{"oa":1,"scopus_import":"1","month":"05","quality_controlled":"1","doi":"10.1103/physrevd.97.103515","year":"2018","publication":"Physical Review D","publication_identifier":{"issn":["2470-0010","2470-0029"]},"intvolume":"        97","external_id":{"arxiv":["1802.01212"]},"publication_status":"published","abstract":[{"text":"Weak lensing maps contain information beyond two-point statistics on small scales. Much recent work has tried to extract this information through a range of different observables or via nonlinear transformations of the lensing field. Here we train and apply a 2D convolutional neural network to simulated noiseless lensing maps covering 96 different cosmological models over a range of {Ωm,σ8}. Using the area of the confidence contour in the {Ωm,σ8} plane as a figure-of-merit, derived from simulated convergence maps smoothed on a scale of 1.0 arcmin, we show that the neural network yields ≈5× tighter constraints than the power spectrum, and ≈4× tighter than the lensing peaks. Such gains illustrate the extent to which weak lensing data encode cosmological information not accessible to the power spectrum or even other, non-Gaussian statistics such as lensing peaks.","lang":"eng"}],"article_processing_charge":"No","_id":"17662","extern":"1","volume":97,"title":"Non-Gaussian information from weak lensing data via deep learning","author":[{"last_name":"Gupta","full_name":"Gupta, Arushi","first_name":"Arushi"},{"full_name":"Matilla, José Manuel Zorrilla","first_name":"José Manuel Zorrilla","last_name":"Matilla"},{"full_name":"Hsu, Daniel","first_name":"Daniel","last_name":"Hsu"},{"full_name":"Haiman, Zoltán","first_name":"Zoltán","id":"7c006e8c-cc0d-11ee-8322-cb904ef76f36","last_name":"Haiman"}],"user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","date_created":"2024-09-06T07:39:50Z","main_file_link":[{"url":" https://doi.org/10.48550/arXiv.1802.01212","open_access":"1"}],"status":"public","day":"18","issue":"10","language":[{"iso":"eng"}],"article_type":"original","date_published":"2018-05-18T00:00:00Z","article_number":"103515","date_updated":"2024-09-25T07:28:42Z","oa_version":"Preprint","citation":{"mla":"Gupta, Arushi, et al. “Non-Gaussian Information from Weak Lensing Data via Deep Learning.” <i>Physical Review D</i>, vol. 97, no. 10, 103515, American Physical Society, 2018, doi:<a href=\"https://doi.org/10.1103/physrevd.97.103515\">10.1103/physrevd.97.103515</a>.","ista":"Gupta A, Matilla JMZ, Hsu D, Haiman Z. 2018. Non-Gaussian information from weak lensing data via deep learning. Physical Review D. 97(10), 103515.","ieee":"A. Gupta, J. M. Z. Matilla, D. Hsu, and Z. Haiman, “Non-Gaussian information from weak lensing data via deep learning,” <i>Physical Review D</i>, vol. 97, no. 10. American Physical Society, 2018.","ama":"Gupta A, Matilla JMZ, Hsu D, Haiman Z. Non-Gaussian information from weak lensing data via deep learning. <i>Physical Review D</i>. 2018;97(10). doi:<a href=\"https://doi.org/10.1103/physrevd.97.103515\">10.1103/physrevd.97.103515</a>","short":"A. Gupta, J.M.Z. Matilla, D. Hsu, Z. Haiman, Physical Review D 97 (2018).","chicago":"Gupta, Arushi, José Manuel Zorrilla Matilla, Daniel Hsu, and Zoltán Haiman. “Non-Gaussian Information from Weak Lensing Data via Deep Learning.” <i>Physical Review D</i>. American Physical Society, 2018. <a href=\"https://doi.org/10.1103/physrevd.97.103515\">https://doi.org/10.1103/physrevd.97.103515</a>.","apa":"Gupta, A., Matilla, J. M. Z., Hsu, D., &#38; Haiman, Z. (2018). Non-Gaussian information from weak lensing data via deep learning. <i>Physical Review D</i>. American Physical Society. <a href=\"https://doi.org/10.1103/physrevd.97.103515\">https://doi.org/10.1103/physrevd.97.103515</a>"},"publisher":"American Physical Society","type":"journal_article"}