Physics-Constrained Denoising Autoencoders for Data-Scarce Wildfire UAV Sensing

• URL: http://arxiv.org/abs/2601.11794v1
• Date: Fri, 16 Jan 2026 21:40:39 GMT
• Title: Physics-Constrained Denoising Autoencoders for Data-Scarce Wildfire UAV Sensing
• Abstract summary: Wildfire monitoring requires high-resolution atmospheric measurements.<n>Traditional deep learning denoising approaches demand large datasets impractical to obtain from limited UAV flight campaigns.<n>We present PC$2$DAE, a physics-informed denoising autoencoder that addresses data scarcity by embedding physical constraints directly into the network architecture.
• Score: 0.8994003055762606
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Wildfire monitoring requires high-resolution atmospheric measurements, yet low-cost sensors on Unmanned Aerial Vehicles (UAVs) exhibit baseline drift, cross-sensitivity, and response lag that corrupt concentration estimates. Traditional deep learning denoising approaches demand large datasets impractical to obtain from limited UAV flight campaigns. We present PC$^2$DAE, a physics-informed denoising autoencoder that addresses data scarcity by embedding physical constraints directly into the network architecture. Non-negative concentration estimates are enforced via softplus activations and physically plausible temporal smoothing, ensuring outputs are physically admissible by construction rather than relying on loss function penalties. The architecture employs hierarchical decoder heads for Black Carbon, Gas, and CO$_2$ sensor families, with two variants: PC$^2$DAE-Lean (21k parameters) for edge deployment and PC$^2$DAE-Wide (204k parameters) for offline processing. We evaluate on 7,894 synchronized 1 Hz samples collected from UAV flights during prescribed burns in Saskatchewan, Canada (approximately 2.2 hours of flight data), two orders of magnitude below typical deep learning requirements. PC$^2$DAE-Lean achieves 67.3\% smoothness improvement and 90.7\% high-frequency noise reduction with zero physics violations. Five baselines (LSTM-AE, U-Net, Transformer, CBDAE, DeSpaWN) produce 15--23\% negative outputs. The lean variant outperforms wide (+5.6\% smoothness), suggesting reduced capacity with strong inductive bias prevents overfitting in data-scarce regimes. Training completes in under 65 seconds on consumer hardware.

Related papers

• Boosting Neural Video Codec via Scale-Driven Online Flow Refinement [59.68390983151205]
  We propose a Training-Free Scale-Driven Online Flow Refinement (SOFR) method.<n>It fuses motion information from coarse and fine scales according to warping accuracy, effectively rectifying motion estimation errors.<n>It brings an average of 2.84% and 4.05% savings in terms of PSNR and MS-SSIM, respectively.
  arXiv  Detail & Related papers  (2026-06-22T08:36:23Z)
• HEPTv2: End-to-End Efficient Point Transformer for Charged Particle Reconstruction [9.951462226612865]
  HEPTv2 is an end-to-end point-transformer architecture that reconstructs tracks from detector hits in one trainable pipeline.<n>On TrackML, HEPTv2 achieves 98.6% double-majority tracking efficiency at a 0.8% fake rate.<n>These results show end-to-end transformers can deliver the accuracy and efficiency required for real-time particle reconstruction at the HL-LHC.
  arXiv  Detail & Related papers  (2026-06-18T16:18:10Z)
• Thermal Anomaly Detection using Physics Aware Neuromorphic Networks: Comparison between Raw and L1C Sentinel-2 Data [5.904895437536006]
  Recent Earth Observation approaches have shown that thermal anomaly detection can be performed directly on decompressed Level-0 (L0) sensor data.<n>Direct exploitation of raw data remains challenging due to domain shift, sensor drift, radiometric inconsistencies, and the scarcity of labelled training samples.<n>This work proposes a Physics-Aware Neuromorphic Network framework for onboard thermal anomaly detection.
  arXiv  Detail & Related papers  (2026-04-10T02:15:02Z)
• YawDD+: Frame-level Annotations for Accurate Yawn Prediction [2.578347047861952]
  Driver fatigue is a leading cause of road accidents, with 24% of crashes involving drowsy drivers.<n>We develop a semi-automated labeling pipeline with human-in-the-loop verification, which we apply to YawDD.<n> YawDD+ improves frame accuracy by up to 6% and mAP by 5% over video-level supervision.
  arXiv  Detail & Related papers  (2025-12-12T10:33:17Z)
• MeanFlow Transformers with Representation Autoencoders [71.45823902973349]
  MeanFlow (MF) is a diffusion-motivated generative model that enables efficient few-step generation by learning long jumps directly from noise to data.<n>We develop an efficient training and sampling scheme for MF in the latent space of a Representation Autoencoder (RAE)<n>We achieve a 1-step FID of 2.03, outperforming vanilla MF's 3.43, while reducing sampling GFLOPS by 38% and total training cost by 83% on ImageNet 256.
  arXiv  Detail & Related papers  (2025-11-17T06:17:08Z)
• Physics-informed GNN for medium-high voltage AC power flow with edge-aware attention and line search correction operator [7.927606793404479]
  Physics-informed graph neural networks (PIGNNs) have emerged as fast AC power-flow solvers.<n>PIGNN-Attn-LS achieves a test RMSE of 0.00033 p.u. in voltage and 0.08$circ$ in angle, outperforming the PIGNN-MLP baseline by 99.5% and 87.1%, respectively.
  arXiv  Detail & Related papers  (2025-09-26T15:09:26Z)
• From large-eddy simulations to deep learning: A U-net model for fast urban canopy flow predictions [0.0]
  This study presents a deep neural network (DNN) approach for fast and accurate predictions of urban wind flow fields.<n>We employ a U-Net architecture trained on LES data including 252 synthetic urban configurations at seven wind directions.<n>Model evaluation on 50 test cases demonstrates high accuracy with an overall mean relative error of 9.3% for velocity magnitude and 5.2% for turbulence intensity.
  arXiv  Detail & Related papers  (2025-07-09T04:25:13Z)
• 4,500 Seconds: Small Data Training Approaches for Deep UAV Audio Classification [2.3354223046061016]
  This study investigates deep learning approaches to UAV classification focusing on the key issue of data scarcity.<n>We train the models using a total of 4,500 seconds of audio samples, evenly distributed across a 9-class dataset.<n>We compare the use of convolutional neural networks (CNNs) and attention-based transformers.
  arXiv  Detail & Related papers  (2025-05-21T22:34:07Z)
• Real-Time AIoT for AAV Antenna Interference Detection via Edge-Cloud Collaboration [6.7233672503362545]
  In fifth-generation (5G) era, eliminating communication interference sources is crucial for maintaining network performance.<n>We propose a computer vision-based AI of Things system to detect antenna interference sources for UAVs.<n>System achieves state-of-the-art (SOTA) performance with a mean average precision (mAP) of 42.1% on our custom antenna interference source dataset.
  arXiv  Detail & Related papers  (2024-12-04T06:20:36Z)
• Data-Free Dynamic Compression of CNNs for Tractable Efficiency [46.498278084317704]
  structured pruning approaches have shown promise in lowering floating-point operations without substantial drops in accuracy.<n>We propose HASTE (Hashing for Tractable Efficiency), a data-free, plug-and-play convolution module that instantly reduces a network's test-time inference cost without training or fine-tuning.<n>We demonstrate our approach on the popular vision benchmarks CIFAR-10 and ImageNet, where we achieve a 46.72% reduction in FLOPs with only a 1.25% loss in accuracy.
  arXiv  Detail & Related papers  (2023-09-29T13:09:40Z)
• Efficient Decoder-free Object Detection with Transformers [75.00499377197475]
  Vision transformers (ViTs) are changing the landscape of object detection approaches. We propose a decoder-free fully transformer-based (DFFT) object detector. DFFT_SMALL achieves high efficiency in both training and inference stages.
  arXiv  Detail & Related papers  (2022-06-14T13:22:19Z)
• FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation [81.76975488010213]
  Dense optical flow estimation plays a key role in many robotic vision tasks. Current networks often occupy large number of parameters and require heavy computation costs. Our proposed FastFlowNet works in the well-known coarse-to-fine manner with following innovations.
  arXiv  Detail & Related papers  (2021-03-08T03:09:37Z)
• Neural Network Virtual Sensors for Fuel Injection Quantities with Provable Performance Specifications [71.1911136637719]
  We show how provable guarantees can be naturally applied to other real world settings. We show how specific intervals of fuel injection quantities can be targeted to maximize robustness for certain ranges.
  arXiv  Detail & Related papers  (2020-06-30T23:33:17Z)
• Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training [70.2914594796002]
  We propose Dynamic R-CNN to adjust the label assignment criteria and the shape of regression loss function. Our method improves upon ResNet-50-FPN baseline with 1.9% AP and 5.5% AP$_90$ on the MS dataset with no extra overhead.
  arXiv  Detail & Related papers  (2020-04-13T15:20:25Z)

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.