arXiv subjects

Thanh Huy Nguyen

Publications and source records attributed to Thanh Huy Nguyen.

28 records · Page 2Linked to original sources

arXiv2022

Improvement of Flood Extent Representation with Remote Sensing Data and Data Assimilation

Flood simulation and forecast capability have been greatly improved thanks to advances in data assimilation. Such an approach combines in-situ gauge measurements with numerical hydrodynamic models to correct the hydraulic states and reduce the uncertainties in the model parameters. However, these methods depend strongly on the availability and quality of observations, thus necessitating other data sources to improve the flood simulation and forecast performances. Using Sentinel-1 images, a flood extent mapping method was carried out by applying a Random Forest algorithm trained on past flood events using manually delineated flood maps. The study area concerns a 50-km reach of the Garonne Marmandaise catchment. Two recent flood events are simulated in analysis and forecast modes, with a +24h lead time. This study demonstrates the merits of using SAR-derived flood extent maps to validate and improve the forecast results based on hydrodynamic numerical models with Telemac2D-EnKF. Quantitative 1D and 2D metrics were computed to assess water level time-series and flood extents between the simulations and observations. It was shown that the free run experiment without DA under-estimates flooding. On the other hand, the validation of DA results with respect to independent SAR-derived flood extent allows to diagnose a model-observation bias that leads to over-flooding. Once this bias is taken into account, DA provides a sequential correction of area-based friction coefficients and inflow discharge, yielding a better flood extent representation. This study paves the way towards a reliable solution for flood forecasting over poorly gauged catchments, thanks to available remote sensing datasets.

eess.IV↗

arXiv2021

Validation and Improvement of Data Assimilation for Flood Hydrodynamic Modelling Using SAR Imagery Data

Relevant comprehension of flood hazards has emerged as a crucial necessity, especially as the severity and the occurrence of flood events intensify with climate changes. Flood simulation and forecast capability have been greatly improved thanks to advances in data assimilation. This approach combines in-situ gauge measurements with hydrodynamic models, aiming to correct the hydraulic states and reduce the uncertainties in the model parameters, e.g., friction coefficients, inflow discharge. These methods depend strongly on the availability and quality of observations, thus requiring other data sources to improve the flood simulation and forecast quality. Sentinel-1 images collected during a flood event were used to classify an observed scene into dry and wet areas. The study area concerns the Garonne Marmandaise catchment, and focuses on recent flood event in January-February 2021. In this paper, seven experiments are carried out, two in free run modes (FR1 and FR2) and five in data assimilation modes (DA1 to DA5). A model-observation bias was diagnosed and corrected over the beginning of the flood event. Quantitative assessments are carried out involving 1D metrics at Vigicrue observing stations and 2D metrics with respect to the Sentinel-1 derived flood extent maps. They demonstrate improvements on flood extent representation thanks to the data assimilation and bias correction.

eess.IV↗

arXiv2020

Super-Resolution-based Snake Model -- An Unsupervised Method for Large-Scale Building Extraction using Airborne LiDAR Data and Optical Image

Automatic extraction of buildings in urban and residential scenes has become a subject of growing interest in the domain of photogrammetry and remote sensing, particularly since mid-1990s. Active contour model, colloquially known as snake model, has been studied to extract buildings from aerial and satellite imagery. However, this task is still very challenging due to the complexity of building size, shape, and its surrounding environment. This complexity leads to a major obstacle for carrying out a reliable large-scale building extraction, since the involved prior information and assumptions on building such as shape, size, and color cannot be generalized over large areas. This paper presents an efficient snake model to overcome such challenge, called Super-Resolution-based Snake Model (SRSM). The SRSM operates on high-resolution LiDAR-based elevation images -- called z-images -- generated by a super-resolution process applied to LiDAR data. The involved balloon force model is also improved to shrink or inflate adaptively, instead of inflating the snake continuously. This method is applicable for a large scale such as city scale and even larger, while having a high level of automation and not requiring any prior knowledge nor training data from the urban scenes (hence unsupervised). It achieves high overall accuracy when tested on various datasets. For instance, the proposed SRSM yields an average area-based Quality of 86.57% and object-based Quality of 81.60% on the ISPRS Vaihingen benchmark datasets. Compared to other methods using this benchmark dataset, this level of accuracy is highly desirable even for a supervised method. Similarly desirable outcomes are obtained when carrying out the proposed SRSM on the whole City of Quebec (total area of 656 km2), yielding an area-based Quality of 62.37% and an object-based Quality of 63.21%.

cs.CV↗

arXiv2020

Coarse-to-Fine Registration of Airborne LiDAR Data and Optical Imagery on Urban Scenes

Applications based on synergistic integration of optical imagery and LiDAR data are receiving a growing interest from the remote sensing community. However, a misaligned integration between these datasets may fail to fully profit the potential of both sensors. In this regard, an optimum fusion of optical imagery and LiDAR data requires an accurate registration. This is a complex problem since a versatile solution is still missing, especially when considering the context where data are collected at different times, from different platforms, under different acquisition configurations. This paper presents a coarse-to-fine registration method of aerial/satellite optical imagery with airborne LiDAR data acquired in such context. Firstly, a coarse registration involves extracting and matching of buildings from LiDAR data and optical imagery. Then, a Mutual Information-based fine registration is carried out. It involves a super-resolution approach applied to LiDAR data, and a local approach of transformation model estimation. The proposed method succeeds at overcoming the challenges associated with the aforementioned difficult context. Considering the experimented airborne LiDAR (2011) and orthorectified aerial imagery (2016) datasets, their spatial shift is reduced by 48.15% after the proposed coarse registration. Moreover, the incompatibility of size and spatial resolution is addressed by the mentioned super-resolution. Finally, a high accuracy of dataset alignment is also achieved, highlighted by a 40-cm error based on a check-point assessment and a 64-cm error based on a check-pair-line assessment. These promising results enable further research for a complete versatile fusion methodology between airborne LiDAR and optical imagery data in this challenging context.

eess.IV↗

arXiv2019

On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks

The gradient noise (GN) in the stochastic gradient descent (SGD) algorithm is often considered to be Gaussian in the large data regime by assuming that the \emph{classical} central limit theorem (CLT) kicks in. This assumption is often made for mathematical convenience, since it enables SGD to be analyzed as a stochastic differential equation (SDE) driven by a Brownian motion. We argue that the Gaussianity assumption might fail to hold in deep learning settings and hence render the Brownian motion-based analyses inappropriate. Inspired by non-Gaussian natural phenomena, we consider the GN in a more general context and invoke the \emph{generalized} CLT, which suggests that the GN converges to a \emph{heavy-tailed} $α$-stable random vector, where \emph{tail-index} $α$ determines the heavy-tailedness of the distribution. Accordingly, we propose to analyze SGD as a discretization of an SDE driven by a Lévy motion. Such SDEs can incur `jumps', which force the SDE and its discretization \emph{transition} from narrow minima to wider minima, as proven by existing metastability theory and the extensions that we proved recently. In this study, under the $α$-stable GN assumption, we further establish an explicit connection between the convergence rate of SGD to a local minimum and the tail-index $α$. To validate the $α$-stable assumption, we conduct experiments on common deep learning scenarios and show that in all settings, the GN is highly non-Gaussian and admits heavy-tails. We investigate the tail behavior in varying network architectures and sizes, loss functions, and datasets. Our results open up a different perspective and shed more light on the belief that SGD prefers wide minima.

stat.ML↗

arXiv2019

Unsupervised Automatic Building Extraction Using Active Contour Model on Unregistered Optical Imagery and Airborne LiDAR Data

Automatic extraction of buildings in urban scenes has become a subject of growing interest in the domain of photogrammetry and remote sensing, particularly with the emergence of LiDAR systems since mid-1990s. However, in reality, this task is still very challenging due to the complexity of building size and shapes, as well as its surrounding environment. Active contour model, colloquially called snake model, which has been extensively used in many applications in computer vision and image processing, is also applied to extract buildings from aerial/satellite imagery. Motivated by the limitations of existing snake models addressing to the building extraction, this paper presents an unsupervised and fully automatic snake model to extract buildings using optical imagery and an unregistered airborne LiDAR dataset, without manual initial points or training data. The proposed method is shown to be capable of extracting buildings with varying color from complex environments, and yielding high overall accuracy.

cs.CV↗

arXiv2019

First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise

Stochastic gradient descent (SGD) has been widely used in machine learning due to its computational efficiency and favorable generalization properties. Recently, it has been empirically demonstrated that the gradient noise in several deep learning settings admits a non-Gaussian, heavy-tailed behavior. This suggests that the gradient noise can be modeled by using $α$-stable distributions, a family of heavy-tailed distributions that appear in the generalized central limit theorem. In this context, SGD can be viewed as a discretization of a stochastic differential equation (SDE) driven by a Lévy motion, and the metastability results for this SDE can then be used for illuminating the behavior of SGD, especially in terms of `preferring wide minima'. While this approach brings a new perspective for analyzing SGD, it is limited in the sense that, due to the time discretization, SGD might admit a significantly different behavior than its continuous-time limit. Intuitively, the behaviors of these two systems are expected to be similar to each other only when the discretization step is sufficiently small; however, to the best of our knowledge, there is no theoretical understanding on how small the step-size should be chosen in order to guarantee that the discretized system inherits the properties of the continuous-time system. In this study, we provide formal theoretical analysis where we derive explicit conditions for the step-size such that the metastability behavior of the discrete-time system is similar to its continuous-time limit. We show that the behaviors of the two systems are indeed similar for small step-sizes and we identify how the error depends on the algorithm and problem parameters. We illustrate our results with simulations on a synthetic model and neural networks.

stat.ML↗

arXiv2019

Robust Building-based Registration of Airborne LiDAR Data and Optical Imagery on Urban Scenes

The motivation of this paper is to address the problem of registering airborne LiDAR data and optical aerial or satellite imagery acquired from different platforms, at different times, with different points of view and levels of detail. In this paper, we present a robust registration method based on building regions, which are extracted from optical images using mean shift segmentation, and from LiDAR data using a 3D point cloud filtering process. The matching of the extracted building segments is then carried out using Graph Transformation Matching (GTM) which allows to determine a common pattern of relative positions of segment centers. Thanks to this registration, the relative shifts between the data sets are significantly reduced, which enables a subsequent fine registration and a resulting high-quality data fusion.

cs.CV↗

arXiv2019

Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization

Recent studies on diffusion-based sampling methods have shown that Langevin Monte Carlo (LMC) algorithms can be beneficial for non-convex optimization, and rigorous theoretical guarantees have been proven for both asymptotic and finite-time regimes. Algorithmically, LMC-based algorithms resemble the well-known gradient descent (GD) algorithm, where the GD recursion is perturbed by an additive Gaussian noise whose variance has a particular form. Fractional Langevin Monte Carlo (FLMC) is a recently proposed extension of LMC, where the Gaussian noise is replaced by a heavy-tailed α-stable noise. As opposed to its Gaussian counterpart, these heavy-tailed perturbations can incur large jumps and it has been empirically demonstrated that the choice of α-stable noise can provide several advantages in modern machine learning problems, both in optimization and sampling contexts. However, as opposed to LMC, only asymptotic convergence properties of FLMC have been yet established. In this study, we analyze the non-asymptotic behavior of FLMC for non-convex optimization and prove finite-time bounds for its expected suboptimality. Our results show that the weak-error of FLMC increases faster than LMC, which suggests using smaller step-sizes in FLMC. We finally extend our results to the case where the exact gradients are replaced by stochastic gradients and show that similar results hold in this setting as well.

math.OC↗

arXiv2018

Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization

Recent studies have illustrated that stochastic gradient Markov Chain Monte Carlo techniques have a strong potential in non-convex optimization, where local and global convergence guarantees can be shown under certain conditions. By building up on this recent theory, in this study, we develop an asynchronous-parallel stochastic L-BFGS algorithm for non-convex optimization. The proposed algorithm is suitable for both distributed and shared-memory settings. We provide formal theoretical analysis and show that the proposed method achieves an ergodic convergence rate of ${\cal O}(1/\sqrt{N})$ ($N$ being the total number of iterations) and it can achieve a linear speedup under certain conditions. We perform several experiments on both synthetic and real datasets. The results support our theory and show that the proposed algorithm provides a significant speedup over the recently proposed synchronous distributed L-BFGS algorithm.

stat.ML↗