Upgrade to PRO for Only $50/Year—Limited-Time Offer! 🔥
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Exoplanet Imaging Data Challenge
Search
Carlos Alberto Gomez Gonzalez
June 06, 2019
Science
2
350
Exoplanet Imaging Data Challenge
Talk @ Global Challenges Science Week, Grenoble, France.
Carlos Alberto Gomez Gonzalez
June 06, 2019
Tweet
Share
More Decks by Carlos Alberto Gomez Gonzalez
See All by Carlos Alberto Gomez Gonzalez
DL4DS - Deep Learning for empirical DownScaling
carlosgog
0
97
Deep learning-based super-resolution for downscaling climate data
carlosgog
0
79
Learning to simulate precipitation with supervised and generative learning models
carlosgog
0
150
Identification of Wastewater CH4 Emission Sources with Computer Vision and Sentinel-2 Observations
carlosgog
0
220
Learning to simulate precipitation with Deep Neural Networks
carlosgog
0
250
A data scientist’s guide to direct imaging of exoplanets
carlosgog
0
420
A la caza de exoplanetas por imagen directa con Python: De la ciencia de datos, la exoplanetología y otros demonios
carlosgog
0
230
Exoplanet direct imaging meets data science
carlosgog
0
430
Image/data processing for direct imaging of exoplanets (PyAstro2018)
carlosgog
0
320
Other Decks in Science
See All in Science
機械学習 - DBSCAN
trycycle
PRO
0
1.4k
(2025) Balade en cyclotomie
mansuy
0
270
HajimetenoLT vol.17
hashimoto_kei
1
110
あなたに水耕栽培を愛していないとは言わせない
mutsumix
1
140
academist Prize 4期生 研究トーク延長戦!「美は世界を救う」っていうけど、どうやって?
jimpe_hitsuwari
0
450
なぜ21は素因数分解されないのか? - Shorのアルゴリズムの現在と壁
daimurat
0
210
Celebrate UTIG: Staff and Student Awards 2025
utig
0
370
ランサムウェア対策にも考慮したVMware、Hyper-V、Azure、AWS間のリアルタイムレプリケーション「Zerto」を徹底解説
climbteam
0
180
データベース10: 拡張実体関連モデル
trycycle
PRO
0
1k
研究って何だっけ / What is Research?
ks91
PRO
2
160
白金鉱業Vol.21【初学者向け発表枠】身近な例から学ぶ数理最適化の基礎 / Learning the Basics of Mathematical Optimization Through Everyday Examples
brainpadpr
1
440
機械学習 - 決定木からはじめる機械学習
trycycle
PRO
0
1.2k
Featured
See All Featured
How to Ace a Technical Interview
jacobian
280
24k
Being A Developer After 40
akosma
91
590k
ReactJS: Keep Simple. Everything can be a component!
pedronauck
666
130k
Documentation Writing (for coders)
carmenintech
76
5.2k
For a Future-Friendly Web
brad_frost
180
10k
The Cost Of JavaScript in 2023
addyosmani
55
9.3k
Rails Girls Zürich Keynote
gr2m
95
14k
Optimizing for Happiness
mojombo
379
70k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
254
22k
Embracing the Ebb and Flow
colly
88
4.9k
Build your cross-platform service in a week with App Engine
jlugia
234
18k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
PRO
196
70k
Transcript
Exoplanet Imaging Data Challenge Carlos Alberto Gomez Gonzalez Global Challenges
Science Week. June3, 2019
{insert research topic here} Data Challenge Carlos Alberto Gomez Gonzalez
Global Challenges Science Week. June3, 2019
Exoplanet Imaging Data Challenge Planet: a celestial body moving in
an elliptical orbit round the Sun
Exo from extrasolar (outside of the Solar System)
Exoplanet Imaging Data Challenge
Data challenges • Problem to solve • Benchmark data •
Metrics • Platform for hosting the competition • Motivate people to participate (*)
Credit: Martin Vargic
Credit: NASA, http://planetquest.jpl.nasa.gov High-contrast imaging Lighthouse -> Star Firefly ->
exoplanet
Credit: NASA, http://planetquest.jpl.nasa.gov High-contrast imaging Lighthouse -> Star Firefly ->
exoplanet
Credit: NASA, http://planetquest.jpl.nasa.gov High-contrast imaging Lighthouse -> Star Firefly ->
exoplanet Stars never shut off !!!
Debris disk Beta Pictoris (occulted)
Yep, this is the exoplanet (Beta Pictoris b)
4k confirmed exoplanets but only ~1% observed!
HR8799, Marois et al. 2010 20 AU 0.5” Konopacky et
al. 2013 Bowler 2016 Milli et al. 2016
Multi-dimensional arrays ( ) exoplanet t, λ, x, y 3D
4D
Fake planet (low contrast) Signal and noise
spatially rescaled images t0 t0 with an integral field spectrograph
Signal and noise
Image processing pipeline Getting rid of the noise…
Algorithms 2006 - 2019 • Median frame subtraction • Pairwise
subtraction (GRAPHIC) • Least squares image combination (LOCI) • Low-rank approximations (PCA, NMF) • Low-rank plus sparse decompositions (LLSG) • MLE & Matched filtering (ANDROMEDA, KLIP-FM) • Supervised detection with deep neural networks (SODINN)
None
None
Data • Lack of benchmark data in the HCI community
• Requested datasets from the most important HCI instruments on Earth • Heterogeneous in terms of quality and characteristics • Synthetic companions were injected
None
Submissions
Blob counting
Metrics
None
Exercise of Openness
Thank you carlgogo.github.io/ github.com/carlgogo/ speakerdeck.com/carlgogo/ linkedin.com/in/carlgogo/