TinyNina: A Resource-Efficient Edge-AI Framework for Sustainable Air Quality Monitoring via Intra-Image Satellite Super-Resolution

• URL: http://arxiv.org/abs/2604.04445v1
• Date: Mon, 06 Apr 2026 05:43:21 GMT
• Title: TinyNina: A Resource-Efficient Edge-AI Framework for Sustainable Air Quality Monitoring via Intra-Image Satellite Super-Resolution
• Abstract summary: TinyNina is a resource-efficient Edge-AI framework for sustainable environmental monitoring.<n>It implements a novel intra-image learning paradigm that leverages the multi-spectral hierarchy of Sentinel-2 as internal training labels.<n>TinyNina achieves a state-of-the-art Mean Absolute Error (MAE) of 7.4 $$g/m$3$ against 3,276 matched satellite-ground station pairs.
• Score: 3.995685365847731
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Nitrogen dioxide (NO$_2$) is a primary atmospheric pollutant and a significant contributor to respiratory morbidity and urban climate-related challenges. While satellite platforms like Sentinel-2 provide global coverage, their native spatial resolution often limits the precision required, fine-grained NO$_2$ assessment. To address this, we propose TinyNina, a resource-efficient Edge-AI framework specifically engineered for sustainable environmental monitoring. TinyNina implements a novel intra-image learning paradigm that leverages the multi-spectral hierarchy of Sentinel-2 as internal training labels, effectively eliminating the dependency on costly and often unavailable external high-resolution reference datasets. The framework incorporates wavelength-specific attention gates and depthwise separable convolutions to preserve pollutant-sensitive spectral features while maintaining an ultra-lightweight footprint of only 51K parameters. Experimental results, validated against 3,276 matched satellite-ground station pairs, demonstrate that TinyNina achieves a state-of-the-art Mean Absolute Error (MAE) of 7.4 $μ$g/m$^3$. This performance represents a 95% reduction in computational overhead and 47$\times$ faster inference compared to high-capacity models such as EDSR and RCAN. By prioritizing task-specific utility and architectural efficiency, TinyNina provides a scalable, low-latency solution for real-time air quality monitoring in smart city infrastructures.

Related papers

• TileNet: Tile-Based CNN-SVM Architecture for Autonomous Unmanned Aerial Systems Inspection of Flat Roofs [6.316693022958222]
  This paper presents a real-time, Unmanned Aerial System (UAS)-based deep learning framework that autonomously detects defects using live imagery captured during dual-altitude aerial passes.<n>The framework integrates a tile-based architecture with a lightweight Convolution Neural Network-Support Vector Machine (CNN-SVM)<n>The final model-comprising five convolutional layers and four dense layers, achieved a mean test accuracy of $94.4%$ ($95%$ confidence interval $pm0.4%$ over three seeds) on a photo-level split.
  arXiv  Detail & Related papers  (2026-09-11T16:11:35Z)
• Predicting Spatiotemporal Mobile Sensing-Based PM2.5 Concentrations Using Low-Rank Adapted Spatially Attentive Graph Neural Network [1.7768447567837418]
  This work introduces a novel mobile-sensing dataset from Surat, Gujarat, India.<n>It comprises PM$*2.5$ concentrations, meteorological variables (temperature, humidity, wind speed, wind direction), and land-use features.<n>We propose a SA-GNN for fine-grained, short-term PM$*2.5$ forecasting and hotspot identification.
  arXiv  Detail & Related papers  (2026-09-04T03:50:32Z)
• ORBITALIF: An Efficient Spiking Federated Learning Framework for Onboard Cloud Removal [46.13568040085732]
  Low-earth-orbit (LEO) satellites enable high-resolution, large-scale Earth observation for applications such as disaster monitoring and environmental surveillance.<n>Conventional cloud-removal pipelines that download cloudy images to ground stations for processing suffer from limited contact windows, constrained satellite-to-ground bandwidth, and high latency.<n>We propose a novel satellite federated learning framework for cloud removal across constellations, named orbital attention leaky integrate-and-fire (OrbitALIF)
  arXiv  Detail & Related papers  (2026-08-25T05:11:19Z)
• LCMamNet: A Lightweight Cross-scale Mamba Network for Infrared Small Target Detection [53.811713750107934]
  We propose LCMamNet, a lightweight cross-scale Mamba network for infrared small target detection.<n>A compact hierarchical encoder with cross-shaped directional bottleneck residual blocks strengthens direction-sensitive target structures.<n>Experiments on IRSTD-1k, NUAA-SIRST, and NUDT-SIRST show that the proposed network achieves mIoU scores of 71.25%, 79.60%, and 95.58%, respectively.
  arXiv  Detail & Related papers  (2026-07-27T09:06:14Z)
• Air Quality Downscaling with Station-Guided Pseudo-Supervision [60.31045749983062]
  Super-resolving coarse atmospheric fields to local PM$_2.5$ variations is uniquely challenged by a mismatch in spatial support.<n>We present a station-guided framework for high-resolution PM$_2.5$ downscaling over Europe.
  arXiv  Detail & Related papers  (2026-07-06T16:32:25Z)
• PollutionNet: A Vision Transformer Framework for Climatological Assessment of NO$_2$ and SO$_2$ Using Satellite-Ground Data Fusion [4.364999214109123]
  PollutionNet is a Vision Transformer-based framework that integrates Sentinel-5P TROPOMI vertical column density (VCD) data with ground-level observations.<n>By leveraging self-attention mechanisms, PollutionNet captures complex dependencies that are often missed by CNN and RNN models.<n>PollutionNet reduces prediction errors by up to 14% compared to baseline models.
  arXiv  Detail & Related papers  (2026-03-31T15:39:26Z)
• Physics-Guided Inductive Spatiotemporal Kriging for PM2.5 with Satellite Gradient Constraints [15.082346657646902]
  High-resolution mapping of fine particulate matter (PM2.5) is a cornerstone of sustainable urbanism but remains critically hindered by the spatial sparsity of ground monitoring networks.<n>This study proposes the Spatio-Guided Inference Network (SPIN), a novel framework designed for inductivetemporal kriging.
  arXiv  Detail & Related papers  (2025-11-20T03:18:41Z)
• Scale-DiT: Ultra-High-Resolution Image Generation with Hierarchical Local Attention [50.391914489898774]
  Scale-DiT is a new diffusion framework that introduces hierarchical local attention with low-resolution global guidance.<n>A lightweight LoRA adaptation bridges global and local pathways during denoising, ensuring consistency across structure and detail.<n>Experiments demonstrate that Scale-DiT achieves more than $2times$ faster inference and lower memory usage.
  arXiv  Detail & Related papers  (2025-10-18T03:15:26Z)
• Data Augmentation and Resolution Enhancement using GANs and Diffusion Models for Tree Segmentation [49.13393683126712]
  Urban forests play a key role in enhancing environmental quality and supporting biodiversity in cities.<n> accurately detecting trees is challenging due to complex landscapes and the variability in image resolution caused by different satellite sensors or UAV flight altitudes.<n>We propose a novel pipeline that integrates domain adaptation with GANs and Diffusion models to enhance the quality of low-resolution aerial images.
  arXiv  Detail & Related papers  (2025-05-21T03:57:10Z)
• ACMamba: Fast Unsupervised Anomaly Detection via An Asymmetrical Consensus State Space Model [51.83639270669481]
  Unsupervised anomaly detection in hyperspectral images (HSI) aims to detect unknown targets from backgrounds.<n>HSI studies are hindered by steep computational costs due to the high-dimensional property of HSI and dense sampling-based training paradigm.<n>We propose an Asymmetrical Consensus State Space Model (ACMamba) to significantly reduce computational costs without compromising accuracy.
  arXiv  Detail & Related papers  (2025-04-16T05:33:42Z)
• SU-YOLO: Spiking Neural Network for Efficient Underwater Object Detection [15.935285733525962]
  Spiking Underwater YOLO (SU-YOLO) is a Spiking Neural Network (SNN) model for underwater object detection.<n>SU-YOLO incorporates a novel spike-based underwater image denoising method based solely on integer addition.<n>Results demonstrate that SU-YOLO achieves mAP of 78.8% with 6.97M parameters and an energy consumption of 2.98 mJ.
  arXiv  Detail & Related papers  (2025-03-31T17:59:52Z)
• FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression [6.768163204818034]
  We present an OEC-native and task-agnostic feature compression method that preserves prediction performance.<n>FOOL partitions high-resolution satellite imagery to maximize throughput.<n>We evaluate transfer cost reduction by including the peculiarity of intermittently available network connections in low earth orbit.
  arXiv  Detail & Related papers  (2024-03-25T12:14:48Z)
• Reconfigurable Intelligent Surface (RIS)-Assisted Entanglement Distribution in FSO Quantum Networks [62.87033427172205]
  Quantum networks (QNs) relying on free-space optical (FSO) quantum channels can support quantum applications in environments where establishing an optical fiber infrastructure is challenging and costly. A reconfigurable intelligent surface (RIS)-assisted FSO-based QN is proposed as a cost-efficient framework providing a virtual line-of-sight between users for entanglement distribution.
  arXiv  Detail & Related papers  (2024-01-19T17:16:40Z)
• Deep Learning for Real Time Satellite Pose Estimation on Low Power Edge TPU [58.720142291102135]
  In this paper we propose a pose estimation software exploiting neural network architectures. We show how low power machine learning accelerators could enable Artificial Intelligence exploitation in space.
  arXiv  Detail & Related papers  (2022-04-07T08:53:18Z)
• Optimised Domain-engineered Crystals for Pure Telecom Photon Sources [101.18253437732933]
  We present a telecom-wavelength parametric down-conversion photon source that operates on the achievable limit of domain engineering. We generate photons from independent sources which achieve two-photon interference visibilities of up to $98.6pm1.1%$ without narrow-band filtering.
  arXiv  Detail & Related papers  (2021-01-20T19:00:04Z)

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.