Multi-Beam Object-Localization for Millimeter-Wave ISAC-Aided Connected Autonomous Vehicles

Millimeter wave (mmWave) multiple-input multiple-output (MIMO) systems capable of integrated sensing and communication (ISAC) constitute a key technology for connected autonomous vehicles (CAVs). In this context, we propose a multi-beam object-localization (MBOL) model for enhancing the sensing beampattern (SBP) gain of adjacent objects in CAV scenarios. Given the ultra-narrow beams of mmWave MIMO systems, a single pencil beam is unsuitable for closely located objects, which tend to require multiple beams. Hence, we formulate the SBP gain maximization problem, considering also the constraints on the signal-to-interference and noise ratio (SINR) of the communication users (CUs), on the transmit power, and the constant modulus of the phase-shifters in the mmWave hybrid transceiver. To solve this non-convex problem, we propose a penalty-based triple alternating optimization algorithm to design the hybrid beamformer. Finally, simulation results are provided for demonstrating the efficacy of the proposed model.

Joint Hybrid Transceiver and Reflection Matrix Design for RIS-Aided mmWave MIMO Cognitive Radio Systems

In this work, a reconfigurable intelligent surface (RIS)-aided millimeter wave (mmWave) multiple-input multiple-output (MIMO) cognitive radio (CR) downlink operating in the underlay mode is investigated. The cognitive base station (CBS) communicates with multiple secondary users (SUs), each having multiple RF chains in the presence of a primary user (PU). We conceive a joint hybrid transmit precoder (TPC), receiver combiner (RC), and RIS reflection matrix (RM) design, which maximizes the sum spectral efficiency (SE) of the secondary system while maintaining the interference induced at the PU below a specified threshold. To this end, we formulate the sum-SE maximization problem considering the total transmit power (TP), the interference power (IP), and the non-convex unity modulus constraints of the RF TPC, RF RC, and RM. To solve this highly non-convex problem, we propose a two-stage hybrid transceiver design in conjunction with a novel block coordinate descent (BCD)-successive Riemannian conjugate gradient (SRCG) algorithm. We initially decompose the RF TPC, RC, and RM optimization problem into a series of sub-problems and subsequently design pairs of RF TPC and RC vectors, followed by successively optimizing the elements of the RM using the iterative BCD-SRCG algorithm. Furthermore, based on the effective baseband (BB) channel, the BB TPC and BB RC are designed using the proposed direct singular value decomposition (D-SVD) and projection based SVD (P-SVD) methods. Subsequently, the proportional water-filling solution is proposed for optimizing the power, which maximizes the weighted sum-SE of the system. Finally, simulation results are provided to compare our proposed schemes to several benchmarks and quantify the impact of other parameters on the sum-SE of the system.

Energy-Efficient Hybrid Beamforming for Integrated Sensing and Communication Enabled mmWave MIMO Systems

This paper conceives a hybrid beamforming design (HBF) that maximizes the energy efficiency (EE) of an integrated sensing and communication (ISAC)-enabled millimeter wave (mmWave) multiple-input multiple-output (MIMO) system. In the system under consideration, an ISAC base station (BS) with the hybrid MIMO architecture communicates with multiple users and simultaneously detects multiple targets. The proposed scheme seeks to maximize the EE of the system, considering the signal-to-interference and noise ratio (SINR) as the user's quality of service (QoS) and the sensing beampattern gain of the targets as constraints. To solve this non-convex problem, we initially adopt Dinkelbach's method to convert the fractional objective function to subtractive form and subsequently obtain the sub-optimal fully-digital transmit beamformer by leveraging the principle of semi-definite relaxation. Subsequently, we propose a penalty-based manifold optimization scheme in conjunction with an alternating minimization method to determine the baseband (BB) and analog beamformers based on the designed fully-digital transmit beamformer. Finally, simulation results are given to demonstrate the efficacy of our proposed algorithm with respect to the benchmarks.

Pareto Optimal Hybrid Beamforming for Short-Packet Millimeter-Wave Integrated Sensing and Communication

Pareto optimal solutions are conceived for radar beamforming error (RBE) and sum rate maximization in short-packet (SP) millimeter-wave (mmWave) integrated sensing and communication (ISAC). Our ultimate goal is to realize ultra-reliable low-latency communication (uRLLC) and real-time sensing capabilities for 6G applications. The ISAC base station (BS) transmits short packets in the downlink (DL) to serve multiple communication users (CUs) and detect multiple radar targets (RTs). We investigate the performance trade-off between the sensing and communication capabilities by optimizing both the radio frequency (RF) and the baseband (BB) transmit precoder (TPC), together with the block lengths. The optimization problem considers the minimum rate requirements of the CUs, the maximum tolerable radar beamforming error (RBE) for the RTs, the unit modulus (UM) elements of the RF TPC, and the finite transmit power as the constraints for SP transmission. The resultant problem is highly non-convex due to the intractable rate expression of the SP regime coupled with the non-convex rate and UM constraints. To solve this problem, we propose an innovative two-layer bisection search (TLBS) algorithm, wherein the RF and BB TPCs are optimized in the inner layer, followed by the block length in the outer layer. Furthermore, a pair of novel methods, namely a bisection search-based majorizer and minimizer (BMM) as well as exact penalty-based manifold optimization (EPMO) are harnessed for optimizing the RF TPC in the inner layer. Subsequently, the BB TPC and the block length are derived via second-order cone programming (SOCP) and mixed integer programming methods, respectively. Finally, our exhaustive simulation results reveal the effect of system parameters for various settings on the RBE-rate region of the SP mmWave ISAC system and demonstrate a significantly enhanced performance compared to the benchmarks.

Image-Based Soil Organic Carbon Remote Sensing from Satellite Images with Fourier Neural Operator and Structural Similarity

Soil organic carbon (SOC) sequestration is the transfer and storage of atmospheric carbon dioxide in soils, which plays an important role in climate change mitigation. SOC concentration can be improved by proper land use, thus it is beneficial if SOC can be estimated at a regional or global scale. As multispectral satellite data can provide SOC-related information such as vegetation and soil properties at a global scale, estimation of SOC through satellite data has been explored as an alternative to manual soil sampling. Although existing studies show promising results, they are mainly based on pixel-based approaches with traditional machine learning methods, and convolutional neural networks (CNNs) are uncommon. To study the use of CNNs on SOC remote sensing, here we propose the FNO-DenseNet based on the Fourier neural operator (FNO). By combining the advantages of the FNO and DenseNet, the FNO-DenseNet outperformed the FNO in our experiments with hundreds of times fewer parameters. The FNO-DenseNet also outperformed a pixel-based random forest by 18% in the mean absolute percentage error.

Encoding Seasonal Climate Predictions for Demand Forecasting with Modular Neural Network

Current time-series forecasting problems use short-term weather attributes as exogenous inputs. However, in specific time-series forecasting solutions (e.g., demand prediction in the supply chain), seasonal climate predictions are crucial to improve its resilience. Representing mid to long-term seasonal climate forecasts is challenging as seasonal climate predictions are uncertain, and encoding spatio-temporal relationship of climate forecasts with demand is complex. We propose a novel modeling framework that efficiently encodes seasonal climate predictions to provide robust and reliable time-series forecasting for supply chain functions. The encoding framework enables effective learning of latent representations -- be it uncertain seasonal climate prediction or other time-series data (e.g., buyer patterns) -- via a modular neural network architecture. Our extensive experiments indicate that learning such representations to model seasonal climate forecast results in an error reduction of approximately 13\% to 17\% across multiple real-world data sets compared to existing demand forecasting methods.