Low-dimensional Matrix Research Articles

A short-term wind power forecasting model based on CUR

Abstract Wind power forecasting plays a crucial role in the contemporary renewable energy system. During the process of forecasting wind power, the establishment of LSTM models requires a lot of time and effort, and the interpretability of prediction results is poor, making it difficult to understand and verify the results. To accomplish interpretable and precise wind power predictions, this paper introduces a wind power prediction algorithm model leveraging CUR matrix decomposition. The CUR matrix decomposition method first obtains the original matrix A (wind power data matrix). The statistical influence scores of rows and columns in A are calculated, and several columns and rows with higher scores are selected to form a low dimensional matrix C and R. Matrix C contains the main characteristic factors that affect wind power, while matrix R contains time series features. Then, the matrix U is approximated by A, C, and R to transform the preference feature extraction problem in high-dimensional space into a matrix analysis problem in low-dimensional space, making it more interpretable and accurate. The efficacy of the wind power forecasting approach utilizing CUR matrix decomposition is assessed and confirmed on openly accessible datasets. The results indicate that the CUR matrix decomposition method has good prediction accuracy and interpretability.

Robust multi-view clustering via structure regularization concept factorization

Recently, many concept factorization-based multi-view clustering methods have been proposed and achieved promising results on text multi-view data. However, existing methods are limited in the following two aspects. (1) The Frobenius norm used in these methods is sensitive to noise and outliers; (2) These methods ignore the global structural information of the data. To address the above problems, we propose a robust concept factorization framework for multi-view clustering, which not only improves the robustness but also fully exploits the available information of multi-view data. Specifically, L2,1-norm is used to evaluate the error of the factorization, thus eliminating the effect of outliers and improving robustness. In addition, to retain more structure information of the original data, the global and local structure information are taken into consideration simultaneously, which makes the learned low-dimensional matrix more discriminative. Further, to make use of the complementary information of the different views, we introduce an adaptive weight learning strategy to assign weights for different views. An iterative updating algorithm is proposed to solve the proposed optimization problem. We compare the proposed method with state-of-the-art alternative methods on benchmark multi-view data sets. The extensive experimental results show the effectiveness and superiority of the proposed method.

Low-rank reconstruction for mid-infrared spectroscopy using broadband ultra-wide-angle photonic filters and IReg algorithm

In this study, a broadband mid-infrared photonic filter is designed. It has the advantages of polarization insensitivity, ultrawide angle, high manufacturability, and easy integration. For infrared spectrum reconstruction, the use of filters as spectral sampling channels can eliminate the influence of slits or complex optical splitting elements in spectral imaging technology. Further, we propose a low-rank matrix logarithm regularization algorithm based on a three-segment filter function (IReg algorithm) combined with the designed filter for a variety of mid-infrared detector front ends, which can significantly suppress noise interference. Here, we demonstrate that the stability of the spectral reconstruction accuracy under the large disturbance environment obtained by the IReg algorithm is much higher than those of the L2 and L1 algorithms. In the low-dimensional matrix state, the accuracy and stability of the ill-conditioned linear equations are guaranteed, the anti-noise ability is enhanced, the effect of data dimensionality reduction is realized, and the accuracy of mid-infrared spectral reconstruction is improved.

Abstract 4907: RanBALL: Identifying B-cell acute lymphoblastic leukemia subtypes based on an ensemble random projection model

Abstract As the most common pediatric malignancy, B-cell acute lymphoblastic leukemia (B-ALL) has multiple distinct subtypes characterized by recurrent and sporadic somatic and germline genetic alterations like chromosomal alteration, transcription factor rearrangement or kinase inhibition. The treatment of B-ALL patients is personalized based on specific subtypes, as the treatment responses for different B-ALL subtypes may vary considerably. Identification of B-ALL subtypes can facilitate risk stratification and enable tailored therapeutic approaches. Existing methods for B-ALL subtyping primarily depend on immunophenotypic, cytogenetic and genomic analyses, which would be costly, complicated, and laborious in clinical practice applications. To overcome these challenges, we present RanBALL (an Ensemble Random Projection-Based Model for Identifying B-Cell Acute Lymphoblastic Leukemia Subtypes), an accurate and cost-effective model for B-ALL subtype identification based on transcriptomic profiling only. RanBALL leverages random projection (RP) to construct an ensemble of dimension-reduced multi-class classifiers for B-ALL subtyping. Specifically, the transcriptomic profiling features were projected onto low-dimensional spaces by random projection matrices whose elements conform to a distribution characterized by zero mean and unit variance. To ensure reliable and robust performance, we selected 20 subspace dimensions ranging from 600 to 2500, with intervals of 100. The transformed low dimensional data matrix was used for training an ensemble of multi-class support vector machine (SVM) classifiers, each corresponding to one of the RP matrices of various dimensions. The predicted probabilistic scores of each B-ALL subtype were integrated for determining the final decision. Results based on 10 times 10-fold cross validation tests for >1700 B-ALL patients demonstrated that the proposed model achieved an accuracy of 93.7%, indicating promising prediction capabilities of RanBALL for B-ALL subtyping. Furthermore, the 30% held-out tests suggested that the model was robust and consistent to maintain high confidence levels for accurate predictions. The high accuracies of RanBALL suggested that our model could effectively capture underlying patterns of transcriptomic profiling for accurate B-ALL subtype identification. To extend the impact of RanBALL, we have established a free and publicly available python package for RanBALL available at https://github.com/wan-mlab/RanBALL. We believe RanBALL will facilitate the discovery of B-ALL subtype-specific marker genes and therapeutic targets, and eventually have consequential positive impacts on downstream risk stratification and tailored treatment design. Citation Format: Lusheng Li, Hanyu Xiao, Joseph D. Khoury, Jieqiong Wang, Shibiao Wan. RanBALL: Identifying B-cell acute lymphoblastic leukemia subtypes based on an ensemble random projection model [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4907.

Gaussian-process-regression-based method for the localization of exceptional points in complex resonance spectra

Resonances in open quantum systems depending on at least two controllable parameters can show the phenomenon of exceptional points (EPs), where not only the eigenvalues but also the eigenvectors of two or more resonances coalesce. Their exact localization in the parameter space is challenging, in particular in systems, where the computation of the quantum spectra and resonances is numerically very expensive. We introduce an efficient machine learning algorithm to find EPs based on Gaussian process regression (GPR). The GPR-model is trained with an initial set of eigenvalue pairs belonging to an EP and used for a first estimation of the EP position via a numerically cheap root search. The estimate is then improved iteratively by adding selected exact eigenvalue pairs as training points to the GPR-model. The GPR-based method is developed and tested on a simple low-dimensional matrix model and then applied to a challenging real physical system, viz., the localization of EPs in the resonance spectra of excitons in cuprous oxide in external electric and magnetic fields. The precise computation of EPs, by taking into account the complete valence band structure and central-cell corrections of the crystal, can be the basis for the experimental observation of EPs in this system.

Nanoscopic decoration of multivalent vanadium oxide on Laser-Induced graphene fibers via atomic layer deposition for flexible gel supercapacitors

Composite materials for high energy/power density supercapacitors are of very high importance. The precise well-defined nanoarchitectonics approach is a key element in the construction of high-performance devices. Surface redox reactions that frequently involve the exchange of oxygen atoms are fundamental to pseudocapacitive reactions mostly mediated by transition metal oxides (TMO). This process often changes the surface stoichiometry and atomic rearrangement in case of uncontrolled growth of TMO. Atomic layer deposition (ALD) has proven to be a facile process for smooth and uniform decoration of TMO on the electrochemically active carbon material to form a binder-free flexible composite material for supercapacitor (SC) applications. Although active carbon materials can be fabricated using various printing and lithographic techniques, continued improvement of cost and scalability, and low dimensional matrix are required to realize their full potential. Here, we demonstrate the scalable fabrication of laser-induced graphene fibers (LIGF) followed by ALD of multivalent vanadium oxide (VOx) films on the LIGF network (VOx-LIGF). The resultant VOx-LIGF shows a specific areal capacitance as high as 99 mF cm−2 at 1 mA cm−2 (aqueous solution, three-electrode cell) and 2 mF cm−2 at 0.25 mA cm−2 (gel electrolyte, two electrode cell). Moreover, the miniaturized supercapacitor device delivers a power density of 244 mW cm−3 as well as long-term cycling stability (93 % capacitance retention after 11,500 cycles) which is among the highest values achieved for any SC. Despite mechanical stress, these flexible supercapacitors maintain excellent electrochemical aspects and thus hold promise for high-power flexible and wearable electronics. Such a general, precise, well-defined, and low-cost route for atomic layer deposition-laser pulse-enhanced supercapacitor materials should find widespread applications.

ECCA: Efficient Correntropy-Based Clustering Algorithm With Orthogonal Concept Factorization.

One of the hottest topics in unsupervised learning is how to efficiently and effectively cluster large amounts of unlabeled data. To address this issue, we propose an orthogonal conceptual factorization (OCF) model to increase clustering effectiveness by restricting the degree of freedom of matrix factorization. In addition, for the OCF model, a fast optimization algorithm containing only a few low-dimensional matrix operations is given to improve clustering efficiency, as opposed to the traditional CF optimization algorithm, which involves dense matrix multiplications. To further improve the clustering efficiency while suppressing the influence of the noises and outliers distributed in real-world data, an efficient correntropy-based clustering algorithm (ECCA) is proposed in this article. Compared with OCF, an anchor graph is constructed and then OCF is performed on the anchor graph instead of directly performing OCF on the original data, which can not only further improve the clustering efficiency but also inherit the advantages of the high performance of spectral clustering. In particular, the introduction of the anchor graph makes ECCA less sensitive to changes in data dimensions and still maintains high efficiency at higher data dimensions. Meanwhile, for various complex noises and outliers in real-world data, correntropy is introduced into ECCA to measure the similarity between the matrix before and after decomposition, which can greatly improve the clustering effectiveness and robustness. Subsequently, a novel and efficient half-quadratic optimization algorithm was proposed to quickly optimize the ECCA model. Finally, extensive experiments on different real-world datasets and noisy datasets show that ECCA can archive promising effectiveness and robustness while achieving tens to thousands of times the efficiency compared with other state-of-the-art baselines.

Recent Advances in Algorithmic Problems for Semigroups

In this article we survey recent progress in the algorithmic theory of matrix semigroups. The main objective in this area of study is to construct algorithms that decide various properties of finitely generated subsemi-groups of an infinite group G , often represented as a matrix group. Such problems might not be decidable in general. In fact, they gave rise to some of the earliest undecidability results in algorithmic theory. However, the situation changes when the group G satisfies additional constraints. In this survey, we give an overview of the decidability and the complexity of several algorithmic problems in the cases where G is a low-dimensional matrix group, or a group with additional structures such as commutativity, nilpotency and solvability.

Low-rank latent matrix-factor prediction modeling for generalized high-dimensional matrix-variate regression.

Motivated by diagnosing the COVID-19 disease using two-dimensional (2D) image biomarkers from computed tomography (CT) scans, we propose a novel latent matrix-factor regression model to predict responses that may come from an exponential distribution family, where covariates include high-dimensional matrix-variate biomarkers. A latent generalized matrix regression (LaGMaR) is formulated, where the latent predictor is a low-dimensional matrix factor score extracted from the low-rank signal of the matrix variate through a cutting-edge matrix factor model. Unlike the general spirit of penalizing vectorization plus the necessity of tuning parameters in the literature, instead, our prediction modeling in LaGMaR conducts dimension reduction that respects the geometric characteristic of intrinsic 2D structure of the matrix covariate and thus avoids iteration. This greatly relieves the computation burden, and meanwhile maintains structural information so that the latent matrix factor feature can perfectly replace the intractable matrix-variate owing to high-dimensionality. The estimation procedure of LaGMaR is subtly derived by transforming the bilinear form matrix factor model onto a high-dimensional vector factor model, so that the method of principle components can be applied. We establish bilinear-form consistency of the estimated matrix coefficient of the latent predictor and consistency of prediction. The proposed approach can be implemented conveniently. Through simulation experiments, the prediction capability of LaGMaR is shown to outperform some existing penalized methods under diverse scenarios of generalized matrix regressions. Through the application to a real COVID-19 dataset, the proposed approach is shown to predict efficiently the COVID-19.

A multi-view clustering algorithm based on deep semi-NMF

Multi-view clustering (MVC) aims to fuse the information among multiple views to achieve effective clustering. Many MVC algorithms based on semi-nonnegative matrix factorization (SNMF) typically have two issues: (1) their optimization schemes are not flexible enough; and (2) the variables are updated only rely on the data but not guided by learning rate. These problems can result in very poor clusters generated. In this paper, we present a multi-view clustering algorithm based on deep SNMF (MCDS) to resolve these issues. Specifically, we first design two types of activation functions to restrict the value domain of the element in the low-dimensional matrix to eliminate the constraint. Then, the SGD algorithm is used to implement element update guided by the learning rate. After obtaining the corresponding weight matrix and bias matrix, we combine them with the activation functions to construct a deep SNMF (DSNMF) network. This network is to update the element in the corresponding low-dimensional matrix for each view and obtain the consensus matrix. To validate the proposed algorithm, numerous experiments are performed on six multi-view datasets including both normal and large-scale datasets. The results demonstrate that MCDS can achieve excellent clustering results and outperform other competitive methods.

Graph Regularized Sparse Non-Negative Matrix Factorization for Clustering

The graph regularized nonnegative matrix factorization (GNMF) algorithms have received a lot of attention in the field of machine learning and data mining, as well as the square loss method is commonly used to measure the quality of reconstructed data. However, noise is introduced when data reconstruction is performed; and the square loss method is sensitive to noise, which leads to degradation in the performance of data analysis tasks. To solve this problem, a novel graph regularized sparse NMF (GSNMF) is proposed in this article. To obtain a cleaner data matrix to approximate the high-dimensional matrix, the l₁-norm to the low-dimensional matrix is added to achieve the adjustment of data eigenvalues in the matrix and sparsity constraint. In addition, the corresponding inference and alternating iterative update algorithm to solve the optimization problem are given. Then, an extension of GSNMF, namely, graph regularized sparse nonnegative matrix trifactorization (GSNMTF), is proposed, and the detailed inference procedure is also shown. Finally, the experimental results on eight different datasets demonstrate that the proposed model has a good performance.

Model order reduction based on low-rank decomposition of the cross Gramian

This paper considers model order reduction based on low-rank decomposition of the cross Gramian for linear systems. The proposed approach uses the low-rank factors of the cross Gramian to generate approximate balanced model for the large-scale system. Then, the reduced-order model is obtained by truncating the states corresponding to the small approximate Hankel singular values. The low-rank factors are directly constructed from the expansion coefficients of impulse responses in the space spanned by Legendre polynomials by solving block tridiagonal linear systems. In contrast to balanced truncation related approaches which require to solve Sylvester equation to compute the full cross Gramian, the proposed method needs to solve sparse linear equations, and only one singular value decomposition is applied to a low-dimensional matrix. The stability preservation of the reduced model is briefly discussed. And in combination with the dominant subspace projection method, the reduction procedure is modified to alleviate the shortcoming, which may unexpectedly lead to unstable systems even though the original one is stable. Finally, numerical experiments are given to demonstrate the effectiveness of the proposed methods.

Adaptive graph regularization and self-expression for noise-aware feature selection

Many traditional unsupervised feature selection algorithms utilize manifold information to mine the local structure of the data. However, the noise existing in the raw data reduces the accuracy of the manifold information of data, which affects the learning effect of the entire algorithm. In order to solve the above problems and more fully find the internal structure inside the data, this paper proposes an adaptive graph regularization and self-expression for noise-aware feature selection (ASNFS). Firstly, the algorithm adopts non-negative matrix factorization to decompose the raw data matrix, and utilizes the low-dimensional matrix generated after decomposition to replace the raw high-dimensional data matrix. This allows the algorithm to reveal some internal structural information of the raw data while reducing the dimensionality of the data. ASNFS also introduces the orthogonal basis clustering with excellent clustering effect, and the interpretability of the algorithm is enhanced. Secondly, in addition to preserving the manifold information in the low-dimensional projection subspace, the algorithm also preserves the manifold information in the non-negative matrix factorization subspace. Meanwhile, the adaptive graph regularization term added to the objective function enables the algorithm to continuously update the similarity matrix. It can effectively remove the noise inside the raw data, and prevent the occurrence of over-fitting phenomenon of the experimental results caused by the fixed similarity matrix. Finally, the similarity matrix retains the local structure information of the data with each iteration, and the results of the feature selection are reused for the construction of the similarity matrix. ASNFS adopts an alternate iterative method to optimize the objective function, which is simple and effective. Then, the algorithm complexity and convergence are analyzed. ASNFS is compared with seven feature selection algorithms on nine datasets, and the experimental results reflect the effectiveness of ASNFS in feature selection.

A Generalized Deep Learning Algorithm Based on NMF for Multi-View Clustering

Multi-view clustering research is a hot topic in the field of data mining, where complementary information between views can better describe data objects and improve the clustering performance. Non-negative matrix factorization (NMF) based multi-view clustering algorithm suffers from weak feature extraction, slow convergence speed and low accuracy. To solve these problems, this paper proposes a generalized deep learning multi-view clustering (GDLMC) algorithm based on NMF. Firstly, via decoupling the elements in the matrix, the matrix elements are non-negatively restricted using an activation function with a non-negative value domain, and the elements are updated employing stochastic gradient descent with learning rate guidance. Then, the corresponding gradients when the elements update are transformed into generalized weights and generalized biases, followed by combining the generalized weights and generalized biases with activation functions to construct generalized deep learning (GDL). Further, GDL is adopted to learn the corresponding low-dimensional matrix of each view and consensus matrix for obtaining the GDLMC algorithm. In addition, the detailed reasoning of the GDLMC algorithm are given. Finally, extensive experiments are conducted on four public datasets including regular and large-scale datasets, and the experimental results show that GDLMC has significant advantages.

Harmonic Balance Analysis of Lur’e Oscillator Network With Non-Diffusive Weak Coupling

The central pattern generator (CPG) is a group of interconnected neurons, existing in biological systems as a control center for oscillatory behaviors. We propose a new approach based on the multivariable harmonic balance to characterize the relationship between the oscillation profile (frequency, amplitude, phase) and interconnections within the CPG, modeled as weakly coupled oscillators. In particular, taking advantage of the weak coupling, we formulate a low-dimensional matrix whose eigenvalue/eigenvector capture the perturbation in the oscillation profile due to the coupling. Then we develop an algorithm to estimate the perturbed oscillation profile of a given CPG, and suggest an optimization to synthesize the interconnections to produce a given oscillation profile.

A Multimodel-Based Deep Learning Framework for Short Text Multiclass Classification with the Imbalanced and Extremely Small Data Set.

Text classification plays an important role in many practical applications. In the real world, there are extremely small datasets. Most existing methods adopt pretrained neural network models to handle this kind of dataset. However, these methods are either difficult to deploy on mobile devices because of their large output size or cannot fully extract the deep semantic information between phrases and clauses. This paper proposes a multimodel-based deep learning framework for short-text multiclass classification with an imbalanced and extremely small dataset. Our framework mainly includes five layers: the encoder layer, the word-level LSTM network layer, the sentence-level LSTM network layer, the max-pooling layer, and the SoftMax layer. The encoder layer uses DistilBERT to obtain context-sensitive dynamic word vectors that are difficult to represent in traditional feature engineering methods. Since the transformer part of this layer is distilled, our framework is compressed. Then, we use the next two layers to extract deep semantic information. The output of the encoder layer is sent to a bidirectional LSTM network, and the feature matrix is extracted hierarchically through the LSTM at the word and sentence level to obtain the fine-grained semantic representation. After that, the max-pooling layer converts the feature matrix into a lower-dimensional matrix, preserving only the obvious features. Finally, the feature matrix is taken as the input of a fully connected SoftMax layer, which contains a function that can convert the predicted linear vector into the output value as the probability of the text in each classification. Extensive experiments on two public benchmarks demonstrate the effectiveness of our proposed approach on an extremely small dataset. It retains the state-of-the-art baseline performance in terms of precision, recall, accuracy, and F1 score, and through the model size, training time, and convergence epoch, we can conclude that our method can be deployed faster and lighter on mobile devices.

Matrix Factorization-Based Dimensionality Reduction Algorithms─A Comparative Study on Spectroscopic Profiling Data.

Spectroscopic profiling data used in analytical chemistry can be very high-dimensional. Dimensionality reduction (DR) is an effective way to handle the potential "curse of dimensionality" problem. Among the existing DR algorithms, many can be categorized as a matrix factorization (MF) problem, which decomposes the original data matrix X into the product of a low-dimensional matrix W and a dictionary matrix H. First, this paper provides a theoretical reformulation of relevant DR algorithms under a unified MF perspective, including PCA (principal component analysis), NMF (non-negative matrix factorization), LAE (linear autoencoder), RP (random projection), SRP (sparse random projection), VQ (vector quantization), AA (archetypical analysis), and ICA (independent component analysis). From this perspective, an open-sourced toolkit has been developed to integrate all of the above algorithms with a unified API. Second, we made a comparative study on MF-based DR algorithms. In a case study of TOF (time-of-flight) mass spectra, the eight algorithms extracted three components from the original 27,619 features. The results are compared by a set of DR quality metrics, e.g., reconstruction error, pairwise distance/ranking property, computational cost, local and global structure preservations, etc. Finally, based on the case study result, we summarized guidelines for DR algorithm selection. (1) For reconstruction quality, choose ICA. In the case study, ICA, PCA, and NMF have high reconstruction qualities (reconstruction error < 2%), ICA being the best. (2) To keep the pairwise topological structure, choose PCA. PCA best preserves the pairwise distance/ranking property. (3) For edge computing and IoT scenarios, choose RP or SRP if reconstruction is not required and the JL-lemma condition is met. The RP family has the best computational performance in the experiment, almost 10-100 times faster than its peers.

A Nyström-Based Low-Complexity Algorithm with Improved Effective Array Aperture for Coherent DOA Estimation in Monostatic MIMO Radar

In this paper, we propose a computationally efficient algorithm with improved effective aperture for coherent angle estimation in a monostatic multiple-input multiple-output (MIMO) radar. First, the direction matrix of MIMO radar is mapped into a low-dimensional matrix of virtual uniform linear array (ULA). Then, an augmented data expansion matrix with improved effective aperture is obtained by exploiting the Vandermonde-like structure of the low-dimensional direction matrix and radar cross section (RCS) matrix to enlarge the aperture of the array. Next, a unitary transformation is used to transform the augmented matrix into a real value and the approximate signal subspace of the augmented matrix is obtained by the Nyström method, which can reduce the computational complexity. The eigenvectors of the approximate signal subspace are used to reconstruct the matrix for direct decorrelation processing. Finally, direction of arrivals (DOAs) can be estimated faster by utilizing the unitary ESPRIT algorithm since the rotation invariance of the extended reconstruction matrix still exists. The proposed algorithm has a lower total computational complexity, and the estimation accuracy is improved by utilizing real values and enlarging the array aperture for estimation. Several theoretical analyses and simulation results confirm the effectiveness and advantages of the proposed method.

Fast simulation of fully non-stationary wind fields using a new matrix factorization assisted interpolation method

The classical spectral representation method and its improved versions have been widely used to generate non-stationary wind fields. However, they are not efficient for the simulation of non-stationary wind fields with time-varying coherence (i.e., fully non-stationary wind fields) due to the extensive computational demand regarding spectral matrix decomposition or harmonic superposition. To this end, this study develops a new matrix factorization assisted interpolation method, which is composed of an improved interpolation scheme and the monotone projected Barzilai-Borwein based non-negative matrix factorization (MPBB-NMF). Specifically, an improved interpolation scheme is firstly developed to quantify the desired distribution of time-frequency interpolation nodes, and only the decomposed spectra at these nodes are calculated by Cholesky decomposition. Then, MPBB-NMF with a fast global convergence is used to decouple these spectra into products of non-negative time- and frequency-dependent functions. Finally, one-dimensional interpolation is performed for these decoupled functions, which makes it possible to accelerate the harmonic superposition using a small amount of fast Fourier transforms (FFTs). Obviously, the proposed method realizes the decomposition of spectral matrix in the decoupling form. Besides reducing of the number of Cholesky decomposition and invoking FFT, its decoupling only aims at the low dimensional matrix and the interpolation merely involves a few decoupled items. Numerical simulation on the fully non-stationary wind field of a long-span bridge demonstrates the effectiveness and superiority of the proposed method.

Fast simulation of nonstationary wind velocity fields by proper orthogonal decomposition interpolation

The classic spectral representation method (SRM) has been extensively utilized in simulating nonstationary wind velocity fields because of its great precision and simplicity. However, this method is computationally expensive when it is applied to the situation with a great number of simulation positions. Although several attempts have been made to alleviate the computational burden, the efficiency improvement may be limited. To this end, this study develops a proper orthogonal decomposition (POD) interpolation-enhanced approach to expedite the simulation of nonstationary wind fields by SRM. Firstly, the Cholesky decomposition is only executed for the spectral matrices at time-frequency interpolation points and the corresponding computational cost is therefore reduced greatly. The POD interpolation is then used to approximately decouple each decomposed spectrum into a small amount of time and frequency functions, thereby invoking the fast Fourier transform to speed up the summing of cosine functions. The POD operation is merely executed for the low-dimensional matrix and the interpolation operation solely aims at the few time and frequency functions. As a result, the proposed approach has the potential to considerably improve the simulation efficiency. Finally, numerical examples with the simulation of two different nonstationary wind fields validate its precision and efficiency.