![Dataset construction pipeline. We extract comparisons from astronomy papers, screen them using performance differences and authors’ explanations, and write binary questions with expert review throughout. -- [astro-ph.IM]](https://i0.wp.com/astrobiology.com/wp-content/uploads/2026/11/Astro2Method.png?resize=1200%2C720&ssl=1)
[astro-ph.IM] Machine learning (ML) is increasingly used in astronomy, but choosing a suitable method for a scientific problem often requires expertise in both astronomy and ML.
AI
Posted inSETI & Technosignatures
Agentic AI Joins the Search for Extraterrestrial Signals
[NVIDIA]. While science fiction lore tells us that humans will meet extraterrestrial life in the form of little green men, the detail that should raise hairs this Halloween is this: […]
ML-Astrobiology Initiative Virtual Seminar: Human-Machine Collaboration for Scientific Hypothesis Generation: Lessons from AstroAgents
Hosted by the ML-Astrobiology Initiative at NASA Ames Research Center The speaker for this event will be Dr. Amirali Aghazadeh, from the Georgia Institute of Technology. Access event ASTROAGENTS Human-Machine […]
Posted inAI - Data - Apps - Cybernetics
The Great Chat In The Sky: Aligning Exotic Astronomical Data To Language With AstroBridge
[astro-ph.IM] Astronomical observations include images, spectra, and light curves, while the scientific literature describes these objects in natural language. We present AstroBridge, a framework that connects these observations to an […]
Posted inSpace Life Science
AI-Run Growth Chamber Will Test How Plants Develop in Microgravity Against a Matching Experiment on Earth
[Voyager Technologies] (NYSE: VOYG) executed a mission management contract with Interstellar Lab to host BioPod EDEN, the company’s autonomous plant growth payload, aboard the International Space Station (ISS).
![Left. Two-dimensional UMAP representation of the TMC-1 inventory using the original ChemBERTa input vectors. Right. Same representation but using the last hidden layer of the neural netwok model. The red rectangle highlights the region of the UMAP representation where highly abundant molecules are located. The different dot sizes represent the observed column density of each molecule. -- [astro-ph.GA]](https://i0.wp.com/astrobiology.com/wp-content/uploads/2026/10/A-neural.png?resize=1200%2C725&ssl=1)
Posted inAstrochemistry
A Neural-network Model To Find Correlations In Astrochemical Space
[astro-ph.GA] The detection of new interstellar molecules is central to astrochemistry, and arguably the most transformative development in the field in past decade has been the increase in both number […]
NASA Ames Machine Learning Seminar INDUS and INDUS-SDE: Scientific Language Models for Metadata Curation and Discovery Across NASA Science Divisions
JOIN THIS ML SEMINAR SERIES HERE Time: October 27th, 12PM PDT/3PM EDT Everyone is invited to the monthly machine learning virtual seminar hosted by the ML-Astrobiology Initiative at NASA Ames […]
![Overview of the ML-DH framework. Top: Training stage, using DFT energies, forces, and dipoles to train the NNFF and EPNN. Bottom: Prediction stage, yielding IR spectra via NNFF optimization, normal mode analysis, and EPNN dipole derivatives.-- [astro-ph.GA]](https://i0.wp.com/astrobiology.com/wp-content/uploads/2026/10/A-machine.png?resize=1200%2C719&ssl=1)
Posted inAstrochemistry
A Machine-learning-driven Dataset Of 144,111 Polycyclic Aromatic Hydrocarbon Infrared Spectra For Interpreting Aromatic Infrared Bands
[astro-ph.GA] The interpretation of interstellar aromatic infrared bands (AIBs) relies on reference spectral libraries, but the chemical space covered by existing databases remains incomplete relative to the vast structural diversity […]
![Set Transformer actor–critic architecture used by the RL policy. The input candidate set 𝑋 ∈ R 𝑁×𝐹 is first projected into a latent 𝑑-dimensional representation and processed by 𝐿 Induced Set Attention Blocks (ISABs). Learned inducing tokens provide the queries in the first attention operation of each ISAB, after which information is redistributed to the candidate tokens. The actor combines each contextualised target representation with the global mission state to produce one logit per available observation. Each logit is then converted into a probability to select a corresponding observation. The critic uses Pooling by Multihead Attention (PMA) to obtain a permutation-invariant summary of the candidate set, which is combined with the same global state to estimate 𝑉 (𝑠). -- [astro-ph.EP]](https://i0.wp.com/astrobiology.com/wp-content/uploads/2026/10/aRieL-Reinforcement.png?resize=1200%2C715&ssl=1)
Posted inAriel Mission
aRieL – Reinforcement Learning For The Ariel Space Telescope Scheduling
[astro-ph.EP] The Ariel mission will conduct a population level survey of hundreds of exoplanet atmospheres, requiring observations to be scheduled across a large and diverse catalogue of potential targets.
Posted inAI - Data - Apps - Cybernetics
Giving NASA’s SciX A Quick Astrobiology Roadtest
Keith’s note: Goodbye ADS – Hello SciX. According to an editorial “Farewell NASA ADS” in Nature magazine, “After more than 33 years, NASA’s Astrophysics Data System will close its virtual […]