Multi-Modal Conditioned High-Resolution Transformer for Urban Electromagnetic Field Map Prediction Download PDF

• URL: http://arxiv.org/abs/2606.27671v1
• Date: Fri, 26 Jun 2026 03:06:23 GMT
• Title: Multi-Modal Conditioned High-Resolution Transformer for Urban Electromagnetic Field Map Prediction Download PDF
• Abstract summary: Predicting electromagnetic field (EMF) strength in urban environments is essential for cellular network planning.<n>We propose a multi-conditioned dense prediction framework that generates 500 500 EMF maps from building layout images and antenna configurations.<n>Our best model achieves a test MAE of 0.0461, a 25.2% improvement over a plain UNet baseline and 31.8% over an HRFormer-only baseline.
• Score: 3.3172899945646965
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Predicting electromagnetic field (EMF) strength in urban environments is essential for cellular network planning but computationally expensive with physics-based simulators. We propose a multi-conditioned dense prediction framework that generates 500 500 EMF maps from building layout images and antenna configurations. Our architecture uses a High-Resolution Transformer (HRFormer) backbone with two complementary conditioning mechanisms: Feature-wise Linear Modulation (FiLM) injects scalar antenna parameters into all backbone stages, while cross-attention fuses 1-D radiation pattern tokens with spatial features at the deepest stage. We further introduce transmitter-relative spatial channels encoding distance, proximity, and bearing from the antenna, enabling coordinate-consistent test-time augmentation (TTA) that reduces test MAE by 6.3%. To address the prediction difficulty imbalance across EMF maps, we design a composite loss combining masked L1, multi-scale structural similarity (MS-SSIM), and a focal L1 term that upweights high-signal pixels, outperforming individual loss components in all metrics. Our best model achieves a test MAE of 0.0461, a 25.2% improvement over a plain UNet baseline and 31.8% over an HRFormer-only baseline.Do-

Related papers

• Low-Altitude Fluid Antenna Network with Multi-Agent Reinforcement Learning [49.09908852315575]
  We study the fast and high-performance reconfiguration for low-altitude FA networks with multi-agent reinforcement learning (MARL)<n>Our case study shows that joint FA positions and beamforming optimization can enhance the system sum-rate by 118.5%, compared to the fixed position baseline.
  arXiv  Detail & Related papers  (2026-08-28T04:27:44Z)
• HybridSim: A Physics-Learning Hybrid Digital Twin for mmWave Human Sensing [16.25180983132509]
  HybridSim is a physics-learning hybrid simulator that synthesizes mmWave radar signals from dynamic human meshes under a fixed indoor room configuration.<n>We show improved agreement with a physically based reference and consistent gains on downstream radar-based human sensing tasks when using HybridSim for site-specific data augmentation.
  arXiv  Detail & Related papers  (2026-07-17T10:20:31Z)
• Machine Learning-Based Reconstruction for Resistive Silicon Sensors [53.365453214937496]
  We study machine-learning-based reconstruction and compression for resistive silicon sensors.<n>We use full-waveform information from correlated pads to regularise the reconstruction and extract spatial information.<n>We first introduce recurrent neural network models based on LSTM layers, which provide a proof-of-concept implementation for full-waveform reconstruction.
  arXiv  Detail & Related papers  (2026-07-13T14:03:26Z)
• Phase-Preserving Trimodal Transformer for Tropical Forest Biomass Estimation Using Optical and PolInSAR Data [0.3499870393443268]
  Trimodal Coherent Co-attention Transformer (TCCT) is a physics-informed deep learning architecture.<n>TCCT fuses optical surface reflectance (Landsat-5) with complex-valued Polarimetric SAR Interferometry (PolInSAR) data from both P and L bands.<n>When converted to Above-Ground Biomass (AGB), the fine-tuned TCCT map yielded a Relative RMSE of 4.51% in dense forest areas above 50 Mg/ha.
  arXiv  Detail & Related papers  (2026-07-04T02:32:51Z)
• TriSweep: A Four-Drone Swarm Framework for Electromagnetic Side-Channel Analysis [0.0]
  TriSweep is a simulation framework that designs and evaluates a four-drone swarm architecture for autonomous standoff EM-SCA.<n>Three spatially specialized collector drones feed a stationary Accumulator drone that performs coherent combining.<n>No physical hardware has been fabricated; prototype construction is the planned next step.
  arXiv  Detail & Related papers  (2026-05-21T16:47:44Z)
• OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation [100.36917520403227]
  We present a unified text-conditioned diffusion framework that generates LiDAR scans in a shared range-image representation across eight representative domains.<n>In the absence of a public consolidated benchmark, we construct an 8-domain dataset by combining real-world scans with physically based weather simulation and systematic beam reduction.
  arXiv  Detail & Related papers  (2026-05-13T17:42:20Z)
• Physics-Based Flow Matching for Full-Field Prediction of Silicon Photonic Devices [0.02455468619225742]
  We present PICFlow, a generative neural surrogate that predicts electromagnetic field distributions for photonic devices.<n>Our approach combines three key ideas: (i) conditional flow matching as the generative framework; (ii) a real-valued U-Net operating on split real and imaginary field channels; and (iii) physics-constrained training through a Helmholtz residual loss enforcing runtimenabla2 E_z + k2 varepsilon E_z = 0$.
  arXiv  Detail & Related papers  (2026-05-07T20:40:24Z)
• ReVeal-MT: A Physics-Informed Neural Network for Multi-Transmitter Radio Environment Mapping [9.43653276377036]
  We propose emphReVeal-MT, a novel PINN which integrates the multi-source PDE residual into a neural network loss function.<n>ReVeal-MT is validated using real-world measurements from the ARA wireless living lab across rural and suburban environments.<n>Results show that ReVeal-MT achieves substantial accuracy gains in multi-transmitter scenarios.
  arXiv  Detail & Related papers  (2025-11-22T23:33:06Z)
• A Fluid Antenna Enabled Physical Layer Key Generation for Next-G Wireless Networks [83.86388221738225]
  Physical layer key generation (PLKG) enables legitimate users to obtain secret keys from wireless channel without security infrastructures.<n>In harsh propagation environments, the key generation rate (KGR) is significantly deteriorated.<n>We propose a novel fluid antenna (FA) enabled PLKG system to address this challenge.
  arXiv  Detail & Related papers  (2025-08-16T18:39:19Z)
• On the Limitations of Ray-Tracing for Learning-Based RF Tasks in Urban Environments [4.097291451674696]
  We study the realism of Sionna v ray-tracing for outdoor cellular links in central Rome.<n>We vary the main simulation parameters, including path depth, diffuse/specular/refraction flags, carrier frequency, as well as antenna's properties.
  arXiv  Detail & Related papers  (2025-07-25T19:58:44Z)
• Deep Learning Optimization of Two-State Pinching Antennas Systems [48.70043547158868]
  Pinching antennas (PAs) can dynamically control electromagnetic wave propagation through binary activation states.<n>In this work, we investigate the problem of optimally selecting a subset of fixed-position PAs to activate in a waveguide, when the aim is to maximize the communication rate at a user terminal.
  arXiv  Detail & Related papers  (2025-07-08T17:55:54Z)
• Fairness-Driven Optimization of RIS-Augmented 5G Networks for Seamless 3D UAV Connectivity Using DRL Algorithms [8.296140341710462]
  We study the problem of joint active and passive beamforming for reconfigurable intelligent surface (RIS)-assisted massive multiple-input multiple-output systems. We propose two novel algorithms to address this problem.
  arXiv  Detail & Related papers  (2023-11-14T06:43:36Z)
• Federated Learning for Energy-limited Wireless Networks: A Partial Model Aggregation Approach [79.59560136273917]
  limited communication resources, bandwidth and energy, and data heterogeneity across devices are main bottlenecks for federated learning (FL) We first devise a novel FL framework with partial model aggregation (PMA) The proposed PMA-FL improves 2.72% and 11.6% accuracy on two typical heterogeneous datasets.
  arXiv  Detail & Related papers  (2022-04-20T19:09:52Z)
• Collaborative Intelligent Reflecting Surface Networks with Multi-Agent Reinforcement Learning [63.83425382922157]
  Intelligent reflecting surface (IRS) is envisioned to be widely applied in future wireless networks. In this paper, we investigate a multi-user communication system assisted by cooperative IRS devices with the capability of energy harvesting.
  arXiv  Detail & Related papers  (2022-03-26T20:37:14Z)
• Integrating LEO Satellites and Multi-UAV Reinforcement Learning for Hybrid FSO/RF Non-Terrestrial Networks [55.776497048509185]
  A mega-constellation of low-altitude earth orbit satellites (SATs) and burgeoning unmanned aerial vehicles (UAVs) are promising enablers for high-speed and long-distance communications in beyond fifth-generation (5G) systems. We investigate the problem of forwarding packets between two faraway ground terminals through SAT and UAV relays using either millimeter-wave (mmWave) radio-frequency (RF) or free-space optical (FSO) link.
  arXiv  Detail & Related papers  (2020-10-20T09:07:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.