arXiv subjects

Wenyuan Li

Publications and source records attributed to Wenyuan Li.

At least 55 records · Page 3Linked to original sources

arXiv2024

RSMamba: Remote Sensing Image Classification with State Space Model

Remote sensing image classification forms the foundation of various understanding tasks, serving a crucial function in remote sensing image interpretation. The recent advancements of Convolutional Neural Networks (CNNs) and Transformers have markedly enhanced classification accuracy. Nonetheless, remote sensing scene classification remains a significant challenge, especially given the complexity and diversity of remote sensing scenarios and the variability of spatiotemporal resolutions. The capacity for whole-image understanding can provide more precise semantic cues for scene discrimination. In this paper, we introduce RSMamba, a novel architecture for remote sensing image classification. RSMamba is based on the State Space Model (SSM) and incorporates an efficient, hardware-aware design known as the Mamba. It integrates the advantages of both a global receptive field and linear modeling complexity. To overcome the limitation of the vanilla Mamba, which can only model causal sequences and is not adaptable to two-dimensional image data, we propose a dynamic multi-path activation mechanism to augment Mamba's capacity to model non-causal data. Notably, RSMamba maintains the inherent modeling mechanism of the vanilla Mamba, yet exhibits superior performance across multiple remote sensing image classification datasets. This indicates that RSMamba holds significant potential to function as the backbone of future visual foundation models. The code will be available at \url{https://github.com/KyanChen/RSMamba}.

cs.CV↗

arXiv2024

Observation-Guided Meteorological Field Downscaling at Station Scale: A Benchmark and a New Method

Downscaling (DS) of meteorological variables involves obtaining high-resolution states from low-resolution meteorological fields and is an important task in weather forecasting. Previous methods based on deep learning treat downscaling as a super-resolution task in computer vision and utilize high-resolution gridded meteorological fields as supervision to improve resolution at specific grid scales. However, this approach has struggled to align with the continuous distribution characteristics of meteorological fields, leading to an inherent systematic bias between the downscaled results and the actual observations at meteorological stations. In this paper, we extend meteorological downscaling to arbitrary scattered station scales, establish a brand new benchmark and dataset, and retrieve meteorological states at any given station location from a coarse-resolution meteorological field. Inspired by data assimilation techniques, we integrate observational data into the downscaling process, providing multi-scale observational priors. Building on this foundation, we propose a new downscaling model based on hypernetwork architecture, namely HyperDS, which efficiently integrates different observational information into the model training, achieving continuous scale modeling of the meteorological field. Through extensive experiments, our proposed method outperforms other specially designed baseline models on multiple surface variables. Notably, the mean squared error (MSE) for wind speed and surface pressure improved by 67% and 19.5% compared to other methods. We will release the dataset and code subsequently.

cs.CV↗

arXiv2024

Learning to detect cloud and snow in remote sensing images from noisy labels

Detecting clouds and snow in remote sensing images is an essential preprocessing task for remote sensing imagery. Previous works draw inspiration from semantic segmentation models in computer vision, with most research focusing on improving model architectures to enhance detection performance. However, unlike natural images, the complexity of scenes and the diversity of cloud types in remote sensing images result in many inaccurate labels in cloud and snow detection datasets, introducing unnecessary noises into the training and testing processes. By constructing a new dataset and proposing a novel training strategy with the curriculum learning paradigm, we guide the model in reducing overfitting to noisy labels. Additionally, we design a more appropriate model performance evaluation method, that alleviates the performance assessment bias caused by noisy labels. By conducting experiments on models with UNet and Segformer, we have validated the effectiveness of our proposed method. This paper is the first to consider the impact of label noise on the detection of clouds and snow in remote sensing images.

cs.CV↗

arXiv2024

DeepPhysiNet: Bridging Deep Learning and Atmospheric Physics for Accurate and Continuous Weather Modeling

Accurate weather forecasting holds significant importance to human activities. Currently, there are two paradigms for weather forecasting: Numerical Weather Prediction (NWP) and Deep Learning-based Prediction (DLP). NWP utilizes atmospheric physics for weather modeling but suffers from poor data utilization and high computational costs, while DLP can learn weather patterns from vast amounts of data directly but struggles to incorporate physical laws. Both paradigms possess their respective strengths and weaknesses, and are incompatible, because physical laws adopted in NWP describe the relationship between coordinates and meteorological variables, while DLP directly learns the relationships between meteorological variables without consideration of coordinates. To address these problems, we introduce the DeepPhysiNet framework, incorporating physical laws into deep learning models for accurate and continuous weather system modeling. First, we construct physics networks based on multilayer perceptrons (MLPs) for individual meteorological variable, such as temperature, pressure, and wind speed. Physics networks establish relationships between variables and coordinates by taking coordinates as input and producing variable values as output. The physical laws in the form of Partial Differential Equations (PDEs) can be incorporated as a part of loss function. Next, we construct hyper-networks based on deep learning methods to directly learn weather patterns from a large amount of meteorological data. The output of hyper-networks constitutes a part of the weights for the physics networks. Experimental results demonstrate that, upon successful integration of physical laws, DeepPhysiNet can accomplish multiple tasks simultaneously, not only enhancing forecast accuracy but also obtaining continuous spatiotemporal resolution results, which is unattainable by either the NWP or DLP.

physics.ao-ph↗

arXiv2023

Time Travelling Pixels: Bitemporal Features Integration with Foundation Model for Remote Sensing Image Change Detection

Change detection, a prominent research area in remote sensing, is pivotal in observing and analyzing surface transformations. Despite significant advancements achieved through deep learning-based methods, executing high-precision change detection in spatio-temporally complex remote sensing scenarios still presents a substantial challenge. The recent emergence of foundation models, with their powerful universality and generalization capabilities, offers potential solutions. However, bridging the gap of data and tasks remains a significant obstacle. In this paper, we introduce Time Travelling Pixels (TTP), a novel approach that integrates the latent knowledge of the SAM foundation model into change detection. This method effectively addresses the domain shift in general knowledge transfer and the challenge of expressing homogeneous and heterogeneous characteristics of multi-temporal images. The state-of-the-art results obtained on the LEVIR-CD underscore the efficacy of the TTP. The Code is available at \url{https://kychen.me/TTP}.

cs.CV↗

arXiv2023

RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model

Leveraging the extensive training data from SA-1B, the Segment Anything Model (SAM) demonstrates remarkable generalization and zero-shot capabilities. However, as a category-agnostic instance segmentation method, SAM heavily relies on prior manual guidance, including points, boxes, and coarse-grained masks. Furthermore, its performance in remote sensing image segmentation tasks remains largely unexplored and unproven. In this paper, we aim to develop an automated instance segmentation approach for remote sensing images, based on the foundational SAM model and incorporating semantic category information. Drawing inspiration from prompt learning, we propose a method to learn the generation of appropriate prompts for SAM. This enables SAM to produce semantically discernible segmentation results for remote sensing images, a concept we have termed RSPrompter. We also propose several ongoing derivatives for instance segmentation tasks, drawing on recent advancements within the SAM community, and compare their performance with RSPrompter. Extensive experimental results, derived from the WHU building, NWPU VHR-10, and SSDD datasets, validate the effectiveness of our proposed method. The code for our method is publicly available at kychen.me/RSPrompter.

cs.CV↗

arXiv2023

Partially Explicit Generalized Multiscale Method for Poroelasticity Problem

We develop a partially explicit time discretization based on the framework of constraint energy minimizing generalized multiscale finite element method (CEM-GMsFEM) for the problem of linear poroelasticity with high contrast. Firstly, dominant basis functions generated by the CEM-GMsFEM approach are used to capture important degrees of freedom and it is known to give contrast-independent convergence that scales with the mesh size. In typical situation, one has very few degrees of freedom in dominant basis functions. This part is treated implicitly. Secondly, we design and introduce an additional space in the complement space and these degrees are treated explicitly. We also investigate the CFL-type stability restriction for this problem, and the restriction for the time step is contrast independent.

math.NA↗

arXiv2023

Efficient Planning of Multi-Robot Collective Transport using Graph Reinforcement Learning with Higher Order Topological Abstraction

Efficient multi-robot task allocation (MRTA) is fundamental to various time-sensitive applications such as disaster response, warehouse operations, and construction. This paper tackles a particular class of these problems that we call MRTA-collective transport or MRTA-CT -- here tasks present varying workloads and deadlines, and robots are subject to flight range, communication range, and payload constraints. For large instances of these problems involving 100s-1000's of tasks and 10s-100s of robots, traditional non-learning solvers are often time-inefficient, and emerging learning-based policies do not scale well to larger-sized problems without costly retraining. To address this gap, we use a recently proposed encoder-decoder graph neural network involving Capsule networks and multi-head attention mechanism, and innovatively add topological descriptors (TD) as new features to improve transferability to unseen problems of similar and larger size. Persistent homology is used to derive the TD, and proximal policy optimization is used to train our TD-augmented graph neural network. The resulting policy model compares favorably to state-of-the-art non-learning baselines while being much faster. The benefit of using TD is readily evident when scaling to test problems of size larger than those used in training.

cs.MA↗

arXiv2023

Continuous Remote Sensing Image Super-Resolution based on Context Interaction in Implicit Function Space

Despite its fruitful applications in remote sensing, image super-resolution is troublesome to train and deploy as it handles different resolution magnifications with separate models. Accordingly, we propose a highly-applicable super-resolution framework called FunSR, which settles different magnifications with a unified model by exploiting context interaction within implicit function space. FunSR composes a functional representor, a functional interactor, and a functional parser. Specifically, the representor transforms the low-resolution image from Euclidean space to multi-scale pixel-wise function maps; the interactor enables pixel-wise function expression with global dependencies; and the parser, which is parameterized by the interactor's output, converts the discrete coordinates with additional attributes to RGB values. Extensive experimental results demonstrate that FunSR reports state-of-the-art performance on both fixed-magnification and continuous-magnification settings, meanwhile, it provides many friendly applications thanks to its unified nature.

cs.CV↗

arXiv2022

Conjugate Fillings and Legendrian Weaves

First, we show that conjugate Lagrangian fillings, associated to plabic graphs, and Lagrangian fillings obtained as Reeb pinching sequences are both Hamiltonian isotopic to Lagrangian projections of Legendrian weaves. In general, we establish a series of new Reidemeister moves for hybrid Lagrangian surfaces. These allow for explicit combinatorial isotopies between the different types of Lagrangian fillings and we use them to show that Legendrian weaves indeed generalize these previously known combinatorial methods to construct Lagrangian fillings. This generalization is strict, as weaves are typically able to produce infinitely many distinct Hamiltonian isotopy classes of Lagrangian fillings, whereas conjugate surfaces and Reeb pinching sequences produce finitely many fillings. Second, we compare the sheaf quantizations associated to each such types of Lagrangian fillings and show that the cluster structures in the corresponding moduli of pseudo-perfect objects coincide. In particular, this shows that the cluster variables in Bott-Samelson cells, given as generalized minors, are geometric microlocal holonomies associated to sheaf quantizations. Similar results are presented for the Fock-Goncharov cluster variables in the moduli spaces of framed local systems. In the course of the article and its appendices, we also establish several technical results needed for a rigorous comparison between the different Lagrangian fillings and their microlocal sheaf invariants.

math.SG↗

arXiv2022

Compositionally Complex Perovskite Oxides for Solar Thermochemical Water Splitting

Solar thermochemical hydrogen generation (STCH) is a promising approach for eco-friendly H2 production, but conventional STCH redox compounds often suffer from thermodynamic and kinetic limitations with limited tunability. Expanding from the nascent high-entropy ceramics field, this study explores a new class of compositionally complex perovskite oxides (La0.8Sr0.2)(Mn(1-x)/3Fe(1-x)/3CoxAl(1-x)/3)O3 for STCH. In situ X-ray diffraction demonstrates the phase stability during redox cycling and in situ X-ray photoelectron spectroscopy shows preferential redox of Co. The extent of reduction increases, but the intrinsic kinetics decreases, with increased Co content. Consequently, (La0.8Sr0.2)(Mn0.2Fe0.2Co0.4Al0.2)O3-δ achieves an optimal balance between the thermodynamics and kinetics properties. The combination of a moderate enthalpy of reduction, high entropy of reduction, and preferable surface oxygen exchange kinetics enables a maximum H2 yield of 395 +- 11 μmol g-1 in a short 1-hour redox duration. Entropy stabilization expectedly contributes to the structure stability during redox without phase transformation, which enables an exceptional STCH stability for >50 cycles under harsh interrupted conditions. The underlying redox mechanism is further elucidated by the density functional theory based parallel Monte Carlo computation, which represents a new computation paradigm first established here. This study suggests a new class of non-equimolar compositionally complex ceramics for STCH and chemical looping.

cond-mat.mtrl-sci↗

arXiv2022

Semantic-aware Dense Representation Learning for Remote Sensing Image Change Detection

Supervised deep learning models depend on massive labeled data. Unfortunately, it is time-consuming and labor-intensive to collect and annotate bitemporal samples containing desired changes. Transfer learning from pre-trained models is effective to alleviate label insufficiency in remote sensing (RS) change detection (CD). We explore the use of semantic information during pre-training. Different from traditional supervised pre-training that learns the mapping from image to label, we incorporate semantic supervision into the self-supervised learning (SSL) framework. Typically, multiple objects of interest (e.g., buildings) are distributed in various locations in an uncurated RS image. Instead of manipulating image-level representations via global pooling, we introduce point-level supervision on per-pixel embeddings to learn spatially-sensitive features, thus benefiting downstream dense CD. To achieve this, we obtain multiple points via class-balanced sampling on the overlapped area between views using the semantic mask. We learn an embedding space where background and foreground points are pushed apart, and spatially aligned points across views are pulled together. Our intuition is the resulting semantically discriminative representations invariant to irrelevant changes (illumination and unconcerned land covers) may help change recognition. We collect large-scale image-mask pairs freely available in the RS community for pre-training. Extensive experiments on three CD datasets verify the effectiveness of our method. Ours significantly outperforms ImageNet pre-training, in-domain supervision, and several SSL methods. Empirical results indicate our pre-training improves the generalization and data efficiency of the CD model. Notably, we achieve competitive results using 20% training data than baseline (random initialization) using 100% data. Our code is available.

cs.CV↗

arXiv2022

Hybrid explicit-implicit learning for multiscale problems with time dependent source

The splitting method is a powerful method for solving partial differential equations. Various splitting methods have been designed to separate different physics, nonlinearities, and so on. Recently, a new splitting approach has been proposed where some degrees of freedom are handled implicitly while other degrees of freedom are handled explicitly. As a result, the scheme contains two equations, one implicit and the other explicit. The stability of this approach has been studied. It was shown that the time step scales as the coarse spatial mesh size, which can provide a significant computational advantage. However, the implicit solution part can still be expensive, especially for nonlinear problems. In this paper, we introduce modified partial machine learning algorithms to replace the implicit solution part of the algorithm. These algorithms are first introduced in arXiv:2109.02147, where a homogeneous source term is considered along with the Transformer, which is a neural network that can predict future dynamics. In this paper, we consider time-dependent source terms which is a generalization of the previous work. Moreover, we use the whole history of the solution to train the network. As the implicit part of the equations is more complicated to solve, we design a neural network to predict it based on training. Furthermore, we compute the explicit part of the solution using our splitting strategy. In addition, we use Proper Orthogonal Decomposition based model reduction in machine learning. The machine learning algorithms provide computational saving without sacrificing accuracy. We present three numerical examples which show that our machine learning scheme is stable and accurate.

math.NA↗

arXiv2022

Nonlocal transport equations in multiscale media. Modeling, dememorization, and discretizations

In this paper, we consider a class of convection-diffusion equations with memory effects. These equations arise as a result of homogenization or upscaling of linear transport equations in heterogeneous media and play an important role in many applications. First, we present a dememorization technique for these equations. We show that the convection-diffusion equations with memory effects can be written as a system of standard convection-diffusion-reaction equations. This allows removing the memory term and simplifying the computations. We consider a relation between dememorized equations and micro-scale equations, which do not contain memory terms. We note that dememorized equations differ from micro-scale equations and constitute a macroscopic model. Next, we consider both implicit and partially explicit methods. The latter is introduced for problems in multiscale media with high-contrast properties. Because of high contrast, explicit methods are restrictive and require time steps that are very small (scales as the inverse of the contrast). We show that, by appropriately decomposing the space, we can treat only a few degrees of freedom implicitly and the remaining degrees of freedom explicitly. We present a stability analysis. Numerical results are presented that confirm our theoretical findings of partially explicit schemes applied to dememorized systems of equations.

math.NA↗

arXiv2021

Partially Explicit Time Discretization for Nonlinear Time Fractional Diffusion Equations

Nonlinear time fractional partial differential equations are widely used in modeling and simulations. In many applications, there are high contrast changes in media properties. For solving these problems, one often uses coarse spatial grid for spatial resolution. For temporal discretization, implicit methods are often used. For implicit methods, though the time step can be relatively large, the equations are difficult to compute due to the nonlinearity and the fact that one deals with large-scale systems. On the other hand, the discrete system in explicit methods are easier to compute but it requires small time steps. In this work, we propose the partially explicit scheme following earlier works on developing partially explicit methods for nonlinear diffusion equations. In this scheme, the diffusion term is treated partially explicitly and the reaction term is treated fully explicitly. With the appropriate construction of spaces and stability analysis, we find that the required time step in our proposed scheme scales as the coarse mesh size, which creates a great saving in computing. The main novelty of this work is the extension of our earlier works for diffusion equations to time fractional diffusion equations. For the case of fractional diffusion equations, the constraints on time steps are more severe and the proposed methods alleviate this since the time step in partially explicit method scales as the coarse mesh size. We present stability results. Numerical results are presented where we compare our proposed partially explicit methods with a fully implicit approach. We show that our proposed approach provides similar results, while treating many degrees of freedom in nonlinear terms explicitly.

math.NA↗

arXiv2021

Contrast-independent partially explicit time discretizations for nonlinear multiscale problems

This work continues a line of works on developing partially explicit methods for multiscale problems. In our previous works, we have considered linear multiscale problems, where the spatial heterogeneities are at subgrid level and are not resolved. In these works, we have introduced contrast-independent partially explicit time discretizations for linear equations. The contrast-independent partially explicit time discretization divides the spatial space into two components: contrast dependent (fast) and contrast independent (slow) spaces defined via multiscale space decomposition. Following this decomposition, temporal splitting is proposed that treats fast components implicitly and slow components explicitly. The space decomposition and temporal splitting are chosen such that it guarantees a stability and formulate a condition for the time stepping. This condition is formulated as a condition on slow spaces. In this paper, we extend this approach to nonlinear problems. We propose a splitting approach and derive a condition that guarantees stability. This condition requires some type of contrast-independent spaces for slow components of the solution. We present numerical results and show that the proposed methods provide results similar to implicit methods with the time step that is independent of the contrast.

math.NA↗

arXiv2021

Geographical Knowledge-driven Representation Learning for Remote Sensing Images

The proliferation of remote sensing satellites has resulted in a massive amount of remote sensing images. However, due to human and material resource constraints, the vast majority of remote sensing images remain unlabeled. As a result, it cannot be applied to currently available deep learning methods. To fully utilize the remaining unlabeled images, we propose a Geographical Knowledge-driven Representation learning method for remote sensing images (GeoKR), improving network performance and reduce the demand for annotated data. The global land cover products and geographical location associated with each remote sensing image are regarded as geographical knowledge to provide supervision for representation learning and network pre-training. An efficient pre-training framework is proposed to eliminate the supervision noises caused by imaging times and resolutions difference between remote sensing images and geographical knowledge. A large scale pre-training dataset Levir-KR is proposed to support network pre-training. It contains 1,431,950 remote sensing images from Gaofen series satellites with various resolutions. Experimental results demonstrate that our proposed method outperforms ImageNet pre-training and self-supervised representation learning methods and significantly reduces the burden of data annotation on downstream tasks such as scene classification, semantic segmentation, object detection, and cloud / snow detection. It demonstrates that our proposed method can be used as a novel paradigm for pre-training neural networks. Codes will be available on https://github.com/flyakon/Geographical-Knowledge-driven-Representaion-Learning.

cs.CV↗

arXiv2021

Generation of In-group Asset Condition Data for Power System Reliability Assessment

In a power system, unlike some critical and standalone assets that are equipped with condition monitoring devices, the conditions of most regular in-group assets are acquired through periodic inspection work. Due to their large quantities, significant amount of manual inspection effort and sometimes data management issues, it is not uncommon to see the asset condition data in a target study area is unavailable or incomplete. Lack of asset condition data undermines the reliability assessment work. To solve this data problem and enhance data availability, this paper explores an unconventional method-generating numerical and non-numerical asset condition data based on condition degradation, condition correlation and categorical distribution models. Empirical knowledge from human experts can also be incorporated in the modeling process. Also, a probabilistic diversification step can be taken to make the generated numerical condition data probabilistic. This method can generate close-to-real asset condition data and has been validated systematically based on two public datasets. An area reliability assessment example based on cables is given to demonstrate the usefulness of this method and its generated data. This method can also be used to conveniently generate hypothetical asset condition data for research purposes.

cs.CE↗