Monte Carlo Approximate Bayesian Computation Research Articles

Calibration of cellular automata urban growth models from urban genesis onwards - a novel application of Markov chain Monte Carlo approximate Bayesian computation

Cellular Automata (CA) models are widely used to study spatial dynamics of urban growth and evolving patterns of land use. One complication across CA approaches is the relatively short period of data available for calibration, providing sparse information on patterns of change and presenting problematic signal-to-noise ratios. To overcome the problem of short-term calibration, this study investigates a novel approach in which the model is calibrated based on the urban morphological patterns that emerge from a simulation starting from urban genesis, i.e., a land cover map completely void of urban land. The application of the model uses the calibrated parameters to simulate urban growth forward in time from a known urban configuration.This approach to calibration is embedded in a new framework for the calibration and validation of a Constrained Cellular Automata (CCA) model of urban growth. The investigated model uses just four parameters to reflect processes of spatial agglomeration and preservation of scarce non-urban land at multiple spatial scales and makes no use of ancillary layers such as zoning, accessibility, and physical suitability. As there are no anchor points that guide urban growth to specific locations, the parameter estimation uses a goodness-of-fit (GOF) measure that compares the built density distribution inspired by the literature on fractal urban form. The model calibration is a novel application of Markov Chain Monte Carlo Approximate Bayesian Computation (MCMC-ABC). This method provides an empirical distribution of parameter values that reflects model uncertainty. The validation uses multiple samples from the estimated parameters to quantify the propagation of model uncertainty to the validation measures.The framework is applied to two UK towns (Oxford and Swindon). The results, including cross-application of parameters, show that the models effectively capture the different urban growth patterns of both towns. For Oxford, the CCA correctly produces the pattern of scattered growth in the periphery, and for Swindon, the pattern of compact, concentric growth. The ability to identify different modes of growth has both a theoretical and practical significance. Existing land use patterns can be an important indicator of future trajectories. Planners can be provided with insight in alternative future trajectories, available decision space, and the cumulative effect of parcel-by-parcel planning decisions.

Sheep scab transmission: a spatially explicit dynamic metapopulation model

Psoroptic mange (sheep scab), caused by the parasitic mite, Psoroptes ovis, is an important disease of sheep worldwide. It causes chronic animal welfare issues and economic losses. Eradication of scab has proved impossible in many sheep-rearing areas and recent reports of resistance to macrocyclic lactones, a key class of parasiticide, highlight the importance of improving approaches to scab management. To allow this, the current study aimed to develop a stochastic spatial metapopulation model for sheep scab transmission which can be adapted for use in any geographical region, exhibited here using data for Great Britain. The model uses agricultural survey and sheep movement data to geo-reference farms and capture realistic movement patterns. Reported data on sheep scab outbreaks from 1973 to 1991 were used for model fitting with Sequential Monte Carlo Approximate Bayesian Computation methods. The outbreak incidence predicted by the model was from the same statistical distribution as the reported outbreak data ({chi }^{2} = 115.3, p = 1) and the spatial location of sheep scab outbreaks predicted was positively correlated with the observed outbreak data by county (tau = 0.55, p < 0.001), confirming that the model developed is able to accurately capture the number of farms infected in a year, the seasonality of scab incidence and the spatial patterns seen in the data. This model gives insight into the transmission dynamics of sheep scab and will allow the exploration of more effective control strategies.

A comparison of approximate versus exact techniques for Bayesian parameter inference in nonlinear ordinary differential equation models.

The behaviour of many processes in science and engineering can be accurately described by dynamical system models consisting of a set of ordinary differential equations (ODEs). Often these models have several unknown parameters that are difficult to estimate from experimental data, in which case Bayesian inference can be a useful tool. In principle, exact Bayesian inference using Markov chain Monte Carlo (MCMC) techniques is possible; however, in practice, such methods may suffer from slow convergence and poor mixing. To address this problem, several approaches based on approximate Bayesian computation (ABC) have been introduced, including Markov chain Monte Carlo ABC (MCMC ABC) and sequential Monte Carlo ABC (SMC ABC). While the system of ODEs describes the underlying process that generates the data, the observed measurements invariably include errors. In this paper, we argue that several popular ABC approaches fail to adequately model these errors because the acceptance probability depends on the choice of the discrepancy function and the tolerance without any consideration of the error term. We observe that the so-called posterior distributions derived from such methods do not accurately reflect the epistemic uncertainties in parameter values. Moreover, we demonstrate that these methods provide minimal computational advantages over exact Bayesian methods when applied to two ODE epidemiological models with simulated data and one with real data concerning malaria transmission in Afghanistan.

In search of an effective Monte Carlo method for identification of atmospheric contamination source

We present the Bayesian framework able to identify the source of the airborne contaminant. We compare the effectiveness of framework utilizing the three popular Monte Carlo algorithms with the use of data from the full-scale Field experiment - Copenhagen Tracer Experiments. The input data ta are the on-line arriving concentrations of released substance registered by sensors, while the output are the posterior probabilities of four parameters characterizing the contamination source, i.e.: contamination source position (x,y,z) and release rate (q). As the forward model to predict the concentrations at the sensors locations, we use fast response Second-order Closure Integrated Puff model. The performer study present that among the Markov Chain Monte Carlo (MCMC), Sequential Monte Carlo (SMC) and Sequential Monte Carlo Approximate Bayesian Computation (SMC ABC) the last algorithm performed the best in the proposed framework localizing the airborne contaminant source parameters.

Bayesian calibration of force-fields from experimental data: TIP4P water.

Molecular dynamics (MD) simulations give access to equilibrium structures and dynamic properties given an ergodic sampling and an accurate force-field. The force-field parameters are calibrated to reproduce properties measured by experiments or simulations. The main contribution of this paper is an approximate Bayesian framework for the calibration and uncertainty quantification of the force-field parameters, without assuming parameter uncertainty to be Gaussian. To this aim, since the likelihood function of the MD simulation models is intractable in the absence of Gaussianity assumption, we use a likelihood-free inference scheme known as approximate Bayesian computation (ABC) and propose an adaptive population Monte Carlo ABC algorithm, which is illustrated to converge faster and scales better than the previously used ABCsubsim algorithm for the calibration of the force-field of a helium system. The second contribution is the adaptation of ABC algorithms for High Performance Computing to MD simulations within the Python ecosystem ABCpy. This adaptation includes a novel use of a dynamic allocation scheme for Message Passing Interface (MPI). We illustrate the performance of the developed methodology to learn posterior distribution and Bayesian estimates of Lennard-Jones force-field parameters of helium and the TIP4P system of water implemented for both simulated and experimental datasets collected using neutron and X-ray diffraction. For simulated data, the Bayesian estimate is in close agreement with the true parameter value used to generate the dataset. For experimental as well as for simulated data, the Bayesian posterior distribution shows a strong correlation pattern between the force-field parameters. Providing an estimate of the entire posterior distribution, our methodology also allows us to perform the uncertainty quantification of model prediction. This research opens up the possibility to rigorously calibrate force-fields from available experimental datasets of any structural and dynamic property.

Massively parallel approximate Bayesian computation for estimating nanoparticle diffusion coefficients, sizes and concentrations using confocal laser scanning microscopy.

We implement a massively parallel population Monte Carlo approximate Bayesian computation (PMC-ABC) method for estimating diffusion coefficients, sizes and concentrations of diffusing nanoparticles in liquid suspension using confocal laser scanning microscopy and particle tracking. The method is based on the joint probability distribution of diffusion coefficients and the time spent by a particle inside a detection region where particles are tracked. We present freely available central processing unit (CPU) and graphics processing unit (GPU) versions of the analysis software, and we apply the method to characterize mono- and bidisperse samples of fluorescent polystyrene beads.

Local Kernel Dimension Reduction in Approximate Bayesian Computation

Approximate Bayesian Computation (ABC) is a popular sampling method in applications involving intractable likelihood functions. Without evaluating the likelihood function, ABC approximates the posterior distribution by the set of accepted samples which are simulated with parameters drawn from the prior distribution, where acceptance is determined by the distance between the summary statistics of the sample and the observation. The sufficiency and dimensionality of the summary statistics play a central role in the application of ABC. This paper proposes Local Gradient Kernel Dimension Reduction (LGKDR) to construct low dimensional summary statistics for ABC. The proposed method identifies a sufficient subspace of the original summary statistics by implicitly considers all nonlinear transforms therein, and a weighting kernel is used for the concentration of the projections. No strong assumptions are made on the marginal distributions nor the regression model, permitting usage in a wide range of applications. Experiments are done with both simple rejection ABC and sequential Monte Carlo ABC methods. Results are reported as competitive in the former and substantially better in the latter cases in which Monte Carlo errors are compressed as much as possible.

Approximate Bayesian Computation in the estimation of the parameters of the Forbush decrease model

Realistic modeling of the complicated phenomena as Forbush decrease of the galactic cosmic ray intensity is a quite challenging task. One aspect is a numerical solution of the Fokker-Planck equation in five-dimensional space (three spatial variables, the time and particles energy). The second difficulty arises from a lack of detailed knowledge about the spatial and time profiles of the parameters responsible for the creation of the Forbush decrease. Among these parameters, the central role plays a diffusion coefficient. Assessment of the correctness of the proposed model can be done only by comparison of the model output with the experimental observations of the galactic cosmic ray intensity. We apply the Approximate Bayesian Computation (ABC) methodology to match the Forbush decrease model to experimental data. The ABC method is becoming increasing exploited for dynamic complex problems in which the likelihood function is costly to compute. The main idea of all ABC methods is to accept samples as an approximate posterior draw if its associated modeled data are close enough to the observed one. In this paper, we present application of the Sequential Monte Carlo Approximate Bayesian Computation algorithm scanning the space of the diffusion coefficient parameters. The proposed algorithm is adopted to create the model of the Forbush decrease observed by the neutron monitors at the Earth in March 2002. The model of the Forbush decrease is based on the stochastic approach to the solution of the Fokker-Planck equation.

Model selection and parameter estimation in tumor growth models using approximate Bayesian computation-ABC

Cancer is one of the most fatal diseases in the world. Governments and researchers from various areas have continuously concentrated efforts to better understand the disease and propose diagnostic and treatment techniques. The use of mathematical models of tumor growth is of great importance for the development of such techniques. Due to the variety of models nowadays available in the literature, the problems of model selection and parameter estimation come into picture, aiming at suitably predicting the patient’s status of the disease. As the available data on dependent variables of existing models might not justify the use of common likelihood functions, approximate Bayesian computation (ABC) becomes a very attractive tool for model selection and model calibration (parameter estimation) in tumor growth models. In the present study, a Monte Carlo approximate Bayesian computation (ABC) algorithm is applied to select among competing models of tumor growth, with and without chemotherapy treatment. Simulated measurements are used in this work. The results obtained show that the algorithm correctly selects the model and estimates the parameters used to generate the simulated measurements.

An approximate Bayesian computation approach to parameter estimation in a stochastic stage-structured population model.

Complex population processes may require equally complex models, which can lead to analytically intractable estimation problems. Approximate Bayesian computation (ABC) is a computational tool for parameter estimation in situations where likelihoods cannot be computed. Instead of using likelihoods, ABC methods quantify the similarities between an observed data set and repeated simulations from a model. A practical obstacle to implementing an ABC algorithm is selecting summary statistics and distance metrics that accurately capture the main features of the data. We demonstrate the application of a sequential Monte Carlo ABC sampler (ABC SMC) to parameter estimation of a general stochastic stage-structured population model with ongoing reproduction and heterogeneity in development and mortality. Individual variation in demographic traits has considerable consequences for population dynamics in many systems, but including it in a population model by explicitly allowing stage durations to follow a realistic distribution creates a complex model. We applied the ABC SMC to fit the model to a simulated representative data set with known underlying parameters to evaluate the performance of the algorithm. We also introduced a systematic method for selecting summary statistics and distance metrics, using simulated data and receiver operating characteristic (ROC) curves from classification theory. Evaluations suggest that the approach is promising for model inference in our example of realistic stage-structured population models.

Bayesian Symbol Detection in Wireless Relay Networks via Likelihood-Free Inference

This paper presents a general stochastic model developed for a class of cooperative wireless relay networks, in which imperfect knowledge of the channel state information at the destination node is assumed. The framework incorporates multiple relay nodes operating under general known non-linear processing functions. When a non-linear relay function is considered, the likelihood function is generally intractable resulting in the maximum likelihood and the maximum a posteriori detectors not admitting closed form solutions. We illustrate our methodology to overcome this intractability under the example of a popular optimal non-linear relay function choice and demonstrate how our algorithms are capable of solving the previously intractable detection problem. Overcoming this intractability involves development of specialised Bayesian models. We develop three novel algorithms to perform detection for this Bayesian model, these include a Markov chain Monte Carlo Approximate Bayesian Computation (MCMC-ABC) approach; an Auxiliary Variable MCMC (MCMC-AV) approach; and a Suboptimal Exhaustive Search Zero Forcing (SES-ZF) approach. Finally, numerical examples comparing the symbol error rate (SER) performance versus signal to noise ratio (SNR) of the three detection algorithms are studied in simulated examples.