top of page

Emille E. O. Ishida, PhD

I am a Brazilian physicist based in France and  working in Astronomy and Cosmology since I can remember.  

My research is focused on machine learning applications to astronomy and in the development of sustainable interdisciplinary scientific environments.

I am co-founder of the Cosmostatistics Initiative (COIN), 

the Fink broker and the SNAD team. 

Main scientific activities

An adaptable LSST community broker based on machine learning
The Cosmostatistics Initiative
SuperNova Anomaly Detection


Screenshot from 2024-02-08 08-33-54.png

Multi-View Symbolic Regression

Russeil et al., 2024

Symbolic regression (SR) searches for analytical expressions representing the relationship between a set of explanatory and response variables. Current SR methods assume a single dataset extracted from a single experiment. Nevertheless, frequently, the researcher is confronted with multiple sets of results obtained from experiments conducted with different set-ups. Traditional SR methods may fail to find the underlying expression since the parameters of each experiment can be different. In this work we present Multi-View Symbolic Regression (MvSR), which takes into account multiple datasets simultaneously, mimicking experimental environments, and outputs a general parametric solution. This approach fits the evaluated expression to each independent dataset and returns  a parametric family of functions 𝑓 (𝑥; 𝜃 ) simultaneously capable of accurately fitting all datasets. We demonstrate the effectiveness of MvSR using data generated from known expressions, as well as real-world data from astronomy, chemistry and economy, for which an a priori analytical expression is not available. Results show that MvSR obtains the correct expression more frequently and is robust to hyperparameters change. In real-world data, it is able to grasp the group behavior, recovering known expressions from the literature as well as promising alternatives, thus enabling the use SR to a large range of experimental scenarios.

Screenshot from 2024-02-08 08-30-19.png

The 2022–2023 accretion outburst of the young star V1741 Sgr

Kuhn et al., 2024

V1741 Sgr (= SPICY 71482/Gaia22dtk) is a Classical T Tauri star on the outskirts of the Lagoon Nebula. After at least a decade of stability, in mid-2022, the optical source brightened by ∼3 mag over two months, remained bright until early 2023, then dimmed erratically over the next four months. This event was monitored with optical and infrared spectroscopy and photometry. Spectra from the peak (October 2022) indicate an EX Lup-type (EXor) accretion outburst, with strong emission from H i, He i, and Ca ii lines and CO bands. At this stage, spectroscopic absorption features indicated a temperature of 𝑇 ∼ 4750 K with low-gravity lines (e.g., Ba ii and Sr ii). By April 2023, with the outburst beginning to dim, strong TiO absorption appeared,
indicating a cooler 𝑇 ∼ 3600 K temperature. However, once the source had returned to its pre-outburst flux in August 2023, the TiO absorption and the CO emission disappeared. When the star went into outburst, the source’s spectral energy distribution became flatter, leading to bluer colours at wavelengths shorter than ∼1.6 μm and redder colours at longer wavelengths. The brightening requires a continuum emitting area larger than the stellar surface, likely from optically thick circumstellar gas with cooler surface layers producing the absorption features. Additional contributions to the outburst spectrum may include blue excess from hotspots on the stellar surface, emission lines from diffuse gas, and reprocessed emission from the dust disc. Cooling
of the circumstellar gas would explain the appearance of TiO, which subsequently disappeared once this gas had faded and the stellar spectrum reemerged.

bottom of page