Sequential optimal positioning of mobile sensors using mutual information

Schmidt, Kathleen; Smith, Ralph C.; Hite, Jason; Mattingly, John; Azmy, Yousry Y.; Rajan, Deepta; Goldhahn, Ryan

doi:10.1002/sam.11431

Cited by 8 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This criterion attempts to minimise the model’s joint entropy by minimising the log-determinant of the output covariance matrix, balancing minimising marginal variances with maximising correlation magnitude, which can be viewed as minimising uncertainty about the spatial patterns (MacKay, 1992). The joint MI has been used frequently in past work (Lindley, 1956; Krause et al, 2008; Schmidt et al, 2019).…”

Section: Resultsmentioning

confidence: 99%

Environmental sensor placement with convolutional Gaussian neural processes

Andersson

Bruinsma

Markou

et al. 2023

Environ. Data Science

View full text Add to dashboard Cite

Environmental sensors are crucial for monitoring weather conditions and the impacts of climate change. However, it is challenging to place sensors in a way that maximises the informativeness of their measurements, particularly in remote regions like Antarctica. Probabilistic machine learning models can suggest informative sensor placements by finding sites that maximally reduce prediction uncertainty. Gaussian process (GP) models are widely used for this purpose, but they struggle with capturing complex non-stationary behaviour and scaling to large datasets. This paper proposes using a convolutional Gaussian neural process (ConvGNP) to address these issues. A ConvGNP uses neural networks to parameterise a joint Gaussian distribution at arbitrary target locations, enabling flexibility and scalability. Using simulated surface air temperature anomaly over Antarctica as training data, the ConvGNP learns spatial and seasonal non-stationarities, outperforming a non-stationary GP baseline. In a simulated sensor placement experiment, the ConvGNP better predicts the performance boost obtained from new observations than GP baselines, leading to more informative sensor placements. We contrast our approach with physics-based sensor placement methods and propose future steps towards an operational sensor placement recommendation system. Our work could help to realise environmental digital twins that actively direct measurement sampling to improve the digital representation of reality.

show abstract

Section: Resultsmentioning

confidence: 99%

Environmental sensor placement with convolutional Gaussian neural processes

Andersson

Bruinsma

Markou

et al. 2023

Environ. Data Science

View full text Add to dashboard Cite

show abstract

“…An additional area of future work is the use of these surrogate models for optimal detector placement and moving detectors, similar to the work done in Ref. [2,5]. The surrogate models developed here would require being retrained for every new detector location considered for optimal placement, making these surrogate models in their current framework infeasible for use in that problem.…”

Section: Discussionmentioning

confidence: 99%

“…To apply and test this numerical model for a realistic scenario, we select the domain to be a 250 m × 180 m block in downtown Washington, D.C. [2,5]. We construct a 2D representation of the domain using data from the OpenStreetMaps database.…”

Section: Model Geometrymentioning

confidence: 99%

Application and Evaluation of Surrogate Models for Radiation Source Search

et al. 2019

Self Cite

View full text Add to dashboard Cite

Surrogate models are increasingly required for applications in which first-principles simulation models are prohibitively expensive to employ for uncertainty analysis, design, or control. They can also be used to approximate models whose discontinuous derivatives preclude the use of gradient-based optimization or data assimilation algorithms. We consider the problem of inferring the 2D location and intensity of a radiation source in an urban environment using a ray-tracing model based on Boltzmann transport theory. Whereas the code implementing this model is relatively efficient, extension to 3D Monte Carlo transport simulations precludes subsequent Bayesian inference to infer source locations, which typically requires thousands to millions of simulations. Additionally, the resulting likelihood exhibits discontinuous derivatives due to the presence of buildings. To address these issues, we discuss the construction of surrogate models for optimization, Bayesian inference, and uncertainty propagation. Specifically, we consider surrogate models based on Legendre polynomials, multivariate adaptive regression splines, radial basis functions, Gaussian processes, and neural networks. We detail strategies for computing training points and discuss the merits and deficits of each method.Algorithms 2019, 12, 269 2 of 24 responses within this test environment [4]. Whereas this algorithm is based on Boltzmann transport theory, scattering is neglected to significantly improve the efficiency. It is shown in Ref.[5] that, despite these simplifying assumptions, the code can resolve source locations to within meters for the considered geometry and background levels. To solve the source localization problem, we employ Bayesian inference by using a Delayed Rejection Adaptive Metropolis (DRAM) algorithm [6], which requires thousands to millions of model evaluations to infer the 2D position (x, y) and intensity I, which are the design variables used throughout this paper. Whereas the use of DRAM is tractable for this model, two issues motivate the construction of surrogate models: (1) extension to 3D models employing Monte Carlo N-Particle (MCNP) [7] simulations that incorporate more comprehensive physics; and (2) addressing the non-differentiable likelihood due to the presence of buildings in the geometry. We extend the analysis presented in Ref.[2] by exploring the choice of surrogate modeling technique and training point selection in this paper.We performed preliminary research regarding the use of Monte Carlo simulations [7] to generate measurement data for nine point detectors in three dimensions with scattering in an extremely simplified geometry detailed in Ref. [8]. A Monte Carlo simulation was run once to generate synthetic measurements, and calibration was then performed against the calculated detector responses using the ray-tracing model. In this geometry, four rectangular prisms in a 2 × 2 layout were considered in a 100 m × 100 m domain, each adjusted to have wall thicknesses of 0.5 m of concrete. Employing the ray-traci...

show abstract

“…Furthermore, a mutual information formula is also adopted as a metric to identify the set of positions (among a set of predetermined discrete positions) that will provide the highest amount of information about the source localization parameters. The proposed approach is fully described and tested in [45].…”

Section: Sequential Bayesian Approachmentioning

confidence: 99%

Survey of Machine Learning Approaches in Radiation Data Analytics Pertained to Nuclear Security

Alamaniotis

Heifetz

2021

Learning and Analytics in Intelligent Systems

View full text Add to dashboard Cite

The increasing concerns over the use of nuclear materials for malevolent purposes (i.e., terrorist attacks) have fueled the interest in developing technologies that can detect hidden nuclear material before its use. The process of detecting and identifying nuclear materials for non-reported purposes is under the umbrella of nuclear security. Among several areas that contribute to the security and safeguards of nuclear materials, radiation data analytics has recently been marked as an area of high potential. Therefore, there is an increasing trend in applying machine learning for developing data analysis methods applied to radiation signals aiming at identifying patterns of interest associated with nuclear materials. This chapter aspires in providing a comprehensive survey and discussion of machine learning and data analytics methods pertained to nuclear security. The chapter will also discuss further trends and how data analytics can further enhance nuclear security by effectively analyzing radiation data.

show abstract

Sequential optimal positioning of mobile sensors using mutual information

Cited by 8 publications

References 25 publications

Environmental sensor placement with convolutional Gaussian neural processes

Environmental sensor placement with convolutional Gaussian neural processes

Application and Evaluation of Surrogate Models for Radiation Source Search

Survey of Machine Learning Approaches in Radiation Data Analytics Pertained to Nuclear Security

Contact Info

Product

Resources

About