World PulseNow
Newsletter

Operational machine learning for remote spectroscopic detection of CH$_{4}$ point sources

arXiv — cs.CV•Wednesday, November 12, 2025 at 5:00:00 AM
PositiveArtificial Intelligence
A new machine learning system has been operationally deployed within the Methane Alert and Response System (MARS) of the United Nations Environment Programme to enhance the detection of methane emissions. Traditional satellite-based imaging spectrometers like EMIT, PRISMA, and EnMAP have struggled with high false detection rates, necessitating extensive manual verification. This innovative approach has successfully reduced false detections by over 74%, allowing for the verification of 1,351 distinct methane leaks and the notification of 479 stakeholders. This advancement is significant in the fight against climate change, as mitigating methane emissions is a cost-effective strategy to slow global warming.
— via World Pulse Now AI Editorial System
Read Original

Was this article worth reading? Share it

Recommended Readings
Detection of Bark Beetle Attacks using Hyperspectral PRISMA Data and Few-Shot Learning
arXiv — cs.CV2 days ago
Detection of Bark Beetle Attacks using Hyperspectral PRISMA Data and Few-Shot Learning
PositiveArtificial Intelligence
Bark beetle infestations pose a significant threat to the health of coniferous forests. A recent study introduces a few-shot learning method that utilizes contrastive learning to detect these infestations through satellite hyperspectral data from PRISMA. The approach involves pre-training a CNN encoder to extract features from hyperspectral data, which are then used to estimate the proportions of healthy, infested, and dead trees. Results from the Dolomites indicate that this method surpasses traditional PRISMA spectral bands and Sentinel-2 data in effectiveness.
Read full article
via arXiv — cs.CV