncertainty that stems from the lack of ability to exactly predict the transmissivity at unmeasured locations. In reality, the number of measurements used to infer the statistical properties of the transmissvity field is often limited, which introduces error in the estimation of the structural parameters. The method presented accounts for the uncertainty that originates from the imperfect knowledge of the parameters by treating them as random variables. In particular, we use Bayesian methods of inference so as to make proper allowance for the uncertainty associated with estimating the unknown values of the parameters. The classical and Bayesian approach to stochastic capture zone delineation are detailed and applied to a hypothetical flow field. Two different sampling densities on a regular grid are considered to evaluate the effect of data density in both methods. Results indicate that the predictions of the Bayesian approach are more conservative.     

Bayesian approach to contaminant source characterization in water distribution systems: adaptive sampling framework

Bayesian analysis can yield a probabilistic contaminant source characterization conditioned on available sensor data and accounting for system stochastic processes. This paper is based on a previously proposed Markov chain Monte Carlo (MCMC) approach tailored for water distribution systems and incorporating stochastic water demands. The observations can include those from fixed sensors and, the focus of this paper, mobile sensors. Decision makers, such as utility managers, need not wait until new observations are available from an existing sparse network of fixed sensors. This paper addresses a key research question: where is the best location in the network to gather additional measurements so as to maximize the reduction in the source uncertainty? Although this has been done in groundwater management, it has not been well addressed in water distribution networks. In this study, an adaptive framework is proposed to guide the strategic placement of mobile sensors to complement the fixed sensor network. MCMC is the core component of the proposed adaptive framework, while several other pieces are indispensable: Bayesian preposterior analysis, value of information criterion and the search strategy for identifying an optimal location. Such a framework is demonstrated with an illustrative example, where four candidate sampling locations in the small water distribution network are investigated. Use of different value-of-information criteria reveals that while each may lead to different outcomes, they share some common characteristics. The results demonstrate the potential of Bayesian analysis and the MCMC method for contaminant event management.     

Hydrologic drought prediction under climate change: Uncertainty modeling with Dempster–Shafer and Bayesian approaches

Representation and quantification of uncertainty in climate change impact studies are a difficult task. Several sources of uncertainty arise in studies of hydrologic impacts of climate change, such as those due to choice of general circulation models (GCMs), scenarios and downscaling methods. Recently, much work has focused on uncertainty quantification and modeling in regional climate change impacts. In this paper, an uncertainty modeling framework is evaluated, which uses a generalized uncertainty measure to combine GCM, scenario and downscaling uncertainties. The Dempster–Shafer (D–S) evidence theory is used for representing and combining uncertainty from various sources. A significant advantage of the D–S framework over the traditional probabilistic approach is that it allows for the allocation of a probability mass to sets or intervals, and can hence handle both aleatory or stochastic uncertainty, and epistemic or subjective uncertainty. This paper shows how the D–S theory can be used to represent beliefs in some hypotheses such as hydrologic drought or wet conditions, describe uncertainty and ignorance in the system, and give a quantitative measurement of belief and plausibility in results. The D–S approach has been used in this work for information synthesis using various evidence combination rules having different conflict modeling approaches. A case study is presented for hydrologic drought prediction using downscaled streamflow in the Mahanadi River at Hirakud in Orissa, India. Projections of n most likely monsoon streamflow sequences are obtained from a conditional random field (CRF) downscaling model, using an ensemble of three GCMs for three scenarios, which are converted to monsoon standardized streamflow index (SSFI-4) series. This range is used to specify the basic probability assignment (bpa) for a Dempster–Shafer structure, which represents uncertainty associated with each of the SSFI-4 classifications. These uncertainties are then combined across GCMs and scenarios using various evidence combination rules given by the D–S theory. A Bayesian approach is also presented for this case study, which models the uncertainty in projected frequencies of SSFI-4 classifications by deriving a posterior distribution for the frequency of each classification, using an ensemble of GCMs and scenarios. Results from the D–S and Bayesian approaches are compared, and relative merits of each approach are discussed. Both approaches show an increasing probability of extreme, severe and moderate droughts and decreasing probability of normal and wet conditions in Orissa as a result of climate change.     

Uncertainty estimation of a complex water quality model: The influence of Box–Cox transformation on Bayesian approaches and comparison with a non-Bayesian method

In urban drainage modelling, uncertainty analysis is of undoubted necessity. However, uncertainty analysis in urban water-quality modelling is still in its infancy and only few studies have been carried out. Therefore, several methodological aspects still need to be experienced and clarified especially regarding water quality modelling. The use of the Bayesian approach for uncertainty analysis has been stimulated by its rigorous theoretical framework and by the possibility of evaluating the impact of new knowledge on the modelling predictions. Nevertheless, the Bayesian approach relies on some restrictive hypotheses that are not present in less formal methods like the Generalised Likelihood Uncertainty Estimation (GLUE). One crucial point in the application of Bayesian method is the formulation of a likelihood function that is conditioned by the hypotheses made regarding model residuals. Statistical transformations, such as the use of Box–Cox equation, are generally used to ensure the homoscedasticity of residuals. However, this practice may affect the reliability of the analysis leading to a wrong uncertainty estimation. The present paper aims to explore the influence of the Box–Cox equation for environmental water quality models. To this end, five cases were considered one of which was the “real” residuals distributions (i.e. drawn from available data). The analysis was applied to the Nocella experimental catchment (Italy) which is an agricultural and semi-urbanised basin where two sewer systems, two wastewater treatment plants and a river reach were monitored during both dry and wet weather periods. The results show that the uncertainty estimation is greatly affected by residual transformation and a wrong assumption may also affect the evaluation of model uncertainty. The use of less formal methods always provide an overestimation of modelling uncertainty with respect to Bayesian method but such effect is reduced if a wrong assumption is made regarding the residuals distribution. If residuals are not normally distributed, the uncertainty is over-estimated if Box–Cox transformation is not applied or non-calibrated parameter is used.     

Improving monthly streamflow prediction in alpine regions: integrating HBV model with Bayesian neural network

Statistical methods have been widely used to build different streamflow prediction models; however, lacking of physical mechanism prevents precise streamflow prediction in alpine regions dominated by rainfall, snow and glacier. To improve precision, a new hybrid model (HBNN) integrating HBV hydrological model, Bayesian neural network (BNN) and uncertainty analysis is proposed. In this approach, the HBV is mainly used to generate initial snow-melt and glacier-melt runoffs that are regarded as new inputs of BNN for precision improvement. To examine model reliability, a hybrid deterministic model called HLSSVM incorporating the HBV model and least-square support vector machine is also developed and compared with HBNN in a typical region, the Yarkant River basin in Central Asia. The findings suggest that the HBNN model is a robust streamflow prediction model for alpine regions and capable of combining strengths of both the BNN statistical model and the HBV hydrological model, providing not only more precise streamflow prediction but also more reasonable uncertainty intervals than competitors particularly at high flows. It can be used in predicting streamflow for similar regions worldwide.     

Bayesian flood frequency analysis in the light of model and parameter uncertainties

The specific objective of the paper is to propose a new flood frequency analysis method considering uncertainty of both probability distribution selection (model uncertainty) and uncertainty of parameter estimation (parameter uncertainty). Based on Bayesian theory sampling distribution of quantiles or design floods coupling these two kinds of uncertainties is derived, not only point estimator but also confidence interval of the quantiles can be provided. Markov Chain Monte Carlo is adopted in order to overcome difficulties to compute the integrals in estimating the sampling distribution. As an example, the proposed method is applied for flood frequency analysis at a gauge in Huai River, China. It has been shown that the approach considering only model uncertainty or parameter uncertainty could not fully account for uncertainties in quantile estimations, instead, method coupling these two uncertainties should be employed. Furthermore, the proposed Bayesian-based method provides not only various quantile estimators, but also quantitative assessment on uncertainties of flood frequency analysis.     

Uncertainty-based multi-criteria calibration of rainfall-runoff models: a comparative study

This study compares formal Bayesian inference to the informal generalized likelihood uncertainty estimation (GLUE) approach for uncertainty-based calibration of rainfall-runoff models in a multi-criteria context. Bayesian inference is accomplished through Markov Chain Monte Carlo (MCMC) sampling based on an auto-regressive multi-criteria likelihood formulation. Non-converged MCMC sampling is also considered as an alternative method. These methods are compared along multiple comparative measures calculated over the calibration and validation periods of two case studies. Results demonstrate that there can be considerable differences in hydrograph prediction intervals generated by formal and informal strategies for uncertainty-based multi-criteria calibration. Also, the formal approach generates definitely preferable validation period results compared to GLUE (i.e., tighter prediction intervals that show higher reliability) considering identical computational budgets. Moreover, non-converged MCMC (based on the standard Gelman–Rubin metric) performance is reasonably consistent with those given by a formal and fully-converged Bayesian approach even though fully-converged results requires significantly larger number of samples (model evaluations) for the two case studies. Therefore, research to define alternative and more practical convergence criteria for MCMC applications to computationally intensive hydrologic models may be warranted.     

Response to comment by Keith Beven on “Equifinality of formal (DREAM) and informal (GLUE) Bayesian approaches in hydrologic modeling?”

In recent years, a strong debate has emerged in the hydrologic literature regarding what constitutes an appropriate framework for uncertainty estimation. Particularly, there is strong disagreement whether an uncertainty framework should have its roots within a proper statistical (Bayesian) context, or whether such a framework should be based on a different philosophy and implement informal measures and weaker inference to summarize parameter and predictive distributions. In this paper, we compare a formal Bayesian approach using Markov Chain Monte Carlo (MCMC) with generalized likelihood uncertainty estimation (GLUE) for assessing uncertainty in conceptual watershed modeling. Our formal Bayesian approach is implemented using the recently developed differential evolution adaptive metropolis (DREAM) MCMC scheme with a likelihood function that explicitly considers model structural, input and parameter uncertainty. Our results demonstrate that DREAM and GLUE can generate very similar estimates of total streamflow uncertainty. This suggests that formal and informal Bayesian approaches have more common ground than the hydrologic literature and ongoing debate might suggest. The main advantage of formal approaches is, however, that they attempt to disentangle the effect of forcing, parameter and model structural error on total predictive uncertainty. This is key to improving hydrologic theory and to better understand and predict the flow of water through catchments.     

电磁法观测系统采样时钟不确定度及误差研究

电磁法观测系统中,采样时钟质量直接影响高精度ADC的信噪比,而高精度ADC芯片的信噪比作为电磁法观测系统信号检测非常关键的指标,决定了获取数据的质量.采样时钟的时间抖动是时钟孔径不确定度产生的原因,导致电磁法观测系统中ADC数据转换的信噪比变差,严重影响电磁系统观测质量,为此提出了ADC采样时钟不确定度最大时间抖动的确定方法.该方法通过对ADC采样过程进行时域、频域分析,借助正弦波导数给出采样时钟孔径不确定度引起的采样数据误差数学描述,结合极大值法与ADC信噪比计算方法获取系统信噪比需求范围内的最差时钟孔径不确定度,进而计算出相应采样时钟的最大时间抖动误差.以地球物理仪器中常用的ADC芯片AD7760为例进行了相应的时钟抖动误差计算,确定时钟的孔径不确定度抖动时间.根据信噪比指标确定了时钟孔径不确定度后,采用压控恒温晶振跟踪GPS信号中的秒脉冲的方法,保证时钟抖动误差能够满足AD7760的要求,根据测试表明,在GPS失锁4 h内,时钟输出能够满足技术要求.

     

Combining climate model output via model correlations

In climate science, collections of climate model output, usually referred to as ensembles, are commonly used devices to study uncertainty in climate model experiments. The ensemble members may reflect variation in initial conditions, different physics implementations, or even entirely different climate models. However, there is a need to deliver a unified product based on the ensemble members that reflects the information contained in whole of the ensemble. We propose a technique for creating linear combinations of ensemble members where the weights are constructed from estimates of variation and correlation both within and between ensemble members. At the heart of this approach is a Bayesian hierarchical model that allows for estimation of the correlation between ensemble members as well as the study of the impact of uncertainty in the parameter estimates of the hierarchical model on the weights. The approach is demonstrated on an ensemble of regional climate model (RCM) output.     

Seismic Tomography by Monte Carlo Sampling

The paper discusses the performance and robustness of the Bayesian (probabilistic) approach to seismic tomography enhanced by the numerical Monte Carlo sampling technique. The approach is compared with two other popular techniques, namely the damped least-squares (LSQR) method and the general optimization approach. The theoretical considerations are illustrated by an analysis of seismic data from the Rudna (Poland) copper mine. Contrary to the LSQR and optimization techniques the Bayesian approach allows for construction of not only the “best-fitting” model of the sought velocity distribution but also other estimators, for example the average model which is often expected to be a more robust estimator than the maximum likelihood solution. We demonstrate that using the Markov Chain Monte Carlo sampling technique within the Bayesian approach opens up the possibility of analyzing tomography imaging uncertainties with minimal additional computational effort compared to the robust optimization approach. On the basis of the considered example it is concluded that the Monte Carlo based Bayesian approach offers new possibilities of robust and reliable tomography imaging.     

River flow modelling: comparison of performance and evaluation of uncertainty using data-driven models and conceptual hydrological model

Hydrological and statistical models are playing an increasing role in hydrological forecasting, particularly for river basins with data of different temporal scales. In this study, statistical models, e.g. artificial neural networks, adaptive network-based fuzzy inference system, genetic programming, least squares support vector machine, multiple linear regression, were developed, based on parametric optimization methods such as particle swarm optimization (PSO), genetic algorithm (GA), and data-preprocessing techniques such as wavelet decomposition (WD) for river flow modelling using daily streamflow data from four hydrological stations for a period of 1954–2009. These models were used for 1-, 3- and 5-day streamflow forecasting and the better model was used for uncertainty evaluation using bootstrap resampling method. Meanwhile, a simple conceptual hydrological model GR4J was used to evaluate parametric uncertainty based on generalized likelihood uncertainty estimation method. Results indicated that: (1) GA and PSO did not help improve the forecast performance of the model. However, the hybrid model with WD significantly improved the forecast performance; (2) the hybrid model with WD as a data preprocessing procedure can clarify hydrological effects of water reservoirs and can capture peak high/low flow changes; (3) Forecast accuracy of data-driven models is significantly influenced by the availability of streamflow data. More human interferences from the upper to the lower East River basin can help to introduce greater uncertainty in streamflow forecasts; (4) The structure of GR4J may introduce larger parametric uncertainty at the Longchuan station than at the Boluo station in the East river basin. This study provides a theoretical background for data-driven model-based streamflow forecasting and a comprehensive view about data and parametric uncertainty in data-scarce river basins.     

Equifinality of formal (DREAM) and informal (GLUE) Bayesian approaches in hydrologic modeling?

In recent years, a strong debate has emerged in the hydrologic literature regarding what constitutes an appropriate framework for uncertainty estimation. Particularly, there is strong disagreement whether an uncertainty framework should have its roots within a proper statistical (Bayesian) context, or whether such a framework should be based on a different philosophy and implement informal measures and weaker inference to summarize parameter and predictive distributions. In this paper, we compare a formal Bayesian approach using Markov Chain Monte Carlo (MCMC) with generalized likelihood uncertainty estimation (GLUE) for assessing uncertainty in conceptual watershed modeling. Our formal Bayesian approach is implemented using the recently developed differential evolution adaptive metropolis (DREAM) MCMC scheme with a likelihood function that explicitly considers model structural, input and parameter uncertainty. Our results demonstrate that DREAM and GLUE can generate very similar estimates of total streamflow uncertainty. This suggests that formal and informal Bayesian approaches have more common ground than the hydrologic literature and ongoing debate might suggest. The main advantage of formal approaches is, however, that they attempt to disentangle the effect of forcing, parameter and model structural error on total predictive uncertainty. This is key to improving hydrologic theory and to better understand and predict the flow of water through catchments.     

Investigating evidential reasoning for the interpretation of microbial water quality in a distribution network

Total coliforms are used as indicators for evaluating microbial water quality in distribution networks. However, total coliform provides only a weak “evidence” of possible fecal contamination because pathogens are subset of total coliform and therefore their presence in drinking water is not necessarily associated with fecal contamination. Heterotrophic plate counts are also commonly used to evaluate microbial water quality in the distribution networks, but they cover even a wider range of organisms. As a result, both of these indicators can provide incomplete and highly uncertain bodies of evidence when used individually. In this paper, it is shown that combing these two sources of information by an appropriate data fusion technique can provide improved insight into microbial water quality within distribution networks. Approximate reasoning methods like fuzzy logic and probabilistic reasoning are commonly used for data fusion where knowledge is uncertain (i.e., ambiguous, incomplete, and/or vague). Traditional probabilistic frameworks like Bayesian analysis, reasons through conditioning based on prior probabilities (which are hardly ever available). The Dempster–Shafer (DS) theory generalizes the Bayesian analysis without requiring prior probabilities. The DS theory can efficiently deal with the difficulties related to the interpretation of overall water quality where the redundancy of information is routinely observed and the credibility of available data continuously changes. In this paper, the DS rule of combination and its modifications including Yager’s modified rule, Dubois–Prade disjunctive rule and Dezert–Smarandache rule are described using an example of microbial water quality in a distribution network.     

Species distribution modeling: a statistical review with focus in spatio-temporal issues

The use of complex statistical models has recently increased substantially in the context of species distribution behavior. This complexity has made the inferential and predictive processes challenging to perform. The Bayesian approach has become a good option to deal with these models due to the ease with which prior information can be incorporated along with the fact that it provides a more realistic and accurate estimation of uncertainty. In this paper, we first review the sources of information and different approaches (frequentist and Bayesian) to model the distribution of a species. We also discuss the Integrated Nested Laplace approximation as a tool with which to obtain marginal posterior distributions of the parameters involved in these models. We finally discuss some important statistical issues that arise when researchers use species data: the presence of a temporal effect (presenting different spatial and spatio-temporal structures), preferential sampling, spatial misalignment, non-stationarity, imperfect detection, and the excess of zeros.