Agricultural systems using unmanned aerial vehicles (UAVs) for communication face significant challenges in channel modeling and resource management, particularly in dynamic environments. Traditional frameworks overlook factors such as terrain variability, vegetation growth, and atmospheric conditions, leading to unreliable signal propagation and inefficient network performance. Moreover, UAV operations are constrained by limited energy, and conventional optimization methods fail to address the adaptive allocation of resources in heterogeneous networks (HetNets). This paper proposes a novel framework for UAV channel modeling in agriculture communication systems, applying the Internet of UAV Things (IoUT) and collaborative cloud computing to improve communication reliability and efficiency. The framework dynamically models signal propagation by using machine learning-based predictive algorithms, incorporating terrain features, vegetation density, and weather conditions. A genetic algorithm-long short-term memory network (GA-LSTM) optimization technique further enhances UAV operations, balancing coverage, energy efficiency, and system reliability for smarter and sustainable agricultural networks. The mathematical derivations are performed for channel modeling, UAV mobility, coverage, and IoUT-based cloud computing. Next, the virtual scenario is designed to enhance the accuracy of IoUT-based agriculture communication.

The development of beyond 5G (B5G) future wireless communication networks (FWCN) needs novel solutions to support high-speed, reliable, and low-latency communication. Unmanned aerial vehicles (UAVs) and reconfigurable intelligent surfaces (RISs) are promising techniques that can enhance wireless connectivity in urban environments where tall buildings block line-of-sight (LoS) links. However, existing UAV-assisted communication strategies do not fully address key challenges like mobility management, handover failures (HOFs), and path disorders in dense urban environments. This paper introduces a deep deterministic policy gradient (DDPG)-based UAV-RIS framework to overcome these limitations. The proposed framework jointly optimizes UAV trajectories and RIS phase shifts to improve throughput, energy efficiency (EE), and LoS probability while reducing outage probability (OP) and HOF. A modified K-means clustering algorithm is used to efficiently partition the ground users (GUs) considering the newly added GUs as well. The DDPG algorithm, based on reinforcement learning (RL), adapts UAV positioning and RIS configurations in a continuous action space. Simulation results show that the proposed approach significantly reduces HOF and OP, increases EE, enhances network throughput, and improves LoS probability compared to UAV-only, RIS-only, and without UAV-RIS deployments. Additionally, by dynamically adjusting UAV locations and RIS phase shifts based on GU mobility patterns, the framework further enhances connectivity and reliability. The findings highlight its potential to transform urban wireless communication by mitigating LoS blockages and ensuring uninterrupted connectivity in dense environments.

Terahertz (THz) access provides multi-GHz bandwidth for sixth-generation (6G) services, but its short-range propagation, molecular absorption, blockage, and narrow-beam misalignment make end-to-end (E2E) delay-energy guarantees difficult when computation tasks are offloaded to an edge computing node (ECN). When THz access is combined with non-orthogonal multiple access (NOMA), feasible successive interference cancellation (SIC) ordering must also be maintained, further coupling radio decisions with queueing and computation constraints. A reconfigurable intelligent surface (RIS) mounted on an unmanned aerial vehicle (UAV) create a controllable reflected path to mitigate blockage, yet practical deployment introduces b-bit phase quantization, UAV kinematics, and battery limitations that invalidate many idealized control assumptions. This paper proposes a constraint-aware E2E resource allocation framework for RIS-UAV-assisted THz NOMA-MEC networks. We formulate a single optimization problem that decides users’ transmit powers, SIC order, b-bit RIS phase shifts, UAV 3D waypoints, task offloading ratios, and per-user edge CPU allocations, subject to spectral masks, power limits, queue stability, CPU budgets, UAV kinematics/battery evolution, and RIS quantization constraints. To handle the high-dimensional coupled state, we represent the system as a heterogeneous graph (users, RIS-UAV, and ECN) and learn a graph neural network (GNN) policy. A differentiable feasibility projection enforces hard constraints, while a weighted time-energy objective (uplink transmission, edge execution, downlink return, and UAV propulsion) is augmented with a CVaR term to control tail latency. Simulations show reduced latency, lower energy per bit and energy-delay product, and improved spectral efficiency and outage performance compared with DRL/MARL and greedy baselines, with gains increasing for larger RIS apertures and finer phase resolution.

Unmanned aerial vehicles (UAVs) are increasingly deployed in ultra-wideband (UWB) environments to support applications that demand high data rates and reliable connectivity. However, effective communication between UAVs and ground terminals is challenged by six-dimensional (6D) posture-induced signal variation, non-stationary channel behavior, and dynamic resource constraints. Existing models are limited in addressing 6D posture-aware fading, frequency non-stationarity, and spatiotemporal variability in multipath propagation, which are critical in UAV-to-ground (U2G) communication in UWB environments. This study introduces a 6D UAV posture based non-stationary U2G channel model that incorporates UWB signal features, 6D UAV posture dynamics, and intelligent reflecting surface (IRS) beam control. A graph neural network (GNN) is developed to learn spatiotemporal correlations among UAV 6D movement, IRS states, and frequency-selective channel behavior. The model is initialized with ray-tracing (RT) data and supports resource allocation (RA) by adjusting UAV transmit power and IRS reflection coefficients. Performance is evaluated using key statistical metrics, including space–time–frequency correlation functions (STF-CFs), power delay profiles (PDP), root-mean-square delay spread (RMS-DS), and Doppler spectral density (DPSD). Results show that the proposed framework effectively captures 6D posture-aware fading and frequency non-stationarity across wide bandwidths, achieving an 11.6% reduction in path-loss RMSE, 8.2% improvement in RMS-DS fidelity, and 23.4% increase in sum-rate compared with conventional baselines.

Air-to-ground (A2G) links are increasingly usedfor integrated sensing and communication (ISAC) in consumerdevices such as smartphones, wearables, and immersive devices.Existing A2G models are quasi-stationary, which limited tocapture spatial-temporal-frequency (STF) statistics due to unmannedaerial vehicle (UAV) mobility, blockages, dense multipath,and vehicular communications scenarios. Furthermore,current geometry-based and empirical A2G models neither capturethe coupled evolution of large-scale and small-scale statisticsover time-frequency nor generalize well when measurement dataare sparse. To address these limitations, this work proposes anon-stationary A2G-ISAC channel model for consumer devicesusing generative adversarial networks (GANs) with bacterialforaging optimization (BFO). The proposed model representscommunication and sensing echoes within a time-frequency channelimpulse response and learns their statistics from ray-tracing(RT) and measurement-derived datasets. The GAN learns highdimensional STF statistics from the RT and measured data tosynthesize realistic channel that preserve non-stationary fading,delay and Doppler characteristics. The BFO is then used torefine key parameters, such as path loss, Rician K-factors, rootmean-square delay spread (RMS-DS), power delay profiles (PDP),and Doppler spreads by optimizing a multi-objective cost thatcombines channel fitting error (closely match the GAN-generatedsample) with ISAC performance metrics. Simulation results showthat the GAN-BFO framework yields lower RMS-DS error inPDP, and Doppler power spectral density (DPSD) compared withbenchmark geometry-based and wide-sense stationary models.These findings indicate that the proposed non-stationary A2Gchannel model provides a reliable ISAC waveform and a practicalfoundation for consumer devices, and is applicable to UAV-assistedmobility and vehicular communication scenarios.