Generative assimilation and prediction for weather and climate

Machine learning models have shown great success in predicting weather up to two weeks ahead, outperforming process-based benchmarks. However, existing approaches mostly focus on the prediction task, and do not incorporate the necessary data assimilation. Moreover, these models suffer from error accumulation in long roll-outs, limiting their applicability to seasonal predictions or climate projections. Here, we introduce Generative Assimilation and Prediction (GAP), a unified deep generative framework for assimilation and prediction of both weather and climate. By learning to quantify the probabilistic distribution of atmospheric states under observational, predictive, and external forcing constraints, GAP excels in a broad range of weather-climate related tasks, including data assimilation, seamless prediction, and climate simulation. In particular, GAP is competitive with state-of-the-art ensemble assimilation, probabilistic weather forecast and seasonal prediction, yields stable millennial simulations, and reproduces climate variability from daily to decadal time scales.

Transforming Time-Varying to Static Channels: The Power of Fluid Antenna Mobility

This paper addresses the mobility problem with the assistance of fluid antenna (FA) on the user equipment (UE) side. We propose a matrix pencil-based moving port (MPMP) prediction method, which may transform the time-varying channel to a static channel by timely sliding the liquid. Different from the existing channel prediction method, we design a moving port selection method, which is the first attempt to transform the channel prediction to the port prediction by exploiting the movability of FA. Theoretical analysis shows that for the line-ofsight (LoS) channel, the prediction error of our proposed MPMP method may converge to zero, as the number of BS antennas and the port density of the FA are large enough. For a multi-path channel, we also derive the upper and lower bounds of the prediction error when the number of paths is large enough. When the UEs move at a speed of 60 or 120 km/h, simulation results show that, with the assistance of FA, our proposed MPMP method performs better than the existing channel prediction method.

Eigenvector prediction-based precoding for massive MIMO with mobility

Eigenvector decomposition (EVD) is an inevitable operation to obtain the precoders in practical massive multiple-input multiple-output (MIMO) systems. Due to the large antenna size and at finite computation resources at the base station (BS), the overwhelming computation complexity of EVD is one of the key limiting factors of the system performance. To address this problem, we propose an eigenvector prediction (EGVP) method by interpolating the precoding matrix with predicted eigenvectors. The basic idea is to exploit a few historical precoders to interpolate the rest of them without EVD of the channel state information (CSI). We transform the nonlinear EVD into a linear prediction problem and prove that the prediction of the eigenvectors can be achieved with a complex exponential model. Furthermore, a channel prediction method called fast matrix pencil prediction (FMPP) is proposed to cope with the CSI delay when applying the EGVP method in mobility environments. The asymptotic analysis demonstrates how many samples are needed to achieve asymptotically error-free eigenvector predictions and channel predictions. Finally, the simulation results demonstrate the spectral efficiency improvement of our scheme over the benchmarks and the robustness to different mobility scenarios.

A manifold learning-based CSI feedback framework for FDD massive MIMO

Massive multi-input multi-output (MIMO) in Frequency Division Duplex (FDD) mode suffers from heavy feedback overhead for Channel State Information (CSI). In this paper, a novel manifold learning-based CSI feedback framework (MLCF) is proposed to reduce the feedback and improve the spectral efficiency of FDD massive MIMO. Manifold learning (ML) is an effective method for dimensionality reduction. However, most ML algorithms focus only on data compression, and lack the corresponding recovery methods. Moreover, the computational complexity is high when dealing with incremental data. To solve these problems, we propose a landmark selection algorithm to characterize the topological skeleton of the manifold where the CSI sample resides. Based on the learned skeleton, the local patch of the incremental CSI on the manifold can be easily determined by its nearest landmarks. This motivates us to propose a low-complexity compression and reconstruction scheme by keeping the local geometric relationships with landmarks unchanged. We theoretically prove the convergence of the proposed algorithm. Meanwhile, the upper bound on the error of approximating the CSI samples using landmarks is derived. Simulation results under an industrial channel model of 3GPP demonstrate that the proposed MLCF method outperforms existing algorithms based on compressed sensing and deep learning.

A Multi-Dimensional Matrix Pencil-Based Channel Prediction Method for Massive MIMO with Mobility

This paper addresses the mobility problem in massive multiple-input multiple-output systems, which leads to significant performance losses in the practical deployment of the fifth generation mobile communication networks. We propose a novel channel prediction method based on multi-dimensional matrix pencil (MDMP), which estimates the path parameters by exploiting the angular-frequency-domain and angular-time-domain structures of the wideband channel. The MDMP method also entails a novel path pairing scheme to pair the delay and Doppler, based on the super-resolution property of the angle estimation. Our method is able to deal with the realistic constraint of time-varying path delays introduced by user movements, which has not been considered so far in the literature. We prove theoretically that in the scenario with time-varying path delays, the prediction error converges to zero with the increasing number of the base station (BS) antennas, providing that only two arbitrary channel samples are known. We also derive a lower-bound of the number of the BS antennas to achieve a satisfactory performance. Simulation results under the industrial channel model of 3GPP demonstrate that our proposed MDMP method approaches the performance of the stationary scenario even when the users' velocity reaches 120 km/h and the latency of the channel state information is as large as 16 ms.

A Partial Reciprocity-based Channel Prediction Framework for FDD massive MIMO with High Mobility

Massive multiple-input multiple-output (MIMO) is believed to deliver unrepresented spectral efficiency gains for 5G and beyond. However, a practical challenge arises during its commercial deployment, which is known as the "curse of mobility". The performance of massive MIMO drops alarmingly when the velocity level of user increases. In this paper, we tackle the problem in frequency division duplex (FDD) massive MIMO with a novel Channel State Information (CSI) acquisition framework. A joint angle-delay-Doppler (JADD) wideband beamformer is proposed for channel training. Our idea consists in the exploitation of the partial channel reciprocity of FDD and the angle-delay-Doppler channel structure. More precisely, the base station (BS) estimates the angle-delay-Doppler information of the UL channel based on UL pilots using Matrix Pencil method. It then computes the wideband JADD beamformers according to the extracted parameters. Afterwards, the user estimates and feeds back some scalar coefficients for the BS to reconstruct the predicted DL channel. Asymptotic analysis shows that the CSI prediction error converges to zero when the number of BS antennas and the bandwidth increases. Numerical results with industrial channel model demonstrate that our framework can well adapt to high speed (350 km/h), large CSI delay (10 ms) and channel sample noise.

Towards Understanding and Harnessing the Effect of Image Transformation in Adversarial Detection

Deep neural networks (DNNs) are threatened by adversarial examples. Adversarial detection, which distinguishes adversarial images from benign images, is fundamental for robust DNN-based services. Image transformation is one of the most effective approaches to detect adversarial examples. During the last few years, a variety of image transformations have been studied and discussed to design reliable adversarial detectors. In this paper, we systematically synthesize the recent progress on adversarial detection via image transformations with a novel classification method. Then, we conduct extensive experiments to test the detection performance of image transformations against state-of-the-art adversarial attacks. Furthermore, we reveal that each individual transformation is not capable of detecting adversarial examples in a robust way, and propose a DNN-based approach referred to as AdvJudge, which combines scores of 9 image transformations. Without knowing which individual scores are misleading or not misleading, AdvJudge can make the right judgment, and achieve a significant improvement in detection accuracy. We claim that AdvJudge is a more effective adversarial detector than those based on an individual image transformation.