arXiv:2604. 10094v2 Announce Type: replace-cross Abstract: Anthropogenic methane (CH4) point sources are critical drivers of near-term climate forcing, safety hazards, and system-inefficiencies.
arXiv:2609.09762v1 Announce Type: new Abstract: Methane plume detection from satellite imagery is constrained by incomplete observations: public satellites provide complementary spatial, spectral, an...
The paper introduces UnorthoDOS, a dataset and machine‑learning approach that enables methane plume detection directly on unorthorectified hyperspectral satellite imagery. Using U‑Net models trained on this data, the authors achieve performance close to models trained on orthorectified images (IoU 16.91% vs. 18.47%) and far surpass the traditional matched‑filter baseline (IoU 4.76%). They also demonstrate that FP16 compression can reduce model size by half with negligible loss in output accuracy, making onboard deployment feasible.
The paper reports the first on‑board detection of methane point source emissions using imaging spectroscopy data from the AVIRIS‑5 sensor during the Tokyo Field Campaign in March 2026. It describes how a compact machine‑learning model was deployed on the aircraft to predict potential trace‑gas events in real time, circumventing communication bottlenecks that prevent full data downlink during flight. The approach enables immediate identification of transient gas releases without waiting for ground‑based processing.
Imaging spectrometers increasingly distribute source-resolved methane plume products in which the plume mask, integrated mass enhancement (IME), plume length, emission rate, and uncertainty are physically and algorithmically linked. Using 63 EMIT-derived Carbon Mapper plume records from 27 scenes, we show that these published scalar quantities do not uniquely constrain the plume boundary: substantially different yet plausible masks reproduce the same IME, plume length, and emission rate.
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.
The technical report introduces Hyperspectral Image Models, a modular framework that unifies 55 deep‑learning models across six paradigms for hyperspectral remote sensing. It standardizes tensor conventions, evaluation protocols, and dataset handling, integrating 24 benchmark scenes from various sensors and providing tools to avoid train‑test overlap. Experiments across 1,320 model‑scene combinations show that scene difficulty outweighs architecture, with no single paradigm dominating and small models achieving performance comparable to much larger ones.
HyperSAM is a promptable foundation model for hyperspectral remote sensing that integrates a data‑centric synthesis pipeline with a spectral adaptation architecture based on Segment Anything Model 3 (SAM3). The model generates full‑spectrum hyperspectral cubes from high‑resolution multispectral imagery using a physics‑informed abundance‑transfer generator, and employs SAM3‑derived pseudo‑masks for object‑centric supervision. With a frozen SAM3 RGB branch, a trainable hyperspectral encoder, ControlNet‑style feature injection, and a mixture‑of‑experts mask refiner, HyperSAM demonstrates strong generalization across diverse hyperspectral tasks such as classification, anomaly detection, change detection, target detection, and airborne oil‑spill mapping.
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).
Annual Earth‑observation embeddings, specifically Tessera, can encode wildfire disturbance signals well enough to map burned areas without needing curated fire‑specific imagery or dense time‑series analysis. In tests, linear models using a single Tessera embedding matched or outperformed paired pre‑ and post‑fire HLS imagery and post‑fire imagery alone, achieving high F1 scores for burn‑scar delineation and regional mapping. The approach successfully mapped all same‑year fires in benchmark scenes, recovered 97% of California burned area without California training data, transferred to European fires with high accuracy, and even estimated ignition timing within a 13‑day error margin. "whyItMatters":"The study demonstrates that pre‑trained annual embeddings can simplify and scale burned‑area mapping, reducing reliance on dense time‑series data and enabling more efficient wildfire monitoring."
Hyperspectral remote sensing has advanced across diverse deep learning paradigms, including spectral spatial CNNs, Vision Transformers, Mamba, graph neural networks, Kolmogorov Arnold networks, and se...
The study presents a spatially aware deep learning framework that retrieves all‑sky tropospheric temperature and humidity profiles from the Meteosat Third Generation Flexible Combined Imager (FCI) without relying on numerical weather prediction background fields. Using a Residual U‑Net trained on 14 months of collocated FCI observations and CERRA reanalysis data, the model achieves temperature biases below 0.4 K and relative humidity standard deviations between 12–20 %, with modest performance degradation under cloud cover. Ablation and feature‑sensitivity analyses confirm that incorporating spatial context across all 16 FCI channels, including visible and near‑infrared bands, improves retrieval accuracy, especially beneath cloud tops.
arXiv:2607. 05207v1 Announce Type: cross Abstract: Self-supervised learning (SSL) is designed to learn generic, transferable representations rather than representations optimized for a single task.