ExoNet: Calibrated Multimodal Deep Learning for TESS Exoplanet Candidate Vetting using Phase-Folded Light Curves, Stellar Parameters, and Multi-Head Attention

• URL: http://arxiv.org/abs/2604.15560v3
• Date: Wed, 22 Apr 2026 11:08:34 GMT
• Title: ExoNet: Calibrated Multimodal Deep Learning for TESS Exoplanet Candidate Vetting using Phase-Folded Light Curves, Stellar Parameters, and Multi-Head Attention
• Abstract summary: ExoNet is a multimodal deep learning framework that processes phase-folded global and local light curve views alongside stellar parameter features.<n>It is trained on 7,585 labeled Kepler Objects of Interest and achieves Test AUC = 0.9549 and 86.3% accuracy.<n>ToI-5728.01 and TOI-6716.01 emerge as the most Earth-like unconfirmed candidates.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The discovery of exoplanets at scale has become one of the defining data science challenges in modern astrophysics. NASA's Transiting Exoplanet Survey Satellite (TESS) had catalogued over 7,800 planet candidates by early 2026, yet confirmation stands at fewer than 720. This paper introduces ExoNet, a multimodal deep learning framework that jointly processes phase-folded global and local light curve views alongside stellar parameter features through a calibrated late-fusion architecture combining 1D Convolutional Neural Networks, 8-head Multi-Head Attention over temporal feature maps, and a residual fusion head with post-hoc Temperature Scaling calibration. Trained on 7,585 labeled Kepler Objects of Interest, ExoNet achieves Test AUC = 0.9549 and 86.3% accuracy. Applied to 4,720 verified unconfirmed TESS Planet Candidates with TOI-TIC cross-identification verified against the NASA Exoplanet Archive, the model yields 1,754 high-confidence signals, 52 habitable-zone candidates, and six Earth-sized habitable-zone targets below 1.6 Earth radii. TOI-5728.01 and TOI-6716.01 emerge as the most Earth-like unconfirmed candidates. Full ablation confirms each modality improves AUC. Code and catalog are openly released.

Related papers

• Apodex Discovery: Reality Benchmarks and Environments for Evaluating and Building Discoverative Artificial Intelligence [86.61561123749011]
  We introduce Apodex Discovery, a framework for building and evaluating discoverative AI through the heavy-duty solver.<n>First, a problem-scouting process surveyed 561 industries across 16 sectors, assembled 423 high-value real-world problems, and selected 20 for the initial release.<n>Second, a common environment-task-episode abstraction provides data, tools, constraints, feedback, trajectory recording, and verification of intermediate artifacts and final submissions.
  arXiv  Detail & Related papers  (2026-08-11T18:48:40Z)
• Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Tasks [20.969678030412407]
  Earth-OneVision is a 2B RS-MLLM that unifies six sensor modalities and cross-sensor fusion across 9 task categories.<n>With only 2B parameters, Earth-OneVision achieves competitive or state-of-the-art results across extensive benchmarks.
  arXiv  Detail & Related papers  (2026-06-09T13:01:51Z)
• Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discovery [51.70607714288616]
  Science Earth is a planet-scale scientific runtime in which any capability can connect to any other.<n>Its underlying EACN protocol lets capabilities discover one another, negotiate task ownership, and adjudicate across incompatible evidentiary standards.<n>Two runs validate this under structurally distinct conditions.
  arXiv  Detail & Related papers  (2026-05-31T16:05:41Z)
• Multi-Tier Labeling and Physics-Informed Learning for Orbital Anomaly Detection at Scale [0.0]
  We present a multi-tier labeling cascade that composes three weak supervision sources of increasing fidelity.<n>applied to 232M Two-Line Element (TLE) records spanning 60 years, the cascade yields 8.6M labeled sequences of length 50 (430M timesteps) over 11 features.<n>On overlapping satellites, IMM-UKF surfaces 42.6x more anomalies than rule_v1 alone.
  arXiv  Detail & Related papers  (2026-05-10T22:20:52Z)
• TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation [65.74990259650984]
  We introduce TerraFM, a scalable self-supervised learning model that leverages globally distributed Sentinel-1 and Sentinel-2 imagery.<n>Our training strategy integrates local-global contrastive learning and introduces a dual-centering mechanism.<n>TerraFM achieves strong generalization on both classification and segmentation tasks, outperforming prior models on GEO-Bench and Copernicus-Bench.
  arXiv  Detail & Related papers  (2025-06-06T17:59:50Z)
• DART-Vetter: A Deep LeARning Tool for automatic triage of exoplanet candidates [29.27453886018479]
  DART-Vetter is a Convolutional Neural Network that processes only the light curves folded on the period of the relative signal.<n>We trained and tested DART-Vetter on several dataset of publicly available and homogeneously labelled TESS and Kepler light curves.
  arXiv  Detail & Related papers  (2025-06-05T20:05:16Z)
• EarthMind: Leveraging Cross-Sensor Data for Advanced Earth Observation Interpretation with a Unified Multimodal LLM [103.7537991413311]
  Earth Observation (EO) data analysis is vital for monitoring environmental and human dynamics.<n>Recent Multimodal Large Language Models (MLLMs) show potential in EO understanding but remain restricted to single-sensor inputs.<n>We propose EarthMind, a unified vision-language framework that handles both single- and cross-sensor inputs.
  arXiv  Detail & Related papers  (2025-06-02T13:36:05Z)
• OmniEarth-Bench: Towards Holistic Evaluation of Earth's Six Spheres and Cross-Spheres Interactions with Multimodal Observational Earth Data [72.98496934729245]
  Existing benchmarks for multimodal learning in Earth science offer limited, siloed coverage of Earth's spheres and their cross-sphere interactions.<n>We introduce textbf OmniEarth-Bench, the first multimodal benchmark that systematically spans all six spheres.<n>Built with a scalable, modular-topology data inference framework and native multi-observation sources, OmniEarth-Bench produces 29,855 standardized, expert-curated annotations.
  arXiv  Detail & Related papers  (2025-05-29T15:02:27Z)
• A New Statistical Model of Star Speckles for Learning to Detect and Characterize Exoplanets in Direct Imaging Observations [37.845442465099396]
  This paper presents a novel statistical model that captures nuisance fluctuations using a multi-scale approach.<n>It integrates into an interpretable, end-to-end learnable framework for simultaneous exoplanet detection and flux estimation.<n>The proposed approach is computationally efficient, robust to varying data quality, and well suited for large-scale observational surveys.
  arXiv  Detail & Related papers  (2025-03-21T13:07:55Z)
• PFSD: A Multi-Modal Pedestrian-Focus Scene Dataset for Rich Tasks in Semi-Structured Environments [73.80718037070773]
  We present the multi-modal Pedestrian-Focused Scene dataset, rigorously annotated in semi-structured scenes with the format of nuScenes.<n>We also propose a novel Hybrid Multi-Scale Fusion Network (HMFN) to detect pedestrians in densely populated and occluded scenarios.
  arXiv  Detail & Related papers  (2025-02-21T09:57:53Z)
• ExoMiner++: Enhanced Transit Classification and a New Vetting Catalog for 2-Minute TESS Data [0.30325574299856156]
  We present an enhanced deep learning model that builds on the success of ExoMiner to improve transit signal classification in 2-minute TESS data.<n>ExoMiner++ incorporates additional diagnostic inputs, including periodogram, flux trend, difference image, unfolded flux, and spacecraft attitude control data.<n>To serve the exoplanet community, we introduce new TESS catalog containing ExoMiner++ classifications and confidence scores for each transit signal.
  arXiv  Detail & Related papers  (2025-02-13T21:53:58Z)
• Exoplanet Transit Candidate Identification in TESS Full-Frame Images via a Transformer-Based Algorithm [2.447952962179654]
  We propose an approach to identify exoplanet transit signals without the need for phase folding or assuming periodicity.<n>We implement a new neural network inspired by Transformers to directly process Full Frame Image (FFI) light curves to detect exoplanet transits.<n>Our model successfully identified 214 new planetary system candidates, including 122 multi-transit light curves, 88 single-transit and 4 multi-planet systems.
  arXiv  Detail & Related papers  (2025-02-11T13:29:58Z)
• SpectralEarth: Training Hyperspectral Foundation Models at Scale [47.93167977587301]
  We introduce SpectralEarth, a large-scale multitemporal dataset designed to pretrain hyperspectral foundation models.<n>We pretrain a series of foundation models on SpectralEarth, integrating a spectral adapter into classical vision backbones.<n>In tandem, we construct nine downstream datasets for land-cover, crop-type mapping, and tree-species classification.
  arXiv  Detail & Related papers  (2024-08-15T22:55:59Z)
• SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection [68.18620488664187]
  We propose a simple yet effective Semi-supervised Oriented Object Detection method termed SOOD++.<n> Specifically, we observe that objects from aerial images usually have arbitrary orientations, small scales, and dense distribution.<n>Extensive experiments conducted on various oriented object under various labeled settings demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2024-07-01T07:03:51Z)
• Identifying Exoplanets with Deep Learning. V. Improved Light Curve Classification for TESS Full Frame Image Observations [1.4060799411474627]
  This paper presents a dataset containing light curves from the Primary Mission and 1st Extended Mission full frame images and periodic signals detected via Box Least Squares. The dataset was curated using a thorough manual review process then used to train a neural network called Astronet-Triage-v2. Astronet-Triage-v2 is able to recover 3577 out of 4140 TOIs, while Astronet-Triage only recovers 3349 targets at an equal level of precision.
  arXiv  Detail & Related papers  (2023-01-03T21:58:13Z)
• MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection [89.26380781863665]
  Fusing LiDAR and camera information is essential for achieving accurate and reliable 3D object detection in autonomous driving systems. Recent approaches aim at exploring the semantic densities of camera features through lifting points in 2D camera images into 3D space for fusion. We propose a novel framework that focuses on the multi-scale progressive interaction of the multi-granularity LiDAR and camera features.
  arXiv  Detail & Related papers  (2022-09-07T12:29:29Z)
• Automated identification of transiting exoplanet candidates in NASA Transiting Exoplanets Survey Satellite (TESS) data with machine learning methods [1.9491825010518622]
  The AI/ML ThetaRay system is trained initially with Kepler exoplanetary data and validated with confirmed exoplanets. By the application of ThetaRay to 10,803 light curves of threshold crossing events (TCEs) produced by the TESS mission, we uncover 39 new exoplanetary candidates.
  arXiv  Detail & Related papers  (2021-02-20T12:28:39Z)
• A Two-Stage Deep Learning Detection Classifier for the ATLAS Asteroid Survey [0.0]
  We present a two-step neural network model to separate detections of solar system objects from optical and electronic artifacts. We show that the model reaches 99.6% accuracy on real asteroids in ATLAS data with a 0.4% false negative rate.
  arXiv  Detail & Related papers  (2021-01-22T01:35:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.