Active learning with RESSPECT: Resource allocation for extragalactic astronomical transients
| Autor: | Kennamer, Noble, Galbany González, Lluis, LSST Dark Energy Science Collaboration, COIN Collaboration |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: | |
| Zdroj: | Digibug. Repositorio Institucional de la Universidad de Granada instname |
| Popis: | The authors would like to thank David Kirkby and Connor Sheere for insightful discussions. This work is part of the Recommendation System for Spectroscopic Followup (RESSPECT) project, governed by an inter-collaboration agreement signed between the Cosmostatistics Initiative (COIN) and the LSST Dark Energy Science Collaboration (DESC). This research is supported in part by the HPI Research Center in Machine Learning and Data Science at UC Irvine. EEOI and SS acknowledge financial support from CNRS 2017 MOMENTUM grant under the project Active Learning for Large Scale Sky Surveys. SGG and AKM acknowledge support by FCT under Project CRISP PTDC/FIS-AST-31546/2017. This work was partly supported by the Hewlett Packard Enterprise Data Science Institute (HPE DSI) at the University of Houston. DOJ is supported by a Gordon and Betty Moore Foundation postdoctoral fellowship at the University of California, Santa Cruz. Support for this work was provided by NASA through the NASA Hubble Fellowship grant HF2-51462.001 awarded by the Space Telescope Science Institute, which is operated by the Association of Universities for Research in Astronomy, Inc., for NASA, under contract NAS5-26555. BQ is supported by the International Gemini Observatory, a program of NSF's NOIRLab, which is managed by the Association of Universities for Research in Astronomy (AURA) under a cooperative agreement with the National Science Foundation, on behalf of the Gemini partnership of Argentina, Brazil, Canada, Chile, the Republic of Korea, and the United States of America. AIM acknowledges support from the Max Planck Society and the Alexander von Humboldt Foundation in the framework of the Max Planck-Humboldt Research Award endowed by the Federal Ministry of Education and Research. L.G. was funded by the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No. 839090. This work has been partially supported by the Spanish grant PGC2018-095317-B-C21 within the European Funds for Regional Development (FEDER). The recent increase in volume and complexity of available astronomical data has led to a wide use of supervised machine learning techniques. Active learning strategies have been proposed as an alternative to optimize the distribution of scarce labeling resources. However, due to the specific conditions in which labels can be acquired, fundamental assumptions, such as sample representativeness and labeling cost stability cannot be fulfilled. The Recommendation System for Spectroscopic followup (RESSPECT) project aims to enable the construction of optimized training samples for the Rubin Observatory Legacy Survey of Space and Time (LSST), taking into account a realistic description of the astronomical data environment. In this work, we test the robustness of active learning techniques in a realistic simulated astronomical data scenario. Our experiment takes into account the evolution of training and pool samples, different costs per object, and two different sources of budget. Results show that traditional active learning strategies significantly outperform random sampling. Nevertheless, more complex batch strategies are not able to significantly overcome simple uncertainty sampling techniques. Our findings illustrate three important points: 1) active learning strategies are a powerful tool to optimize the label-acquisition task in astronomy, 2) for upcoming large surveys like LSST, such techniques allow us to tailor the construction of the training sample for the first day of the survey, and 3) the peculiar data environment related to the detection of astronomical transients is a fertile ground that calls for the development of tailored machine learning algorithms. HPI Research Center in Machine Learning and Data Science at UC Irvine CNRS 2017 MOMENTUM grant under the project Active Learning for Large Scale Sky Surveys FCT under Project CRISP PTDC/FIS-AST-31546/2017 Hewlett Packard Enterprise Data Science Institute (HPE DSI) at the University of Houston Gordon and Betty Moore Foundation postdoctoral fellowship at the University of California, Santa Cruz Space Telescope Science Institute National Aeronautics & Space Administration (NASA) HF2-51462.001 NAS5-26555 International Gemini Observatory, a program of NSF's NOIRLab National Science Foundation (NSF) Max Planck Society Foundation CELLEX Alexander von Humboldt Foundation European Commission 839090 Spanish grant within the European Funds for Regional Development (FEDER) PGC2018-095317-B-C21 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|