The paper introduces a transformer-based DeepONet that uses a Perceiver encoder and cross‑attention decoder to model the radiative transfer equation (RTE) across multiple spatial resolutions. Unlike traditional DeepONets, this architecture avoids affine reconstruction, allowing a single model to handle inputs at varying resolutions without resampling. Experiments on a two‑dimensional pool‑fire dataset show that the new method outperforms autoencoder‑based DeepONets in predicting radiative intensity and incident radiation, with fewer parameters and better preservation of small‑scale structures.
arXiv:2608. 14744v1 Announce Type: new Abstract: Recovering high-resolution states from sparse, low-resolution observations is a central challenge in scientific machine learning and data assimilation.
arXiv:2610.31889v1 Announce Type: cross Abstract: Energy-Based Models (EBMs) are a flexible class of generative models that decouple probabilistic modeling from the generation process. This decouplin...
arXiv:2608. 07580v1 Announce Type: cross Abstract: In this work, we present a wildfire temperature retrieval framework for VSWIR imaging spectroscopy data, employed on data from NASA's Airborne Visible Infrared Imaging Spectrometer (AVIRIS-3).
The paper introduces TSR-ITNR, a two‑stage, self‑supervised framework for hyperspectral image super‑resolution that fuses high‑resolution multispectral and low‑resolution hyperspectral data. Stage 1 refines an implicit Tucker representation using a low‑rank spatial tensor and spectral basis, enhanced by a pretrained denoiser, to capture fine spatial details and spectral correlations. Stage 2 applies parameter‑free calibration to extract complementary corrections from both observations, preserving geometry and ensuring orthogonal complementarity, leading to superior reconstruction quality demonstrated on benchmark datasets and improved downstream segmentation performance.
The study evaluates deep learning surrogates for wildfire spread prediction, training four architectures on 10,584 high‑resolution simulations from Catalonia. Results show that only surface fuel load significantly predicts burn probability, and convolutional models mainly use distance to the fire front while a transformer model emphasizes fuel and terrain. When applied to a new region without retraining, the models still perform reasonably, with only a modest accuracy drop.
arXiv:2609.18773v1 Announce Type: new Abstract: Long-range infrared imaging frequently confronts dense target clusters whose diffraction-limited signatures merge into a single indistinguishable blob,...
arXiv:2606. 08324v1 Announce Type: cross Abstract: Passive long-wave infrared (LWIR) hyperspectral imaging under a standoff geometry depends on atmospheric absorption and emission, as well as reflected radiance, thus making atmospheric compensation essential to get knowledge of a target of interest.
arXiv:2509. 09195v2 Announce Type: replace Abstract: Current evaluation metrics for deep learning weather models create a "Statistical Similarity Trap", rewarding blurry predictions while missing rare, high-impact events.
arXiv:2610.04044v3 Announce Type: replace-cross Abstract: The quadratic attention cost of Vision Transformers (ViTs) forces a trade-off between spatial resolution and rollout horizon, particularly fo...
The review discusses how two‑phase heat transfer—critical for boiling, condensation, and thermal management—poses challenges for data reuse due to its complex interfacial physics. It surveys open datasets, machine‑learning techniques, and reusable software, organizing them with a spatial‑plus‑temporal dimensionality taxonomy (S+TD) that links data types to AI tasks such as regression, sequence learning, and image/video analysis. The paper proposes a roadmap for physics‑aware open data, including metadata standards, maturity labels, benchmark splits, and community databanks, emphasizing that progress in two‑phase AI relies as much on robust data infrastructure as on model design.
The paper investigates how different attention mechanisms affect the performance of DeepONet neural operators. Five variants—varying in cross‑attention, self‑attention, tokenization, and attention depth—are trained in both data‑driven and physics‑informed settings on one‑ and two‑dimensional PDE benchmarks. Results show that per‑sensor tokenization with cross‑attention consistently reduces error, while branch self‑attention helps only in complex spatial problems, and deeper cross‑attention yields diminishing returns with higher cost.
arXiv:2605. 13258v2 Announce Type: replace-cross Abstract: In this work, we present our winning solution for the 8th UG2+ Challenge (CVPR 2026) Track 1: Image Restoration under All-weather Conditions.