{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T13:38:04Z","timestamp":1770989884619,"version":"3.50.1"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T00:00:00Z","timestamp":1770940800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>The observation of the lunar crescent is significant in astronomy, cultural traditions, and religious lunar calendar determinations. However, earth-based imaging that captures all lunar phases, particularly the new crescent across multiple months, remains limited. This study explores the feasibility of using artificial intelligence (AI) techniques to detect and analyze the birth of the new lunar crescent using space-borne imagery from NASA\u2019s Lunar Reconnaissance Orbiter (LRO), spanning over 13 years.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study evaluates both deep learning and traditional machine learning approaches for new crescent detection. Convolutional Neural Networks (CNN), Random Forests (RF), and Support Vector Machines (SVM) were applied to orbital lunar images. A custom image preprocessing pipeline was implemented, including grayscale conversion, contrast-limited adaptive histogram equalization, and noise reduction. The CNN architecture was further enhanced by integrating lunar imagery with moon age data. Experiments were conducted using a temporally split dataset to simulate real-world conditions. Model robustness was also evaluated using synthetically generated noise and occlusion.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The experimental results demonstrated high performance across all evaluated models, achieving precision, recall, F-score, and overall accuracy of approximately 98%. Among the tested approaches, RF and CNN models produced the best overall performance, outperforming SVM. The CNN model showed strong robustness under degraded image conditions, maintaining high accuracy when subjected to Gaussian noise and image occlusions of up to 50%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The findings indicate that AI-based techniques, particularly CNN and RF models, are effective for detecting the new lunar crescent from orbital imagery. The robustness of the CNN model suggests practical applicability in real-world lunar observation scenarios. This study contributes toward supporting traditional crescent identification methods and offers potential solutions for reducing calendar discrepancies across different regions.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1727824","type":"journal-article","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T12:32:33Z","timestamp":1770985953000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An AI approach to lunar phase detection: enhancing the identification of the new crescent with astronomical data integration"],"prefix":"10.3389","volume":"9","author":[{"given":"Murad","family":"Al-Rajab","sequence":"first","affiliation":[{"name":"College of Engineering, Abu Dhabi University","place":["Abu Dhabi, United Arab Emirates"]}]},{"given":"Samia","family":"Loucif","sequence":"additional","affiliation":[{"name":"College of Technological Innovation, Zayed University","place":["Abu Dhabi, United Arab Emirates"]}]},{"given":"Raed Abu","family":"Zitar","sequence":"additional","affiliation":[{"name":"College of Engineering and Computing, Liwa University","place":["Abu Dhabi, United Arab Emirates"]}]},{"given":"Mubarak Gwaza","family":"Abdu-Aguye","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence","place":["Abu Dhabi, United Arab Emirates"]}]}],"member":"1965","published-online":{"date-parts":[[2026,2,13]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1016\/j.compbiomed.2017.08.022","article-title":"A deep convolutional neural network model to classify heartbeats","volume":"89","author":"Acharya","year":"2017","journal-title":"Comput. Biol. Med."},{"key":"ref2","first-page":"203","volume-title":"Enhancement of daytime crescent image using wiener filter-based de-blurring technique, 7th international conference on contemporary information technology and mathematics (ICCITM)","author":"Ali","year":"2021"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"6674","DOI":"10.1038\/s41598-023-32807-x","article-title":"Predicting new crescent moon visibility applying machine learning algorithm","volume":"13","author":"Al-Rajab","year":"2023","journal-title":"Sci. Rep."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1016\/0083-6656(77)90021-6","article-title":"The first visibility of the lunar crescent","volume":"21","author":"Bruin","year":"1977","journal-title":"Vistas Astron."},{"key":"ref5","volume-title":"L'Astronomie","author":"Danjon","year":"1932"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"115970","DOI":"10.1016\/j.icarus.2024.115970","article-title":"Assessment and review of modern lunar crescent visibility criterion","volume":"412","author":"Faid","year":"2024","journal-title":"Icarus"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/s11038-014-9449-3","article-title":"Lunar crescent detection based on image processing algorithms","volume":"114","author":"Fakhar","year":"2014","journal-title":"Earth Moon Planets"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1177\/002182868801900102","article-title":"Three islamic lunar crescent visibility tables","volume":"19","author":"Hogendijk","year":"1988","journal-title":"J. Hist. Astron."},{"key":"ref9","first-page":"3","article-title":"Enhancing moon crescent visibility using contrast-limited adaptive histogram equalization and bilateral filtering techniques","volume":"22","author":"Jawahir","year":"2022","journal-title":"J. Telecommun. Inf. Technol."},{"key":"ref10","article-title":"A convolutional neural network for modeling sentences","author":"Kalchbrenner","year":"2014","journal-title":"arXiv preprint arXiv:1404.2188"},{"key":"ref11","volume-title":"Fundamentals of machine learning for predictive data analytics: Algorithms, worked examples, and case studies","author":"Kelleher","year":"2020"},{"key":"ref12","volume-title":"Imagenet classification with deep convolutional neural networks, advances in neural information processing systems, 25","author":"Krizhevsky","year":"2012"},{"key":"ref13","first-page":"1","article-title":"Fixing weight decay regularization in Adam","volume":"5","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv:1711.05101"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1186\/s40537-024-00979-6","article-title":"Toward a globally lunar calendar: a machine learning-driven approach for crescent moon visibility prediction","volume":"11","author":"Loucif","year":"2024","journal-title":"J. Big Data"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"129","DOI":"10.12928\/telkomnika.v20i1.22338","article-title":"Machine learning models for moon phase detection: algorithm, prototype and performance comparison","volume":"20","author":"Moshayedi","year":"2022","journal-title":"Telkomnika Telecommun. Comput. Electron. Control"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"100757","DOI":"10.1016\/j.ascom.2023.100757","article-title":"Deep learning for crescent detection and recognition: implementation of mask r-cnn to the observational lunar dataset collected with the robotic lunar telescope system","volume":"45","author":"Muztaba","year":"2023","journal-title":"Astron. Comput."},{"key":"ref17","volume-title":"A selfconstruction of automatic crescent detection using haar-cascade classifier and support vector machine, journal of physics: Conference series, 2734","author":"Muztaba","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/s10686-005-9002-5","article-title":"New criterion for lunar crescent visibility","volume":"18","author":"Odeh","year":"2004","journal-title":"Exp. Astron."},{"key":"ref19","first-page":"582","volume-title":"Performance evaluation of texture measures with classification based on kullback discrimination of distributions, proceedings of 12th international conference on pattern recognition, 1","author":"Ojala","year":"1994"},{"key":"ref20","first-page":"276","article-title":"Bibliography","author":"Pingree","year":"2010","journal-title":"Encycl. Iranica"},{"key":"ref21","article-title":"Support vector machines","volume-title":"Thinking data science","author":"Sarang","year":"2023"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"1511","DOI":"10.1016\/j.ijleo.2015.09.158","article-title":"Evaluation of various digital image processing techniques for detecting critical crescent moon and introducing cmd\u2013a tool for critical crescent moon detection","volume":"127","author":"Sejzei","year":"2016","journal-title":"Optik"},{"key":"ref23","first-page":"53","article-title":"Predicting the visibility of the first crescent: predicting the visibility of the frst crescent","volume":"3","author":"Tafseer","year":"2020","journal-title":"KIET J Comput Inf Sci"},{"key":"ref24","volume-title":"Histograms of oriented s, computer science, mathematics","author":"Tomasi","year":"2015"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"100731","DOI":"10.1016\/j.ascom.2023.100731","article-title":"Young lunar crescent detection based on video data with computer vision techniques","volume":"44","author":"Utama","year":"2023","journal-title":"Astron. Comput."},{"key":"ref26","first-page":"195","article-title":"Predicting the first visibility of the lunar crescent","volume-title":"Astronomical algorithms","author":"van Gent","year":"1998"},{"key":"ref27","volume-title":"A method for predicting the first sighting of the new crescent moon","author":"Yallop","year":"1997"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/s13244-018-0639-9","article-title":"Convolutional neural networks: an overview and application in radiology","volume":"9","author":"Yamashita","year":"2018","journal-title":"Insights Imaging"},{"key":"ref29","author":"Zhong","year":"2020"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"100651","DOI":"10.1016\/j.ascom.2022.100651","article-title":"Detection of a new crescent moon using the maximally stable extremal regions (mser) technique","volume":"41","author":"Zulkeflee","year":"2022","journal-title":"Astron. Comput."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1727824\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T12:32:36Z","timestamp":1770985956000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1727824\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,13]]},"references-count":30,"alternative-id":["10.3389\/frai.2026.1727824"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1727824","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,13]]},"article-number":"1727824"}}