AI Archives

2.5 billion year old microbial structures -- The black features within this thin slice of rock are 2.5-billion-year-old microbial structures. This study suggests that the organic matter preserved within this complex microbial community may have been produced by photosynthetic microorganisms. Image credit: Andrea Corpolongo

AI - Data - Apps - Cybernetics, Atmospheres, Climate, Weather, Biochemistry & Organic Chemistry, Biogeochemical Cycles & Geobiology, Biosignatures & Paleobiology, Fossils & Paleontology, Meteorites & Asteroids, Origin & Evolution of Life, Press Release

Chemical Evidence Of Ancient Life Detected In 3.3 billion-year-old Rocks

by Keith CowingNovember 18, 2025November 18, 2025

Pairing cutting-edge chemistry with artificial intelligence, a multidisciplinary team of scientists today published fresh chemical evidence of Earth’s earliest life – concealed in 3.3-billion-year-old rocks – and molecular evidence that […]

Neural networks help map ocean colour -- ESA (larger image)

AI - Data - Apps - Cybernetics, Atmospheres, Climate, Weather, Biogeochemical Cycles & Geobiology, Gaia - Planetary Perspectives, Mapping, Geodesy, Cartography, Bathymetry, Press Release, Water/Hycean Worlds & Oceanography

AI World Model To Simulate The Earth System

by Keith CowingNovember 13, 2025November 13, 2025

Climate change is already reshaping global weather patterns and ecosystems around the world. In the long-term, its consequences could range from further substantial increases in the number of extreme weather […]

A diagram showing how data flows through the transformer architecture implemented here. Data padding and masking are left out for simplicity. The model does implement this functionality, but it is not necessary for our constant-length sequences. -- astro-ph.EP

AI - Data - Apps - Cybernetics, Atmospheres, Climate, Weather, Biogeochemical Cycles & Geobiology, Exoplanets, -moons, -comets, Status Report

Accelerating Radiative Transfer For Planetary Atmospheres by Orders of Magnitude with a Transformer-Based Machine Learning Model

by Keith CowingNovember 7, 2025November 7, 2025

Radiative transfer calculations are essential for modeling planetary atmospheres. However, standard methods are computationally demanding and impose accuracy-speed trade-offs. High computational costs force numerical simplifications in large models (e.g., General […]

graphical abstract - University of Oxford/Breakthrough Listen

AI - Data - Apps - Cybernetics, Astronomy & Telescopes, Biosignatures & Paleobiology, Intelligence & Language, Interstellar, Press Release, SETI & Technosignatures

Revolutionary AI System Achieves 600× Speed Breakthrough in Detection of Signals from Space

by Keith CowingNovember 6, 2025

In an exciting leap forward for astronomy, researchers at the Breakthrough Listen initiative, in partnership with NVIDIA, have achieved a groundbreaking advancement in the search for Fast Radio Bursts (FRBs), […]

ReplicationBench evaluates AI agents on end-to-end astrophysics research paper replication. For each paper, we supply the manuscript, dataset, and execution metadata, and a complete set of author-written tasks. We evaluate LLM agents in multi-turn code execution environments and conduct both automatic and expert human grading of traces. -- cs.CL

AI - Data - Apps - Cybernetics, Citizen Science / Open Science, Education and Outreach, Genomics, Proteomics, Bioinformatics, Mapping, Geodesy, Cartography, Bathymetry, Nomenclature, Systematics, Natural History, Status Report

ReplicationBench: Can AI Agents Replicate Astrophysics Research Papers?

by Keith CowingOctober 31, 2025October 31, 2025

Frontier AI agents show increasing promise as scientific research assistants, and may eventually be useful for extended, open-ended research workflows.

The Teledyne Marine-Rutgers University Sentinel Redwing autonomous underwater vehicle is embarking on an underwater journey that could be a world first: circumnavigating the globe. -- Teledyne Marine

AI - Data - Apps - Cybernetics, Analog Studies, Arctic / Antarctic / Alpine, Biosignatures & Paleobiology, Exploration Gear & Tech, Habitable Zones, Icy Worlds, Imaging & Spectroscopy, Mapping, Geodesy, Cartography, Bathymetry, Missions & Hardware, Press Release, ROVs/Submersibles/Diving, Sample Return, Tricorders & Sensors, Water/Hycean Worlds & Oceanography

An Autonomous Robotic Glider Will Circle And Explore Our Ocean Planet

by Keith CowingOctober 29, 2025October 29, 2025

Editor’s note: When we start to mount Astrobiology missions to explore ocean worlds we’ll need ways for our robotic submersibles to observe and interact with whatever life forms they may […]

AI - Data - Apps - Cybernetics, Astronomy & Telescopes, Press Release, SETI & Technosignatures

SETI Institute Accelerates the Search for Life Beyond Earth with NVIDIA IGX Thor

by Keith CowingOctober 28, 2025October 29, 2025

The SETI Institute announced that it will incorporate the new NVIDIA IGX Thor platform to enhance its real-time search for signals from space at the Allen Telescope Array (ATA) in […]

For the second stage of our analysis pipeline, outputs were further evaluated using a livability index L (scaled between 0 and 1). Among the 51 Mars-positive samples, the mean livability index was 0.417, with scores clustering at a midrange band of 0.31-0.48 (Table 5). These results suggest that most images were neutrally classified with the model neither stating high nor low livability rates across the tested data. Dust warnings were found to be common, with twenty-four samples flagged as “Warning” , twenty-five as “Caution” , and two as “Severe” (Table 6). -- eartharxiv.org

Biosignatures & Paleobiology, Desert Worlds, Habitable Zones, Imaging & Spectroscopy, Mars, Missions & Hardware, Robotics/Rovers/UAVs, Sample Return, Status Report, Tricorders & Sensors

A Computer Vision Framework For Estimating Surface Habitability From Mars Using Convolutional Analysis

by Keith CowingOctober 28, 2025October 28, 2025

Identifying signs of life in extraterrestrial environments is one of the growing challenges in planetary science. Conventional approaches of detecting habitability rely heavily on direct contact with biosignatures or geological […]

Figure reproduced from H. Toru Shay et al. (2025). The detected inventory of TMC–1 molecular species and their column densities is converted into numerical vectors with the VICGAE model. The vectorized strings and the corresponding column densities are then used to train a machine learning regressor. Through learning the relationship between vectorized molecular structures and their column densities, the model is optimized to find the best fit. Once trained, the best-fit model can predict column densities for new molecules and be used to identify potential detection targets in TMC–1. -- The Astrophysical Journal

AI - Data - Apps - Cybernetics, Astrochemistry, Astronomy & Telescopes, Biochemistry & Organic Chemistry, Biosignatures & Paleobiology, Imaging & Spectroscopy, Status Report

Bridging Machine Learning and Spectroscopy: A New Analysis for Astrochemical Target Selection

by Keith CowingOctober 27, 2025October 27, 2025

In the last few years, several approaches have used machine learning to reproduce the inventory and column densities of interstellar molecular sources.

Visual characteristics observed according to treatment, polygon distribution, sand/clay ratio, primary/secondary desiccations ratio, shapes (type and size), and color on the top of the polygonal forms. A = abiotic control; C = cyanobacteria; D = diatoms; G = green algae; M = mixed; B = biotic strains; 1 = low biomass; 2 = high biomass.

AI - Data - Apps - Cybernetics, Biogeochemical Cycles & Geobiology, Biophysics, Biosignatures & Paleobiology, Imaging & Spectroscopy, Mars, Microbiology & Virology, Press Release

Artificial Intelligence-Enhanced Detection of Biogenicity Using Laboratory Specimens of Biologically and Microbially Induced Sedimentary Structures in a Controlled Experiment

by Keith CowingOctober 24, 2025October 25, 2025

The search for traces of life can be based on the detection of specific signatures produced by microorganisms on sedimentary rocks.

AI

Chemical Evidence Of Ancient Life Detected In 3.3 billion-year-old Rocks

AI World Model To Simulate The Earth System

Accelerating Radiative Transfer For Planetary Atmospheres by Orders of Magnitude with a Transformer-Based Machine Learning Model

Revolutionary AI System Achieves 600× Speed Breakthrough in Detection of Signals from Space

ReplicationBench: Can AI Agents Replicate Astrophysics Research Papers?

An Autonomous Robotic Glider Will Circle And Explore Our Ocean Planet

SETI Institute Accelerates the Search for Life Beyond Earth with NVIDIA IGX Thor

A Computer Vision Framework For Estimating Surface Habitability From Mars Using Convolutional Analysis

Bridging Machine Learning and Spectroscopy: A New Analysis for Astrochemical Target Selection

Artificial Intelligence-Enhanced Detection of Biogenicity Using Laboratory Specimens of Biologically and Microbially Induced Sedimentary Structures in a Controlled Experiment

How High-pressure Ices On Large Ocean Worlds Can Support Habitability: The Compatibility Of Amino Acids Into Ice VI And VII

Ice Drives The Emergence Of Functional Protocells

Chemical Abundance Patterns at z=1-7: Carbon, Nitrogen, Neon, Sulphur, and Argon Abundances From JWST Spectroscopy

Optimization of Petal-Shaped Occulters for Exo-Earth Observation

Topographically Forced Stationary Waves Can Explain The Near-Surface Zonal Winds Observed By Huygens On Titan