Atmos-Bench: 3D Atmospheric Structures for Climate Insight

• URL: http://arxiv.org/abs/2507.11085v1
• Date: Tue, 15 Jul 2025 08:27:29 GMT
• Title: Atmos-Bench: 3D Atmospheric Structures for Climate Insight
• Abstract summary: We present Atmos-Bench: the first 3D atmospheric benchmark, along with a novel FourCastX: Frequency-enhanced Spatio-Temporal Mixture-of-Experts Network that generates 921,600 image slices from 3D scattering volumes simulated at 532 nm and 355 nm by coupling WRF with an enhanced COSP simulator over 384 land-ocean time steps, yielding high-quality voxel-wise references; (b) embeds ATB-BC physical constraints into the model architecture, promoting energy consistency during restoration; (c) achieves consistent improvements on the Atmos-Bench dataset across both 355 nm and 532 nm bands,
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Atmospheric structure, represented by backscatter coefficients (BC) recovered from satellite LiDAR attenuated backscatter (ATB), provides a volumetric view of clouds, aerosols, and molecules, playing a critical role in human activities, climate understanding, and extreme weather forecasting. Existing methods often rely on auxiliary inputs and simplified physics-based approximations, and lack a standardized 3D benchmark for fair evaluation. However, such approaches may introduce additional uncertainties and insufficiently capture realistic radiative transfer and atmospheric scattering-absorption effects. To bridge these gaps, we present Atmos-Bench: the first 3D atmospheric benchmark, along with a novel FourCastX: Frequency-enhanced Spatio-Temporal Mixture-of-Experts Network that (a) generates 921,600 image slices from 3D scattering volumes simulated at 532 nm and 355 nm by coupling WRF with an enhanced COSP simulator over 384 land-ocean time steps, yielding high-quality voxel-wise references; (b) embeds ATB-BC physical constraints into the model architecture, promoting energy consistency during restoration; (c) achieves consistent improvements on the Atmos-Bench dataset across both 355 nm and 532 nm bands, outperforming state-of-the-art baseline models without relying on auxiliary inputs. Atmos-Bench establishes a new standard for satellite-based 3D atmospheric structure recovery and paves the way for deeper climate insight.

Related papers

• 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)
• Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting [52.53742727060265]
  Foundation models (FMs) for the Earth system learn statistical relationships between physical variables across massive datasets.<n>Here, we introduce Earth System Foundation Model (ESFM), a fully open model building on the 3Dwin UNet backbone of the pioneering model.<n>We present findings using dense gridded data (ERA5, CMIP6), regionally masked dense data, sparse gridded MODIS satellite data, and station data.<n>Results demonstrate competitive or superior performance relative to state-of-the-art benchmarks.
  arXiv  Detail & Related papers  (2026-04-20T11:40:39Z)
• Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classification [54.952203312050564]
  Adversarial attacks pose a severe threat to the reliability of deep learning models in remote sensing (RS) image classification.<n>We propose FogFool, a physically plausible adversarial framework that generates fog-based perturbations.<n>Experiments on two benchmark RS datasets demonstrate that FogFool achieves superior performance.
  arXiv  Detail & Related papers  (2026-04-16T05:47:57Z)
• CERBERUS: A Three-Headed Decoder for Vertical Cloud Profiles [0.0]
  Atmospheric clouds exhibit complex three-dimensional structure and microphysical details.<n>This mismatch complicates data-driven learning and evaluation of cloud processes in weather and climate models.<n>We introduce CERBERUS, a probabilistic inference framework for generating vertical radar reflectivity profiles.
  arXiv  Detail & Related papers  (2026-04-09T21:16:42Z)
• Hybrid Quantum-Classical Spatiotemporal Forecasting for 3D Cloud Fields [17.43641088991807]
  We propose QENO, a hybrid quantum-classicaltemporal framework for 3D cloud fields forecasting.<n> Experiments show that QENO consistently outperforms representative baselines.<n>These results indicate that topology-aware hybrid quantum-classical feature modeling is a promising direction for 3D cloud structure forecasting.
  arXiv  Detail & Related papers  (2026-03-31T08:12:13Z)
• NimbusGS: Unified 3D Scene Reconstruction under Hybrid Weather [83.14198482357388]
  We present NimbusGS, a unified framework for reconstructing high-quality 3D scenes from degraded multi-view inputs.<n>Unlike existing methods that target specific weather types, NimbusGS addresses the broader challenge of generalization.
  arXiv  Detail & Related papers  (2026-03-28T10:46:29Z)
• PolGS++: Physically-Guided Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction [76.9760302941819]
  PolGS++ is a polarimetric Gaussian Splatting framework for fast reflective surface reconstruction.<n>We introduce a depth-guided visibility mask acquisition mechanism that enables angle-of-polarization (AoP)-based tangent-space consistency constraints.
  arXiv  Detail & Related papers  (2026-03-11T14:11:42Z)
• Nowcast3D: Reliable precipitation nowcasting via gray-box learning [43.74533335638689]
  Extreme precipitation nowcasting demands high-dimensional fidelity and extended lead times, yet existing approaches remain limited.<n>We introduce a gray-box, fully three-temporal nowcasting framework that directly processes radar motions and couples physically constrained neural operators with datadriven learning.<n>The framework achieves more accurate forecasts up to three-hour lead time in a blind evaluation by 160 meteorologists.
  arXiv  Detail & Related papers  (2025-11-06T18:44:35Z)
• Conditional Diffusion Models for Global Precipitation Map Inpainting [0.0]
  Incomplete satellite-based precipitation presents a significant challenge in global monitoring.<n>In this study, we formulate the completion of precipitation map as a video inpainting task.<n>We propose a machine learning approach based on conditional diffusion models.
  arXiv  Detail & Related papers  (2025-07-28T02:26:36Z)
• ReconMOST: Multi-Layer Sea Temperature Reconstruction with Observations-Guided Diffusion [48.540756751934836]
  ReconMOST is a data-driven guided diffusion model framework for multi-layer sea temperature reconstruction.<n>Our method extends ML-based SST reconstruction to a global, multi-layer setting, handling over 92.5% missing data.
  arXiv  Detail & Related papers  (2025-06-12T06:27:22Z)
• Advanced long-term earth system forecasting by learning the small-scale nature [74.19833913539053]
  We present Triton, an AI framework designed to address this fundamental challenge.<n>Inspired by increasing grids to explicitly resolve small scales in numerical models, Triton employs a hierarchical architecture processing information across multiple resolutions to mitigate spectral bias.<n>We demonstrate Triton's superior performance on challenging forecast tasks, achieving stable year-long global temperature forecasts, skillful Kuroshio eddy predictions till 120 days, and high-fidelity turbulence simulations.
  arXiv  Detail & Related papers  (2025-05-26T02:49:00Z)
• A Staged Deep Learning Approach to Spatial Refinement in 3D Temporal Atmospheric Transport [0.0]
  We introduce the Dual-Stage Temporal Three-dimensional Super-resolution (DST3D-UNet-SR) model for plume dispersion prediction.<n>It is composed of two sequential modules: the temporal module (TM), which predicts the transient evolution of a plume in complex terrain from low-resolution temporal data, and the spatial refinement module (SRM), which subsequently enhances the spatial resolution of the predictions.
  arXiv  Detail & Related papers  (2024-12-14T19:43:48Z)
• PBR-NeRF: Inverse Rendering with Physics-Based Neural Fields [49.6405458373509]
  We present an inverse rendering (IR) model capable of jointly estimating scene geometry, materials, and illumination.<n>Our method is easily adaptable to other inverse rendering and 3D reconstruction frameworks that require material estimation.
  arXiv  Detail & Related papers  (2024-12-12T19:00:21Z)
• KFD-NeRF: Rethinking Dynamic NeRF with Kalman Filter [49.85369344101118]
  We introduce KFD-NeRF, a novel dynamic neural radiance field integrated with an efficient and high-quality motion reconstruction framework based on Kalman filtering. Our key idea is to model the dynamic radiance field as a dynamic system whose temporally varying states are estimated based on two sources of knowledge: observations and predictions. Our KFD-NeRF demonstrates similar or even superior performance within comparable computational time and state-of-the-art view synthesis performance with thorough training.
  arXiv  Detail & Related papers  (2024-07-18T05:48:24Z)
• Enhancing Weather Predictions: Super-Resolution via Deep Diffusion Models [0.0]
  This study investigates the application of deep-learning diffusion models for the super-resolution of weather data. We present a methodology for transforming low-resolution weather data into high-resolution outputs.
  arXiv  Detail & Related papers  (2024-06-06T14:15:12Z)
• Forecasting Tropical Cyclones with Cascaded Diffusion Models [4.272401529389713]
  This work leverages generative diffusion models to forecast cyclone trajectories and precipitation patterns. Forecasts can be produced in as little as 30 mins on a single Nvidia A30/RTX 2080 Ti.
  arXiv  Detail & Related papers  (2023-10-02T23:09:59Z)
• Predicting the Radiation Field of Molecular Clouds using Denoising Diffusion Probabilistic Models [2.2215308271891403]
  We employ deep learning techniques to predict the interstellar radiation field (ISRF) strength based on three-band dust emission at 4.5 um, 24 um, and 250 um. Our model robustly predicts radiation feedback distribution, even in complex, poorly constrained ISRF environments.
  arXiv  Detail & Related papers  (2023-09-11T20:28:43Z)
• DehazeNeRF: Multiple Image Haze Removal and 3D Shape Reconstruction using Neural Radiance Fields [56.30120727729177]
  We introduce DehazeNeRF as a framework that robustly operates in hazy conditions. We demonstrate successful multi-view haze removal, novel view synthesis, and 3D shape reconstruction where existing approaches fail.
  arXiv  Detail & Related papers  (2023-03-20T18:03:32Z)
• Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection [60.89616629421904]
  Lidar-based object detectors are critical parts of the 3D perception pipeline in autonomous navigation systems such as self-driving cars. They are sensitive to adverse weather conditions such as rain, snow and fog due to reduced signal-to-noise ratio (SNR) and signal-to-background ratio (SBR)
  arXiv  Detail & Related papers  (2021-07-14T21:10:47Z)

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.