Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “optimization, inverse problems”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 199 records · Page 11

SU-F-T-342: Dosimetric Constraint Prediction Guided Automatic Mulit-Objective Optimization for Intensity Modulated Radiotherapy

Purpose: For intensity modulated radiotherapy, the plan optimization is time consuming with difficulties of selecting objectives and constraints, and their relative weights. A fast and automatic multi-objective optimization algorithm with abilities to predict optimal constraints and manager their trade-offs can help to solve this problem. Our purpose is to develop such a framework and algorithm for a general inverse planning. Methods: There are three main components contained in this proposed multi-objective optimization framework: prediction of initial dosimetric constraints, further adjustment of constraints and plan optimization. We firstly use our previously developed in-house geometry-dosimetry correlation model to predict the optimal patient-specific dosimetric endpoints, and treat them as initial dosimetric constraints. Secondly, we build an endpoint(organ) priority list and a constraint adjustment rule to repeatedly tune these constraints from their initial values, until every single endpoint has no room for further improvement. Lastly, we implement a voxel-independent based FMO algorithm for optimization. During the optimization, a model for tuning these voxel weighting factors respecting to constraints is created. For framework and algorithm evaluation, we randomly selected 20 IMRT prostate cases from the clinic and compared them with our automatic generated plans, in both the efficiency and plan quality. Results: For each evaluated plan, the proposed multi-objective framework could run fluently and automatically. The voxel weighting factor iteration time varied from 10 to 30 under an updated constraint, and the constraint tuning time varied from 20 to 30 for every case until no more stricter constraint is allowed. The average total costing time for the whole optimization procedure is ∼30mins. By comparing the DVHs, better OAR dose sparing could be observed in automatic generated plan, for 13 out of the 20 cases, while others are with competitive results. Conclusion: We have successfully developed a fast and automatic multi-objective optimization for intensity modulated radiotherapy. This work is supported by the National Natural Science Foundation of China (No: 81571771)

60 APPLIED LIFE SCIENCES↗

Minimizing Optimal Transport for Functions with Fixed-Size Nodal Sets

Consider the class of zero-mean functions with fixed L ∞ and L 1 norms and exactly N ϵ N nodal points. Which functions f minimize W p (f + ,f – ), the Wasserstein distance between the measures whose densities are the positive and negative parts? We provide a complete solution to this minimization problem on the line and the circle, which provides sharp constants for previously proven “uncertainty principle”-type inequalities, i.e., lower bounds on N • W p (f + ,f – ). We further show that, while such inequalities hold in many metric measure spaces, they are no longer sharp when the non-branching assumption is violated; indeed, for metric star-graphs, the optimal lower bound on W p (f + ,f – ) is not inversely proportional to the size of the nodal set, N. Here, based on similar reductions, we make connections between the analogous problem of minimizing W p (f + ,f – ) for f defined on Ω C R d with an equivalent optimal domain partition problem.

97 MATHEMATICS AND COMPUTING↗

A scalable framework for the solution of stochastic inverse problems using a sparse grid collocation approach

Experimental evidence suggests that the dynamics of many physical phenomena are significantly affected by the underlying uncertainties associated with variations in properties and fluctuations in operating conditions. Recent developments in stochastic analysis have opened the possibility of realistic modeling of such systems in the presence of multiple sources of uncertainties. These advances raise the possibility of solving the corresponding stochastic inverse problem: the problem of designing/estimating the evolution of a system in the presence of multiple sources of uncertainty given limited information. A scalable, parallel methodology for stochastic inverse/design problems is developed in this article. The representation of the underlying uncertainties and the resultant stochastic dependant variables is performed using a sparse grid collocation methodology. A novel stochastic sensitivity method is introduced based on multiple solutions to deterministic sensitivity problems. The stochastic inverse/design problem is transformed to a deterministic optimization problem in a larger-dimensional space that is subsequently solved using deterministic optimization algorithms. The design framework relies entirely on deterministic direct and sensitivity analysis of the continuum systems, thereby significantly enhancing the range of applicability of the framework for the design in the presence of uncertainty of many other systems usually analyzed with legacy codes. Various illustrative examples with multiple sources of uncertainty including inverse heat conduction problems in random heterogeneous media are provided to showcase the developed framework.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Forward and inverse modeling of fault transmissibility in subsurface flows

Characterizing physical properties of faults, such as their transmissibility, is crucial for performing predictive numerical simulation of subsurface flows, such as those encountered in petroleum engineering and remediation of subsurface contamination. Here, this paper provides a complete investigation of the inverse problem for fault transmissibility in subsurface flow models, under appropriate assumptions on fault structure. In particular, the following aspects are considered: 1) fault modeling and well-posedness of the forward problem; 2) finite element (FEM) discretizations of the forward problem and their rigorous a priori convergence analysis; 3) Well-posedness of the Bayesian inverse problem, FEM discretization of the infinite dimensional Bayesian inverse formulation, and its rigorous a priori analysis. Moreover, computation of the maximum a posteriori (MAP) point via fast inexact Newton-conjugate gradient optimization and a Laplace approximation of the Bayesian posterior are also presented. Numerical results illustrate the use of the proposed fault model in forward and inverse problems for subsurface flows in two dimensional domains with multiple faults.

97 MATHEMATICS AND COMPUTING↗

Learning viscoelasticity models from indirect data using deep neural networks

In this study, we propose a novel approach to model viscoelasticity materials, where rate-dependent and non-linear constitutive relationships are approximated with deep neural networks. We assume that inputs and outputs of the neural networks are not directly observable, and therefore common training techniques with input–output pairs for the neural networks are inapplicable. To that end, we develop a novel computational approach to both calibrate parametric and learn neural-network-based constitutive relations of viscoelasticity materials from indirect displacement data in the context of multiple-physics systems. We show that limited displacement data holds sufficient information to quantify the viscoelasticity behavior. We formulate the inverse computation – modeling viscoelasticity properties from observed displacement data – as a PDE-constrained optimization problem and minimize the error functional using a gradient-based optimization method. The gradients are computed by a combination of automatic differentiation and implicit function differentiation rules. The effectiveness of our method is demonstrated through numerous benchmark problems in geomechanics and porous media transport.

97 MATHEMATICS AND COMPUTING↗

Sequential ensemble transform for Bayesian inverse problems

In this work, we present the Sequential Ensemble Transform (SET) method, an approach for generating approximate samples from a Bayesian posterior distribution. The method explores the posterior distribution by solving a sequence of discrete optimal transport problems to produce a series of transport plans which map prior samples to posterior samples. We prove that the sequence of Dirac mixture distributions produced by the SET method converges weakly to the true posterior as the sample size approaches infinity. Furthermore, our numerical results indicate that, when compared to standard Sequential Monte Carlo (SMC) methods, the SET approach is more robust to the choice of Markov mutation kernels and requires less computational efforts to reach a similar accuracy when used to explore complex posterior distributions. Finally, we describe adaptive schemes that allow to completely automate the use of the SET method.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Closed-Form Approximation of the Total Variation Proximal Operator

Total variation (TV) is a widely used function for regularizing imaging inverse problems that is particularly appropriate for images whose underlying structure is piecewise constant. TV regularized optimization problems are typically solved using proximal methods, but the way in which they are applied is constrained by the absence of a closed-form expression for the proximal operator of the TV function. A closed-form approximation of the TV proximal operator has previously been proposed, but its accuracy was not theoretically explored in detail. Here, we address this gap by making several new theoretical contributions, proving that the approximation leads to a proximal operator of some convex function, it is equivalent to a gradient descent step on a smoothed version of TV, and that its error can be fully characterized and controlled with its scaling parameter. We experimentally validate our theoretical results on image denoising and sparse-view computed tomography (CT) image reconstruction.

97 MATHEMATICS AND COMPUTING↗

Transient and Steady-State Inverse Problems in Sierra/Aria

Inverse problems arise in a wide range of applications, whenever unknown model parameters cannot be measured directly. Instead, the unknown parameters are estimated using experimental data and forward simulations. Thermal inverse problems, such as material characterization problems, are often large-scale and transient. Therefore, they require intrusive adjoint-based gradient implementations in order to be solved efficiently. The capability to solve large-scale transient thermal inverse problems using an adjoint-based approach was recently implemented in SNL Sierra Mechanics, a massively parallel capable multiphysics code suite. This report outlines the theory, optimization formulation, and path taken to implement thermal inverse capabilities in Sierra within a unit test framework. The capability utilizes Sierra/Aria and Sierra/Fuego data structures, the Rapid Optimization Library, and an interface to the Sierra/InverseOpt library. The existing Sierra/Aria time integrator is leveraged to implement a time-dependent adjoint solver.

97 MATHEMATICS AND COMPUTING↗

The nanostructure problem

Diffraction techniques are making progress in tackling the difficult problem of solving the structures of nanoparticles and nanoscale materials. The great gift of x-ray crystallography has made us almost complacent in our ability to locate the three-dimensional coordinates of atoms in a crystal with a precision of around 10{sup -4} nm. However, the powerful methods of crystallography break down for structures in which order only extends over a few nanometers. In fact, as we near the one hundred year mark since the birth of crystallography, we face a resilient frontier in condensed matter physics: our inability to routinely and robustly determine the structure of complex nanostructured and amorphous materials. Knowing the structure and arrangement of atoms in a solid is so fundamental to understanding its properties that the topic routinely occupies the early chapters of every solid-state physics textbook. Yet what has become clear with the emergence of nanotechnology is that diffraction data alone may not be enough to uniquely solve the structure of nanomaterials. As part of a growing effort to incorporate the results of other techniques to constrain x-ray refinements - a method called 'complex modeling' which is a simple but elegant approach for combining information from spectroscopy with diffraction data to solve the structure of several amorphous and nanostructured materials. Crystallography just works, so we rarely question how and why this is so, yet understanding the physics of diffraction can be very helpful as we consider the nanostructure problem. The relationship between the electron density distribution in three dimensions (i.e., the crystal structure) and an x-ray diffraction pattern is well established: the measured intensity distribution in reciprocal space is the square of the Fourier transform of the autocorrelation function <{rho}(r){rho}(r+r')> of the electron density distribution {rho}(r). The fact that we get the autocorrelation function (rather than just the density distribution) by Fourier transforming the measured intensity leaves us with a very tricky inverse problem: we have to extract the density from its autocorrelation function. The direct problem of predicting the diffraction intensity given a particular density distribution is trivial, but the inverse, unraveling from the intensity distribution the density that gives rise to it, is a highly nontrivial problem in global optimization. In crystallography, this challenging, nontrivial task is sometimes referred to as the 'phase problem.' The diffraction pattern is a wave-interference pattern, but we measure only the intensities (the squares of the waves) not the wave amplitudes. To get the amplitude, you take the square root of the intensity I, but in so doing you lose any knowledge of the phase of the wave {phi}, and half the information needed to reconstruct the density is lost. When solving such inverse problems, you hope you can start with a uniqueness theorem that reassures you that, under ideal conditions, there is only one solution: one density distribution that corresponds to the measured intensity. Then you have to establish that your data set contains sufficient information to constrain that unique solution. This is a problem from information theory that originated with Reverend Thomas Bayes work in the 18th century, and the work of Nyquist and Shannon in the 20 th century, and describes the fact that the degrees of freedom in the model must not exceed the number of pieces of independent information in the data. Finally, you need an efficient algorithm for doing the reconstruction. This is exactly how crystallography works. The information is in the form of Bragg peak intensities and the degrees of freedom are the atomic coordinates. Crystal symmetry lets us confine the model to the contents of a unit cell, rather than all of the atoms in the crystal, keeping the degrees of freedom admirably small in number. A measurement yields a multitude of Bragg peak intensities, providing ample redundant intensity information to make up for the lost phases. Finally, there are highly efficient algorithms, such as 'direct methods,' that make excellent use of the available information and constraints to find the solution quickly from a horrendously large search space. The problem is often so overconstrained that we can cavalierly throw away lots of directional information. In particular, even though Bragg peaks are orientationally averaged to a 1D function in a powder diffraction measurement, we still can get a 3D structural solution. Now it becomes easy to understand the enormous challenge of solving nanostructures: the information content in the data is degraded while the complexity of the model is much greater.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

pnnl/neuromancer

Dynamics-based deep learning methods to modernize current scientific computing methods. Neuromancer is currently capable of solving inverse problems for a system of ordinary differential equations. The functionality includes system identification and constrained optimal control of unknown or partially known ODEs.

Skomski, Elliott↗

Field-theoretic Simulations of Block Copolymers: Design and Solvent Annealing

We first propose a solution to the inverse design problem for block copolymers that uses self-consistent field theory (SCFT) with numerical optimization. We apply our design methodology to both conformationally symmetric and asymmetric diblock copolymer melts. In the latter case, the parameters are specific to poly(ethylene oxide-b-styrene) block copolymer (PEO-PS), a material currently being explored as an electrolyte for lithium-ion batteries. The results of this design approach not only guide the synthesis of block copolymers but also shed light on the polymer physics of the gyroid phase. Second, we develop an SCFT to isolate and study the dynamical aspects of micro-phase separation in block copolymer films during the film drying process. Key questions include whether evaporation rate as a controlled, independent variable can effect a change in microdomain orientation, whether a concentration-dependent kinetic mobility is required to explain such an effect, and working out the consequences for controlling the morphology alignment in copolymer films of varying thicknesses.

36 MATERIALS SCIENCE↗

Optical tomography reconstruction algorithm with the finite element method: An optimal approach with regularization tools

Highlights: •New strategies to improve the accuracy of the reconstruction through mesh and finite element parameterization. •Use of gradient filtering through an alternative inner product within the adjoint method. •An integral form of the cost function is used to make the reconstruction compatible with all finite element formulations, continuous and discontinuous. •Gradient-based algorithm with the adjoint method is used for the reconstruction. -- Abstract: Optical tomography is mathematically treated as a non-linear inverse problem where the optical properties of the probed medium are recovered through the minimization of the errors between the experimental measurements and their predictions with a numerical model at the locations of the detectors. According to the ill-posed behavior of the inverse problem, some regularization tools must be performed and the Tikhonov penalization type is the most commonly used in optical tomography applications. This paper introduces an optimized approach for optical tomography reconstruction with the finite element method. An integral form of the cost function is used to take into account the surfaces of the detectors and make the reconstruction compatible with all finite element formulations, continuous and discontinuous. Through a gradient-based algorithm where the adjoint method is used to compute the gradient of the cost function, an alternative inner product is employed for preconditioning the reconstruction algorithm. Moreover, appropriate re-parameterization of the optical properties is performed. These regularization strategies are compared with the classical Tikhonov penalization one. It is shown that both the re-parameterization and the use of the Sobolev cost function gradient are efficient for solving such an ill-posed inverse problem.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Multimodal Freight Energy Model for Emerging Freight Technology Analysis

While freight movement represents a small portion of the volume in the transportation sector, they are a critical contributor for energy consumed in that sector. To reduce logistics costs, energy consumption and negative environmental impact, emerging technologies, such as digitalization of logistics and alternative powertrain, have been developed and extended applications in freight. These trends are expected to grow and provide opportunities for greater efficiencies in freight movement and corresponding energy use. Still, the complexity of freight systems present challenges in evaluating these benefits, especially in the multimodal inter-city freight. Addressing the research need, this paper develops a multimodal freight energy modeling framework for the analysis of emerging freight technology scenarios. The framework is a bi-level optimization problem: network cost minimization problem (lower-level) and energy minimization problem (upper-level). The lower-level problem is a mode-path assignment problem in multimodal inter-city freight networks, where commodity-specific congestion effects on trans-shipment links are considered. For this model, an inverse modeling approach is applied to infer parameters of the lower-level model. The upper-level problem is designed to search for an optimal scenario that has the lowest energy consumption among different levels of technology applications. The proposed model is empirically tested to analyze truck load-pooling and multimodal load-pooling scenarios through stand-alone and mixed applications using freight shipments originating from or destined to the Chicago region. This framework can be used to explore the impact of emerging freight technologies on mode-path freight flow and energy consumption in the national multimodal freight network.

ADVANCED PROPULSION SYSTEMS↗

iTOUGH2 Universal Optimization Using the PEST Protocol

iTOUGH2 (http://www-esd.lbl.gov/iTOUGH2) is a computer program for parameter estimation, sensitivity analysis, and uncertainty propagation analysis [Finsterle, 2007a, b, c]. iTOUGH2 contains a number of local and global minimization algorithms for automatic calibration of a model against measured data, or for the solution of other, more general optimization problems (see, for example, Finsterle [2005]). A detailed residual and estimation uncertainty analysis is conducted to assess the inversion results. Moreover, iTOUGH2 can be used to perform a formal sensitivity analysis, or to conduct Monte Carlo simulations for the examination for prediction uncertainties. iTOUGH2's capabilities are continually enhanced. As the name implies, iTOUGH2 is developed for use in conjunction with the TOUGH2 forward simulator for nonisothermal multiphase flow in porous and fractured media [Pruess, 1991]. However, iTOUGH2 provides FORTRAN interfaces for the estimation of user-specified parameters (see subroutine USERPAR) based on user-specified observations (see subroutine USEROBS). These user interfaces can be invoked to add new parameter or observation types to the standard set provided in iTOUGH2. They can also be linked to non-TOUGH2 models, i.e., iTOUGH2 can be used as a universal optimization code, similar to other model-independent, nonlinear parameter estimation packages such as PEST [Doherty, 2008] or UCODE [Poeter and Hill, 1998]. However, to make iTOUGH2's optimization capabilities available for use with an external code, the user is required to write some FORTRAN code that provides the link between the iTOUGH2 parameter vector and the input parameters of the external code, and between the output variables of the external code and the iTOUGH2 observation vector. While allowing for maximum flexibility, the coding requirement of this approach limits its applicability to those users with FORTRAN coding knowledge. To make iTOUGH2 capabilities accessible to many application models, the PEST protocol [Doherty, 2007] has been implemented into iTOUGH2. This protocol enables communication between the application (which can be a single 'black-box' executable or a script or batch file that calls multiple codes) and iTOUGH2. The concept requires that for the application model: (1) Input is provided on one or more ASCII text input files; (2) Output is returned to one or more ASCII text output files; (3) The model is run using a system command (executable or script/batch file); and (4) The model runs to completion without any user intervention. For each forward run invoked by iTOUGH2, select parameters cited within the application model input files are then overwritten with values provided by iTOUGH2, and select variables cited within the output files are extracted and returned to iTOUGH2. It should be noted that the core of iTOUGH2, i.e., its optimization routines and related analysis tools, remains unchanged; it is only the communication format between input parameters, the application model, and output variables that are borrowed from PEST. The interface routines have been provided by Doherty [2007]. The iTOUGH2-PEST architecture is shown in Figure 1. This manual contains installation instructions for the iTOUGH2-PEST module, and describes the PEST protocol as well as the input formats needed in iTOUGH2. Examples are provided that demonstrate the use of model-independent optimization and analysis using iTOUGH2.

15 GEOTHERMAL ENERGY↗

Diabatic quantum annealing for the frustrated ring model

Abstract Quantum annealing (QA) is a continuous-time heuristic quantum algorithm for solving or approximately solving classical optimization problems. The algorithm uses a schedule to interpolate between a driver Hamiltonian with an easy-to-prepare ground state and a problem Hamiltonian whose ground state encodes solutions to an optimization problem. The standard implementation relies on the evolution being adiabatic: keeping the system in the instantaneous ground state with high probability and requiring a time scale inversely related to the minimum energy gap between the instantaneous ground and excited states. However, adiabatic evolution can lead to evolution times that scale exponentially with the system size, even for computationally simple problems. Here, we study whether non-adiabatic evolutions with optimized annealing schedules can bypass this exponential slowdown for one such class of problems called the frustrated ring model. For sufficiently optimized annealing schedules and system sizes of up to 39 qubits, we provide numerical evidence that we can avoid the exponential slowdown. Our work highlights the potential of highly-controllable QA to circumvent bottlenecks associated with the standard implementation of QA.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Fourier-DeepONet: Fourier-enhanced deep operator networks for full waveform inversion with improved accuracy, generalizability, and robustness

In this article, full waveform inversion (FWI) infers the subsurface structure information from seismic waveform data by solving a non-convex optimization problem. Data-driven FWI has been increasingly studied with various neural network architectures to improve accuracy and computational efficiency. Nevertheless, the applicability of pre-trained neural networks is severely restricted by potential discrepancies between the source function used in the field survey and the one utilized during training. Here, we develop a Fourier-enhanced deep operator network (Fourier-DeepONet) for FWI with the generalization of seismic sources, including the frequencies and locations of sources. Specifically, we employ the Fourier neural operator as the decoder of DeepONet, and we utilize source parameters as one input of Fourier-DeepONet, facilitating the resolution of FWI with variable sources. To test Fourier-DeepONet, we develop three new and realistic FWI benchmark datasets (FWI-F, FWI-L, and FWI-FL) with varying source frequencies, locations, or both. Our experiments demonstrate that compared with existing data-driven FWI methods, Fourier-DeepONet obtains more accurate predictions of subsurface structures in a wide range of source parameters. Moreover, the proposed Fourier-DeepONet exhibits superior robustness when handling data with Gaussian noise or missing traces and sources with Gaussian noise, paving the way for more reliable and accurate subsurface imaging across diverse real conditions.

42 ENGINEERING↗

Customizable wave tailoring nonlinear materials enabled by bilevel inverse design

Abstract Passive wave transformation via nonlinearity is ubiquitous in settings from acoustics to optics and electromagnetics. It is well known that different nonlinearities yield different effects on propagating signals, which raises the question of “what precise nonlinearity is the best for a given wave tailoring application?” In this work, considering a one-dimensional spring-mass chain connected by polynomial springs (a variant of the Fermi-Pasta-Ulam-Tsingou system), we introduce a bilevel inverse design method which couples the shape optimization of structures for tailored constitutive responses with reduced-order nonlinear dynamical inverse design. We apply it to two qualitatively distinct problems—minimization of peak transmitted kinetic energy from impact, and pulse shape transformation—demonstrating our method’s breadth of applicability. For the impact problem, we obtain two fundamental insights. First, small differences in nonlinearity can drastically change the dynamic response of the system, from severely under- to outperforming a comparative linear system. Second, the oft-used strategy of impact mitigation via “energy locking” bistability can be significantly outperformed by our optimal nonlinearity. We validate this case with impact experiments and find excellent agreement. This study establishes a framework for broader passive nonlinear mechanical wave tailoring material design, with applications to computing, signal processing, shock mitigation, and autonomous materials.

Science & Technology - Other Topics↗

Radiation Source Mapping with Bayesian Inverse Methods

In this work, we present a method to map the spectral and spatial distributions of radioactive sources using a limited number of detectors. Locating and identifying radioactive materials is important for border monitoring, in accounting for special nuclear material in processing facilities, and in cleanup operations following a radioactive material spill. Most methods to analyze these types of problems make restrictive assumptions about the distribution of the source. In contrast, the source mapping method presented here allows an arbitrary three-dimensional distribution in space and a gamma peak distribution in energy. To apply the method, the problem is cast as an inverse problem where the system’s geometry and material composition are known and fixed, while the radiation source distribution is sought. A probabilistic Bayesian approach is used to solve the resulting inverse problem since the system of equations is ill-posed. The posterior is maximized with a Newton optimization method. The probabilistic approach also provides estimates of the confidence in the final source map prediction. A set of adjoint, discrete ordinates flux solutions, obtained in this work by the Denovo code, is required to efficiently compute detector responses from a candidate source distribution. These adjoint fluxes form the linear mapping from the state space to the response space. The test of the method’s success is simultaneously locating a set of 137 Cs and 60 Co gamma sources in a room. This test problem is solved using experimental measurements that we collected for this purpose. Because of the weak sources available for use in the experiment, some of the expected photopeaks were not distinguishable from the Compton continuum. However, by supplanting 14 flawed measurements (out of a total of 69) with synthetic responses computed by MCNP, the proof-of-principle source mapping was successful. The locations of the sources were predicted within 25 cm for two of the sources and 90 cm for the third, in a room with an ~4-x 4-m floor plan. Finally, the predicted source intensities were within a factor of ten of their true value.

07 ISOTOPE AND RADIATION SOURCES↗