This work is the first to employ and adapt the image-to-image translation concept based on conditional generative adversarial networks (cGAN) towards learning a forward and an inverse solution operator of partial differential equations (PDEs). Even though the proposed framework could be applied as a surrogate model for the solution of any PDEs, here we focus on steady-state solutions of coupled hydro-mechanical processes in heterogeneous porous media. Strongly heterogeneous material properties, which translate to the heterogeneity of coefficients of the PDEs and discontinuous features in the solutions, require specialized techniques for the forward and inverse solution of these problems. Additionally, parametrization of the spatially heterogeneous coefficients is excessively difficult by using standard reduced order modeling techniques. In this work, we overcome these challenges by employing the image-to-image translation concept to learn the forward and inverse solution operators and utilize a U-Net generator and a patch-based discriminator. Our results show that the proposed data-driven reduced order model has competitive predictive performance capabilities in accuracy and computational efficiency as well as training time requirements compared to state-of-the-art data-driven methods for both forward and inverse problems.
Ordinary differential equation models are nowadays widely used for the mechanistic description of biological processes and their temporal evolution. These models typically have many unknown and non-measurable parameters, which have to be determined by fitting the model to experimental data. In order to perform this task, known as parameter estimation or model calibration, the modeller faces challenges such as poor parameter identifiability, lack of sufficiently informative experimental data, and the existence of local minima in the objective function landscape. These issues tend to worsen with larger model sizes, increasing the computational complexity and the number of unknown parameters. An incorrectly calibrated model is problematic because it may result in inaccurate predictions and misleading conclusions. For non-expert users, there are a large number of potential pitfalls. Here, we provide a protocol that guides the user through all the steps involved in the calibration of dynamic models. We illustrate the methodology with two models, and provide all the code required to reproduce the results and perform the same analysis on new models. Our protocol provides practitioners and researchers in biological modelling with a one-stop guide that is at the same time compact and sufficiently comprehensive to cover all aspects of the problem.
In this paper, we consider static parameter estimation for a class of continuous-time state-space models. Our goal is to obtain an unbiased estimate of the gradient of the log-likelihood (score function), which is an estimate that is unbiased even if the stochastic processes involved in the model must be discretized in time. To achieve this goal, we apply a doubly randomized scheme, that involves a novel coupled conditional particle filter (CCPF) on the second level of randomization. Our novel estimate helps facilitate the application of gradient-based estimation algorithms, such as stochastic-gradient Langevin descent. We illustrate our methodology in the context of stochastic gradient descent (SGD) in several numerical examples and compare with the Rhee & Glynn estimator.
We review the role of information and learning in the stability and optimization of queueing systems. In recent years, techniques from supervised learning, bandit learning and reinforcement learning have been applied to queueing systems supported by increasing role of information in decision making. We present observations and new results that help rationalize the application of these areas to queueing systems. We prove that the MaxWeight and BackPressure policies are an application of Blackwell's Approachability Theorem. This connects queueing theoretic results with adversarial learning. We then discuss the requirements of statistical learning for service parameter estimation. As an example, we show how queue size regret can be bounded when applying a perceptron algorithm to classify service. Next, we discuss the role of state information in improved decision making. Here we contrast the roles of epistemic information (information on uncertain parameters) and aleatoric information (information on an uncertain state). Finally we review recent advances in the theory of reinforcement learning and queueing, as well as, provide discussion on current research challenges.
We introduce a minimalist outbreak forecasting model that combines data-driven parameter estimation with variational data assimilation. By focusing on the fundamental components of nonlinear disease transmission and representing data in a domain where model stochasticity simplifies into a process with independent increments, we design an approach that only requires four core parameters to be estimated. We illustrate this novel methodology on COVID-19 forecasts. Results include case count and deaths predictions for the US and all of its 50 states, the District of Columbia, and Puerto Rico. The method is computationally efficient and is not disease- or location-specific. It may therefore be applied to other outbreaks or other countries, provided case counts and/or deaths data are available.
We study the problem of estimating the parameters (i.e., infection rate and recovery rate) governing the spread of epidemics in networks. Such parameters are typically estimated by measuring various characteristics (such as the number of infected and recovered individuals) of the infected populations over time. However, these measurements also incur certain costs, depending on the population being tested and the times at which the tests are administered. We thus formulate the epidemic parameter estimation problem as an optimization problem, where the goal is to either minimize the total cost spent on collecting measurements, or to optimize the parameter estimates while remaining within a measurement budget. We show that these problems are NP-hard to solve in general, and then propose approximation algorithms with performance guarantees. We validate our algorithms using numerical examples.
A common setting for scientific inference is the ability to sample from a high-fidelity forward model (simulation) without having an explicit probability density of the data. We propose a simulation-based maximum likelihood deconvolution approach in this setting called OmniFold. Deep learning enables this approach to be naturally unbinned and (variable-, and) high-dimensional. In contrast to model parameter estimation, the goal of deconvolution is to remove detector distortions in order to enable a variety of down-stream inference tasks. Our approach is the deep learning generalization of the common Richardson-Lucy approach that is also called Iterative Bayesian Unfolding in particle physics. We show how OmniFold can not only remove detector distortions, but it can also account for noise processes and acceptance effects.
We introduce a framework for Bayesian experimental design (BED) with implicit models, where the data-generating distribution is intractable but sampling from it is still possible. In order to find optimal experimental designs for such models, our approach maximises mutual information lower bounds that are parametrised by neural networks. By training a neural network on sampled data, we simultaneously update network parameters and designs using stochastic gradient-ascent. The framework enables experimental design with a variety of prominent lower bounds and can be applied to a wide range of scientific tasks, such as parameter estimation, model discrimination and improving future predictions. Using a set of intractable toy models, we provide a comprehensive empirical comparison of prominent lower bounds applied to the aforementioned tasks. We further validate our framework on a challenging system of stochastic differential equations from epidemiology.
Economic model predictive control (EMPC) is a promising methodology for optimal operation of dynamical processes that has been shown to improve process economics considerably. However, EMPC performance relies heavily on the accuracy of the process model used. As an alternative to model-based control strategies, reinforcement learning (RL) has been investigated as a model-free control methodology, but issues regarding its safety and stability remain an open research challenge. This work presents a novel framework for integrating EMPC and RL for online model parameter estimation of a class of nonlinear systems. In this framework, EMPC optimally operates the closed loop system while maintaining closed loop stability and recursive feasibility. At the same time, to optimize the process, the RL agent continuously compares the measured state of the process with the model's predictions (nominal states), and modifies model parameters accordingly. The major advantage of this framework is its simplicity; state-of-the-art RL algorithms and EMPC schemes can be employed with minimal modifications. The performance of the proposed framework is illustrated on a network of reactions with challenging dynamics and practical significance. This framework allows control, optimization, and model correction to be performed online and continuously, making autonomous reactor operation more attainable.
The state of the art in video super-resolution (SR) are techniques based on deep learning, but they perform poorly on real-world videos (see Figure 1). The reason is that training image-pairs are commonly created by downscaling a high-resolution image to produce a low-resolution counterpart. Deep models are therefore trained to undo downscaling and do not generalize to super-resolving real-world images. Several recent publications present techniques for improving the generalization of learning-based SR, but are all ill-suited for real-time application. We present a novel approach to synthesizing training data by simulating two digital-camera image-capture processes at different scales. Our method produces image-pairs in which both images have properties of natural images. Training an SR model using this data leads to far better generalization to real-world images and videos. In addition, deep video-SR models are characterized by a high operations-per-pixel count, which prohibits their application in real-time. We present an efficient CNN architecture, which enables real-time application of video SR on low-power edge-devices. We split the SR task into two sub-tasks: a control-flow which estimates global properties of the input video and adapts the weights and biases of a processing-CNN that performs the actual processing. Since the process-CNN is tailored to the statistics of the input, its capacity kept low, while retaining effectivity. Also, since video-statistics evolve slowly, the control-flow operates at a much lower rate than the video frame-rate. This reduces the overall computational load by as much as two orders of magnitude. This framework of decoupling the adaptivity of the algorithm from the pixel processing, can be applied in a large family of real-time video enhancement applications, e.g., video denoising, local tone-mapping, stabilization, etc.
Mixture models are a fundamental tool in applied statistics and machine learning for treating data taken from multiple subpopulations. The current practice for estimating the parameters of such models relies on local search heuristics (e.g., the EM algorithm) which are prone to failure, and existing consistent methods are unfavorable due to their high computational and sample complexity which typically scale exponentially with the number of mixture components. This work develops an efficient method of moments approach to parameter estimation for a broad class of high-dimensional mixture models with many components, including multi-view mixtures of Gaussians (such as mixtures of axis-aligned Gaussians) and hidden Markov models. The new method leads to rigorous unsupervised learning results for mixture models that were not achieved by previous works; and, because of its simplicity, it offers a viable alternative to EM for practical deployment.
Metabolic modeling strives to develop modeling approaches that are robust and highly predictive. To achieve this, various modeling designs, including hybrid models, and parameter estimation methods that define the type and number of parameters used in the model, are adapted. Accurate input data play an important role so that the selection of experimental methods that provide input data of the required precision with low measurement errors is crucial. For the biopharmaceutically relevant protein glycosylation, the most prominent available models are kinetic models which are able to capture the dynamic nature of protein N-glycosylation. In this review we focus on how to choose the most suitable model for a specific research question, as well as on parameters and considerations to take into account before planning relevant experiments.
This paper addresses the trajectory tracking problem of an autonomous tractor-trailer system by using a fast distributed nonlinear model predictive control algorithm in combination with nonlinear moving horizon estimation for the state and parameter estimation in which constraints on the inputs and the states can be incorporated. The proposed control algorithm is capable of driving the tractor-trailer system to any desired trajectory ensuring high control accuracy and robustness against environmental disturbances.
The modelling of Earth observation data is a challenging problem, typically approached by either purely mechanistic or purely data-driven methods. Mechanistic models encode the domain knowledge and physical rules governing the system. Such models, however, need the correct specification of all interactions between variables in the problem and the appropriate parameterization is a challenge in itself. On the other hand, machine learning approaches are flexible data-driven tools, able to approximate arbitrarily complex functions, but lack interpretability and struggle when data is scarce or in extrapolation regimes. In this paper, we argue that hybrid learning schemes that combine both approaches can address all these issues efficiently. We introduce Gaussian process (GP) convolution models for hybrid modelling in Earth observation (EO) problems. We specifically propose the use of a class of GP convolution models called latent force models (LFMs) for EO time series modelling, analysis and understanding. LFMs are hybrid models that incorporate physical knowledge encoded in differential equations into a multioutput GP model. LFMs can transfer information across time-series, cope with missing observations, infer explicit latent functions forcing the system, and learn parameterizations which are very helpful for system analysis and interpretability. We consider time series of soil moisture from active (ASCAT) and passive (SMOS, AMSR2) microwave satellites. We show how assuming a first order differential equation as governing equation, the model automatically estimates the e-folding time or decay rate related to soil moisture persistence and discovers latent forces related to precipitation. The proposed hybrid methodology reconciles the two main approaches in remote sensing parameter estimation by blending statistical learning and mechanistic modeling.
We describe a method for computing the biases that systematic signals introduce in parameter estimation using a simple extension of the Fisher matrix formalism. This allows us to calculate the offset of the best fit parameters relative to the fiducial model, in addition to the usual statistical error ellipse. As an application, we study the impact that residual systematics in tomographic weak lensing measurements. In particular we explore three different types of shape measurement systematics: (i) additive systematic with no redshift evolution; (ii) additive systematic with redshift evolution; and (iii) multiplicative systematic. In each case, we consider a wide range of scale dependence and redshift evolution of the systematics signal. For a future DUNE-like full sky survey, we find that, for cases with mild redshift evolution, the variance of the additive systematic signal should be kept below 10^-7 to ensure biases on cosmological parameters that are sub-dominant to the statistical errors. For the multiplicative systematics, which depends on the lensing signal, we find the multiplicative calibration m0 needs to be controlled to an accuracy better than 10^-3. We find that the impact of systematics can be underestimated if their assumes redshift dependence is too simplistic. We provide simple scaling relations to extend these requirements to any survey geometry and discuss the impact of our results for current and future weak lensing surveys.
The target state filter is an important module in the traditional target tracking framework. In order to get satisfactory tracking results, traditional Bayesian methods usually need accurate motion models, which require the complicated prior information and parameter estimation. Therefore, the modeling process has a key impact on traditional Bayesian filters for target tracking. However, when encountering unknown prior information or the complicated environment, traditional Bayesian filters have the limitation of greatly reduced accuracy. In this paper, we propose a supervised learning based online tracking filter(SLF). First, a complete tracking filter framework based on supervised learning is established, which is directly based on data-driven and establishes the mapping relationship between data. In other words, the proposed filter does not require the prior information about target dynamics and clutter distribution. Then, an implementation based on eXtreme Gradient Boosting (XGBoost) is provided, which proves the portability and applicability of the SLF framework. Meanwhile, the proposed framework will encourage other researchers to continue to expand the field of combining traditional filters with supervised learning. Finally, numerical simulation experiments prove the effectiveness of the proposed filter.
The optimal power adaptation problem is investigated for vector parameter estimation according to various Fisher information based optimality criteria. By considering an observation model that involves a linear transformation of the parameter vector and an additive noise component with an arbitrary probability distribution, six different optimal power allocation problems are formulated based on Fisher information based objective functions. Via optimization theoretic approaches, various closed-form solutions are derived for the proposed problems. Also, the results are extended to cases in which nuisance parameters exist in the system model or certain types of nonlinear transformations are applied on the parameter vector. Numerical examples are presented to investigate performance of the proposed power allocation strategies.
Elliptically-contoured distributions (ECD) play a significant role, in computer vision, image processing, radar, and biomedical signal processing. Maximum likelihood. estimation (MLE) of ECD leads to a system of non-linear equations, most-often addressed using fixed-point (FP) methods. Unfortunately, the computation time required for these methods is unacceptably long, for large-scale or high-dimensional datasets. To overcome this difficulty, the present work introduces a Riemannian optimisation method, the information stochastic gradient (ISG). The ISG is an online (recursive) method, which achieves the same performance as MLE, for large-scale datasets, while requiring modest memory and time resources. To develop the ISG method, the Riemannian information gradient is derived taking into account the product manifold associated to the underlying parameter space of the ECD. From this information gradient definition, we define also, the information deterministic gradient (IDG), an offline (batch) method, which is an alternative, for moderate-sized datasets. The present work formulates these two methods, and demonstrates their performance through numerical simulations. Two applications, to image re-colorization, and to texture classification, are also worked out.
Earth observation from satellite sensory data poses challenging problems, where machine learning is currently a key player. In recent years, Gaussian Process (GP) regression has excelled in biophysical parameter estimation tasks from airborne and satellite observations. GP regression is based on solid Bayesian statistics and generally yields efficient and accurate parameter estimates. However, GPs are typically used for inverse modeling based on concurrent observations and in situ measurements only. Very often a forward model encoding the well-understood physical relations between the state vector and the radiance observations is available though and could be useful to improve predictions and understanding. In this work, we review three GP models that respect and learn the physics of the underlying processes in the context of both forward and inverse modeling. After reviewing the traditional application of GPs for parameter retrieval, we introduce a Joint GP (JGP) model that combines in situ measurements and simulated data in a single GP model. Then, we present a latent force model (LFM) for GP modeling that encodes ordinary differential equations to blend data-driven modeling and physical constraints of the system governing equations. The LFM performs multi-output regression, adapts to the signal characteristics, is able to cope with missing data in the time series, and provides explicit latent functions that allow system analysis and evaluation. Finally, we present an Automatic Gaussian Process Emulator (AGAPE) that approximates the forward physical model using concepts from Bayesian optimization and at the same time builds an optimally compact look-up-table for inversion. We give empirical evidence of the performance of these models through illustrative examples of vegetation monitoring and atmospheric modeling.
In this paper, we investigate the problem of inverse electromagnetic scattering to recover multilayer human tissue profiles using ultrawideband radar systems in a Bayesian setting. We study the recovery problem in a blind setting, in which we simultaneously estimate both the dielectric/geometric properties of the one-dimensional target tissue profile and the transmitted radar waveform. To perform Bayesian parameter estimation, we propose a hybrid and adaptive Markov Chain Monte Carlo method, which combines the Slice sampling and Hamiltonian Monte Carlo approaches. The introduced sampling mechanism also incorporates the Parallel Tempering approach to escape from the local optimal regions of the complex posterior distribution. We provide empirical support through various numerical simulations for the achieved enhanced sampling efficiency compared to conventional sampling schemes. To investigate the recovery performance, we work on synthetic measurements simulating actual radar returns from multilayer tissue profiles. We derive theoretical bounds for the best achievable estimation performance in terms of normalized root mean square error and provide a comparison with the performance of our estimator.