Related papers: Disk2Planet: A Robust and Automated Machine Learni…
High-precision radial velocity planet searches have surveyed over ~2000 nearby stars and detected over ~200 planets. While these same stars likely harbor many additional planets, they will become increasingly challenging to detect, as they…
We present PlanetPack, a new software tool that we developed to facilitate and standardize the advanced analysis of radial velocity (RV) data for the goal of exoplanets detection, characterization, and basic dynamical $N$-body simulations.…
Deep learning algorithms are growing in popularity in the field of exoplanetary science due to their ability to model highly non-linear relations and solve interesting problems in a data-driven manner. Several works have attempted to…
Many novel methods have been proposed to mitigate stellar activity for exoplanet detection as the presence of stellar activity in radial velocity (RV) measurements is the current major limitation. Unlike traditional methods that model…
This study uses numerical hydrodynamics calculations and a novel method for densely sampling parameter space to measure the precise shape of a gap opened by a planet in a gaseous disk, as a function of planet-to-star mass ratio, disk Mach…
We model the spectral energy distributions (SEDs) of 23 protoplanetary disks in the Taurus-Auriga star-forming region using detailed disk models and a Bayesian approach. This is made possible by combining these models with artificial neural…
The connection between the nature of a protoplanetary disk and that of a debris disk is not well understood. Dust evolution, planet formation, and disk dissipation likely play a role in the processes involved. We aim to reconcile both…
We present models of giant planet migration in evolving protoplanetary disks. Our disks evolve subject to viscous transport of angular momentum and photoevaporation, while planets undergo Type II migration. We use a Monte Carlo approach,…
Recent ALMA molecular line observations have revealed 3-D gas velocity structure in protoplanetary disks, shedding light on mechanisms of disk accretion and structure formation. 1) By carrying out viscous simulations, we confirm that the…
A large amount of document data exists in unstructured form such as raw images without any text information. Designing a practical document image analysis system is a meaningful but challenging task. In previous work, we proposed an…
Recently, the Deep Planning Network (PlaNet) approach was introduced as a model-based reinforcement learning method that learns environment dynamics directly from pixel observations. This architecture is useful for learning tasks in which…
In this paper, we provide a fine-grain machine learning-based method, PerfNetV2, which improves the accuracy of our previous work for modeling the neural network performance on a variety of GPU accelerators. Given an application, the…
The European FP7 project DIANA has performed a coherent analysis of a large set of observations from protoplanetary disks by means of thermo-chemical disk models. The collected data include extinction-corrected stellar UV and X-ray input…
Exoplanet atmospheric modeling is advancing from chemically diverse one-dimensional (1D) models to three-dimensional (3D) global circulation models (GCMs), which are crucial for interpreting observations from facilities like the James Webb…
Deep learning with artificial neural networks is increasingly gaining attention, because of its potential for data-driven astronomy. However, this methodology usually does not provide uncertainties and does not deal with incompleteness and…
Machine learning has revolutionized many fields, including materials science. However, predicting properties of crystalline materials using machine learning faces challenges in input encoding, output versatility, and interpretability. We…
A growing planet embedded in a protoplanetary disk induces three-dimensional gas flow, which exhibits a midplane outflow that can suppress dust accretion onto the planet and form global dust substructures (rings and gaps). Because analytic…
We present DISK, a training-free adaptive inference method for autoregressive world models. DISK coordinates two coupled diffusion transformers for video and ego-trajectory via dual-branch controllers with cross-modal skip decisions,…
During the million years of evolution, gas dust and ice in protoplanetary disks can be chemically reprocessed. There are evidences that the gas-phase carbon and oxygen abundances are sub-solar in disks belonging to nearby star forming…
We present a deep learning approach to extract physical parameters (e.g., mobility, Schottky contact barrier height, defect profiles) of two-dimensional (2D) transistors from electrical measurements, enabling automated parameter extraction…