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 2024-04-18 11-01-22.png

 Transient Classifiers for Fink: Benchmarks for LSST

Fraga et al., 2024


The upcoming Legacy Survey of Space and Time (LSST) at the Vera Rubin Observatory is expected to detect a few million transients per night, which will generate a live alert stream during the entire 10 years of the survey. This will be distributed via community brokers whose task is to select subsets of the stream and direct them to scientific communities. Given the volume and complexity of data, machine learning (ML) algorithms will be paramount for this task. We present the infrastructure tests and classification methods developed within the {\sc Fink} broker in preparation for LSST. This work aims to provide detailed information regarding the underlying assumptions, and methods, behind each classifier, enabling users to make informed follow-up decisions from {\sc Fink} photometric classifications. Using simulated data from the Extended LSST Astronomical Time-series Classification Challenge (ELAsTiCC), we showcase the performance of binary and multi-class ML classifiers available in {\sc Fink}. These include tree-based classifiers coupled with tailored feature extraction strategies, as well as deep learning algorithms. We introduce the CBPF Alert Transient Search (CATS), a deep learning architecture specifically designed for this task. Results show that {\sc Fink} classifiers are able to handle the extra complexity which is expected from LSST data. CATS achieved 97% accuracy on a multi-class classification while our best performing binary classifier achieve 99% when classifying the Periodic class. ELAsTiCC was an important milestone in preparing {\sc Fink} infrastructure to deal with LSST-like data. Our results demonstrate that {\sc Fink} classifiers are well prepared for the arrival of the new stream; this experience also highlights that transitioning from current infrastructures to Rubin will require significant adaptation of currently available tools.

Screenshot from 2024-04-18 10-59-09.png

M-dwarf flares in the Zwicky Transient Facility data and what we can learn from them

Voloshina, Lavrukhina et al., 2024

In this paper, we explore the possibility of detecting M-dwarf flares using data from the Zwicky Transient Facility data releases (ZTF DRs). We employ two different approaches: the traditional method of parametric fit search and a machine learning algorithm originally developed for anomaly detection. We analyzed over 35 million ZTF light curves and visually scrutinized 1168 candidates suggested by the algorithms to filter out artifacts, occultations of a star by an asteroid, and known variable objects of other types. Our final sample comprises 134 flares with amplitude ranging from 0.2 to 4.6 magnitudes, including repeated flares and complex flares with multiple components. Using Pan-STARRS DR2 colors, we also assigned a corresponding spectral subclass to each object in the sample. For 13 flares with well-sampled light curves, we estimated the bolometric energy. Our results show that the ZTF's cadence strategy is suitable for identifying M-dwarf flares and other fast transients, allowing for the extraction of significant astrophysical information from their light curves.

bottom of page