A Deep Multimodal Multi--Head Neural Network for Joint Estimation of Stellar Age, Lifetime, and Evolutionary Stage

TL;DR

This paper presents a novel deep learning model that combines spectroscopic and photometric data to accurately estimate stellar age, lifetime, and evolutionary stage, setting a new benchmark in astrophysical parameter estimation.

Contribution

It introduces a hybrid multimodal neural network architecture with multi-task learning for joint stellar parameter estimation from SDSS data, incorporating advanced data balancing and loss optimization techniques.

Findings

Achieved age estimation RMSE of 0.093 in log-years.

Model provides well-calibrated uncertainties via Monte Carlo Dropout.

Established a new benchmark for multimodal stellar parameter estimation.

Abstract

Accurate estimation of stellar parameters -- stellar age, lifetime, and evolutionary stage -- remains a fundamental challenge in astrophysics. We introduce a hybrid deep learning architecture combining multimodal spectroscopic and photometric data from SDSS DR17. The model comprises a Multi-Layer Perceptron for numerical features and a CNN with a Vision Transformer for spectra, with three output heads for age, lifetime, and evolutionary stage prediction. Training labels are derived from MIST v1.2 isochrones, with evolutionary stage binned into five classes (Hot, Medium, Cool, Subgiant, Red Giant). We conduct multi-phase evaluation: Phase I explores model architectures and data balancing strategies, Phase II tunes architectural complexity, and Phase III optimizes the multi-task loss composition. The final model achieves a balance between precision (Age RMSE 0.093 in $\log(\mathrm{yrs})$) and physical realism. Monte Carlo Dropout confirms well-calibrated uncertainties, enabling meaningful astrophysical interpretation and establishing a new benchmark for multimodal stellar parameter estimation.