{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T06:56:10Z","timestamp":1790751370248,"version":"4.1.0"},"reference-count":56,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100014181","name":"Junta de Extremadura","doi-asserted-by":"publisher","award":["GR24029"],"award-info":[{"award-number":["GR24029"]}],"id":[{"id":"10.13039\/501100014181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014181","name":"Junta de Extremadura","doi-asserted-by":"publisher","award":["GR24170"],"award-info":[{"award-number":["GR24170"]}],"id":[{"id":"10.13039\/501100014181","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"\n Satellite retrieval of chlorophyll-a (Chl-a) is central to monitoring eutrophication in inland reservoirs, yet the atmospheric-correction processors it depends on, trained on oceanic and large-lake conditions, are systematically biased over small water bodies. A data-driven post-correction layer is increasingly used to reduce this bias; for such a layer over the joint output of the C2-Net processors (C2RCC, C2X, and C2XC), we ask which engineered features robustly carry the corrective signal rather than chasing an accuracy headline. Enumerating all 2\n 17<\/jats:sup>\n \u22121 = 131, 071 subsets of a symmetric 17-feature pool exposes a broad performance plateau on which three mainstream heuristics pick inequivalent \u201cbest\u201d subsets at near-identical error, so any single optimum is an artifact of selection on the cross-validated statistic. Stability selection instead isolates a small robust core (led by\n \n \n \n \n |<\/mml:mo>\n C<\/mml:mtext>\n 2<\/mml:mn>\n X<\/mml:mtext>\n \n \n C<\/mml:mtext>\n <\/mml:mrow>\n \n r<\/mml:mi>\n <\/mml:mrow>\n <\/mml:msub>\n |<\/mml:mo>\n <\/mml:mrow>\n <\/mml:msqrt>\n <\/mml:math>\n <\/jats:inline-formula>\n , chosen in 98% of subsamples at\n k<\/jats:italic>\n = 6), the transformations that dominate the lowest-error subset being selected near chance. On 252 satellite\u2013\n in-situ<\/jats:italic>\n pairs from five Guadiana-Basin reservoirs (Spain), the correction improves pooled RMSE over raw C2RCC modestly but, for the Huber model, significantly (~10\u201316%,\n p<\/jats:italic>\n = 0.047 under a cross-validation-corrected test), with the three estimators statistically indistinguishable from one another; under Leave-One-Reservoir-Out validation the degradation runs from ~15% (pooled) to ~34% (per-reservoir mean), both within the wide bootstrap intervals and thus approximate rather than precise. We distill a compact reporting template: an RMSE-vs.-\n k<\/jats:italic>\n curve with variance bands, stability selection in place of a single \u201cbest\u201d subset, a relative-error metric (MdAPE) alongside RMSE, and LORO as a minimum transferability check. All code, data, and models are released openly.\n <\/jats:p>","DOI":"10.3389\/frai.2026.1947948","type":"journal-article","created":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T06:05:04Z","timestamp":1790748304000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Exhaustive feature-subset search for data-driven post-correction of satellite atmospheric processors: a case study on chlorophyll-a retrieval in inland reservoirs"],"prefix":"10.3389","volume":"9","author":[{"given":"Victoria","family":"Amores-Chaparro","sequence":"first","affiliation":[{"name":"Department of Computer Systems and Telematics Engineering, School of Technology, Universidad de Extremadura","place":["C\u00e1ceres, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fernando","family":"Broncano","sequence":"additional","affiliation":[{"name":"Department of Computer Systems and Telematics Engineering, School of Industrial Engineering, Universidad de Extremadura","place":["Badajoz, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jes\u00fas A.","family":"Torrecilla-Pinero","sequence":"additional","affiliation":[{"name":"Department of Construction, School of Technology, Universidad de Extremadura","place":["C\u00e1ceres, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aurora","family":"Cuartero","sequence":"additional","affiliation":[{"name":"Department of Graphical Expression, School of Technology, Universidad de Extremadura","place":["C\u00e1ceres, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,30]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"101114","DOI":"10.1016\/j.envc.2025.101114","article-title":"Optimizing empirical and hybrid modeling for advanced canopy chlorophyll and nitrogen retrieval technique using EnMAP data","volume":"18","author":"Alam","year":"2025","journal-title":"Environ. Chall"},{"key":"B2","doi-asserted-by":"publisher","first-page":"101601","DOI":"10.1016\/j.atech.2025.101601","article-title":"Dimensionality optimized machine learning retrieval of canopy chlorophyll, nitrogen, and phosphorus from Google satellite embeddings","volume":"12","author":"Alam","year":"2025","journal-title":"Smart Agric. Technol"},{"key":"B3","doi-asserted-by":"publisher","first-page":"7672","DOI":"10.1007\/s11263-025-02518-z","article-title":"Analysing satellite imagery classification under spatial domain shift across geographic regions","volume":"133","author":"Al-Emadi","year":"2025","journal-title":"Int. J. Comput. Vis"},{"key":"B4","doi-asserted-by":"publisher","first-page":"7","DOI":"10.3390\/engproc2026123007","article-title":"Monitoring water quality in small reservoirs using Sentinel-2 imagery and machine learning","volume":"123","author":"Amores-Chaparro","year":"2026","journal-title":"Eng. Proc"},{"key":"B5","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1561\/9781638281597","article-title":"Conformal prediction: a gentle introduction","volume":"16","author":"Angelopoulos","year":"2023","journal-title":"Found. Trends Mach. Learn"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1734","DOI":"10.3390\/rs17101734","article-title":"Retrieving inland water quality parameters via satellite remote sensing: sensor evaluation, atmospheric correction, and machine learning approaches","volume":"17","author":"Ansari","year":"2025","journal-title":"Remote Sens"},{"key":"B7","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn"},{"key":"B8","first-page":"54","article-title":"\u201cEvolution of the C2RCC neural network for Sentinel 2 and 3 for the retrieval of ocean colour products in normal and extreme optically complex waters,\u201d","volume-title":"Living Planet Symposium, Vol. 740","author":"Brockmann","year":"2016"},{"key":"B9","doi-asserted-by":"publisher","first-page":"18769","DOI":"10.1109\/JSTARS.2024.3476970","article-title":"Finding optimal spatial window: the influence of size on remote-sensing-based chl-a prediction in small reservoirs","volume":"17","author":"C\u00e1ceres-Merino","year":"2024","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens"},{"key":"B10","doi-asserted-by":"publisher","first-page":"101021","DOI":"10.1016\/j.rsase.2023.101021","article-title":"An application of C2-Net atmospheric corrections for chlorophyll-a estimation in small reservoirs","volume":"32","author":"Cuartero","year":"2023","journal-title":"Remote Sens. Appl"},{"key":"B11","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1139\/f82-108","article-title":"The deep chlorophyll maximum: comparing vertical profiles of chlorophyll a","volume":"39","author":"Cullen","year":"1982","journal-title":"Can. J. Fish. Aquat. Sci"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2794122","DOI":"10.1155\/atr\/2794122","article-title":"AutoML-enhanced delay forecasting with SHAP interpretability in highway work zones under diversion constraints","volume":"2026","author":"Dai","year":"2026","journal-title":"J. Adv. Transp"},{"key":"B13","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1080\/01431160600821127","article-title":"The MERIS Case 2 water algorithm","volume":"28","author":"Doerffer","year":"2007","journal-title":"Int. J. Remote Sens"},{"key":"B14","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.rse.2011.11.026","article-title":"Sentinel-2: ESA's optical high-resolution mission for GMES operational services","volume":"120","author":"Drusch","year":"2012","journal-title":"Remote Sens. Environ"},{"key":"B15","volume-title":"Directive 2000\/60\/EC of the European Parliament and of the Council Establishing a Framework for Community Action in the Field of Water Policy","year":"2000"},{"key":"B16","first-page":"2755","article-title":"\u201cEfficient and robust automated machine learning,\u201d","volume-title":"Advances in neural information processing systems","author":"Feurer","year":"2015"},{"key":"B17","doi-asserted-by":"publisher","first-page":"112213","DOI":"10.1016\/j.ress.2026.112213","article-title":"From physics to machine learning and back: part I-learning with inductive biases in prognostics and health management (PHM)","volume":"271","author":"Fink","year":"2026","journal-title":"Reliab. Eng. Syst. Saf"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1162\/153244303322753616","article-title":"An introduction to variable and feature selection","volume":"3","author":"Guyon","year":"2003","journal-title":"J. Mach. Learn. Res"},{"key":"B19","doi-asserted-by":"publisher","first-page":"e2025G","DOI":"10.1029\/2025GL120062","article-title":"Observation-informed machine learning convective scheme: a new training strategy","volume":"53","author":"Huang","year":"2026","journal-title":"Geophys. Res. Lett"},{"key":"B20","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1214\/aoms\/1177703732","article-title":"Robust estimation of a location parameter","volume":"35","author":"Huber","year":"1964","journal-title":"Ann. Math. Stat"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5","author":"Hutter","year":"2019","journal-title":"Automated Machine Learning: Methods, Systems, Challenges"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1718","DOI":"10.3390\/w17111718","article-title":"Deep learning-based retrieval of chlorophyll-a in lakes using sentinel-1 and sentinel-2 satellite imagery","volume":"17","author":"Jeong","year":"2025","journal-title":"Water"},{"key":"B23","doi-asserted-by":"publisher","first-page":"114536","DOI":"10.1016\/j.ecolind.2025.114536","article-title":"A regional framework for spatio-temporal assessment of lake eutrophication using sentinel-2\/MSI imagery","volume":"182","author":"Joffre","year":"2026","journal-title":"Ecol. Indic"},{"key":"B24","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-94-007-7814-6_2","article-title":"\u201cEutrophication: global scenario and local threat to dynamics of aquatic ecosystems,\u201d","author":"Khan","year":"2014","journal-title":"Eutrophication: Causes, Consequences and Control: Vol. 2"},{"key":"B25","doi-asserted-by":"publisher","first-page":"132148","DOI":"10.1016\/j.neucom.2025.132148","article-title":"A comprehensive review of traffic prediction: from traditional machine learning to autoML","volume":"666","author":"Khatiriolyaee","year":"2026","journal-title":"Neurocomputing"},{"key":"B26","doi-asserted-by":"publisher","first-page":"e70038","DOI":"10.1111\/1752-1688.70038","article-title":"Remote sensing of chlorophyll a and temperature to support algal bloom monitoring in Blue Mesa Reservoir, Colorado","volume":"61","author":"King","year":"2025","journal-title":"J. Am. Water Resour. Assoc"},{"key":"B27","doi-asserted-by":"publisher","first-page":"109324","DOI":"10.1016\/j.ijfatigue.2025.109324","article-title":"Discovery of fatigue strength models via feature engineering and automated explainable machine learning applied to the welded transverse stiffener","volume":"203","author":"Kraus","year":"2026","journal-title":"Int. J. Fatigue"},{"key":"B28","doi-asserted-by":"publisher","first-page":"3671","DOI":"10.3390\/s25123671","article-title":"A unified deep-domain adaptation framework: advancing feature separability and local alignment","volume":"25","author":"Kumar","year":"2025","journal-title":"Sensors"},{"key":"B29","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1111\/j.1467-9868.2010.00740.x","article-title":"Stability selection","volume":"72","author":"Meinshausen","year":"2010","journal-title":"J. R. Stat. Soc. Ser. B"},{"key":"B30","doi-asserted-by":"publisher","first-page":"998","DOI":"10.3390\/su17030998","article-title":"Integration of machine learning and remote sensing for water quality monitoring and prediction: a review","volume":"17","author":"Mohan","year":"2025","journal-title":"Sustainability"},{"key":"B31","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1023\/A:1024068626366","article-title":"Inference for the generalization error","volume":"52","author":"Nadeau","year":"2003","journal-title":"Mach. Learn"},{"key":"B32","doi-asserted-by":"publisher","first-page":"111704","DOI":"10.1016\/j.cie.2025.111704","article-title":"Fundamental flaws of physics-informed neural networks and explainability methods in engineering systems","volume":"212","author":"Naser","year":"2026","journal-title":"Comput. Ind. Eng"},{"key":"B33","doi-asserted-by":"publisher","first-page":"498","DOI":"10.3390\/w18040498","article-title":"Deep learning framework for atmospheric correction and chlorophyll-a estimation from landsat-8 images over the inland waters of northern vietnam","volume":"18","author":"Nguyen","year":"2026","journal-title":"Water"},{"key":"B34","doi-asserted-by":"publisher","first-page":"2381","DOI":"10.3390\/rs13122381","article-title":"Inter-comparison of methods for chlorophyll-a retrieval: sentinel-2 time-series analysis in italian lakes","volume":"13","author":"Niroumand-Jadidi","year":"2021","journal-title":"Remote Sens"},{"key":"B35","doi-asserted-by":"publisher","first-page":"104618","DOI":"10.1016\/j.tra.2025.104618","article-title":"Spatial transferability of pedestrian trip generation models","volume":"199","author":"Nourmohammadi","year":"2025","journal-title":"Transp. Res. A Policy Pract"},{"key":"B36","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1145\/2908812.2908918","article-title":"\u201cEvaluation of a tree-based pipeline optimization tool for automating data science,\u201d","author":"Olson","year":"2016","journal-title":"Proceedings of the genetic and evolutionary computation conference"},{"key":"B37","doi-asserted-by":"publisher","first-page":"111604","DOI":"10.1016\/j.rse.2019.111604","article-title":"Seamless retrievals of chlorophyll-a from Sentinel-2 (MSI) and Sentinel-3 (OLCI) in inland and coastal waters: a machine-learning approach","volume":"240","author":"Pahlevan","year":"2020","journal-title":"Remote Sens. Environ"},{"key":"B38","doi-asserted-by":"publisher","first-page":"270","DOI":"10.3390\/eng6100270","article-title":"A comparative assessment of regular and spatial cross-validation in subfield machine learning prediction of maize yield from sentinel-2 phenology","volume":"6","author":"Radocaj","year":"2025","journal-title":"Eng"},{"key":"B39","doi-asserted-by":"publisher","first-page":"105321","DOI":"10.1016\/j.jag.2026.105321","article-title":"A transferable deep learning framework for flood mapping: spatial generalization across hydro-climatic regimes using satellite imagery","volume":"149","author":"Ratte-Fortin","year":"2026","journal-title":"Int. J. Appl. Earth Observ. Geoinform"},{"key":"B40","doi-asserted-by":"publisher","first-page":"492","DOI":"10.2307\/1312927","article-title":"Remote sensing of algal bloom dynamics","volume":"46","author":"Richardson","year":"1996","journal-title":"Bioscience"},{"key":"B41","doi-asserted-by":"publisher","first-page":"106236","DOI":"10.1016\/j.ecolind.2020.106236","article-title":"Chlorophyll-a and total suspended solids retrieval and mapping using Sentinel-2A and machine learning for inland waters","volume":"113","author":"Saberioon","year":"2020","journal-title":"Ecol. Indic"},{"key":"B42","doi-asserted-by":"publisher","first-page":"24824","DOI":"10.4995\/raet.2026.24824","article-title":"Comparison of ACOLITE and c2RCC automated products for chlorophyll-a estimation in high-andean lakes using sentinel-2","volume":"67","author":"Sanchez-Perez","year":"2026","journal-title":"Rev. Teledeteccion"},{"key":"B43","doi-asserted-by":"publisher","first-page":"1870","DOI":"10.3390\/rs16111870","article-title":"Chlorophyll-a estimation in 149 tropical semi-arid reservoirs using remote sensing data and six machine learning methods","volume":"16","author":"Santos","year":"2024","journal-title":"Remote Sens"},{"key":"B44","doi-asserted-by":"publisher","first-page":"112848","DOI":"10.1016\/j.rse.2021.112848","article-title":"An ensemble neural network atmospheric correction for Sentinel-3 OLCI over coastal waters providing inherent model uncertainty estimation and sensor noise propagation","volume":"270","author":"Schroeder","year":"2022","journal-title":"Remote Sens. Environ"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1124","DOI":"10.3390\/rs14051124","article-title":"Towards the combination of C2RCC processors for improving water quality retrieval in inland and coastal areas","volume":"14","author":"Soriano-Gonz\u00e1lez","year":"2022","journal-title":"Remote Sens"},{"key":"B46","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/s10750-018-3741-6","article-title":"Remote sensing application for the study of rapid flushing to remediate eutrophication in shallow lagoons (albufera of valencia)","volume":"829","author":"S\u00f2ria-Perpiny\u00e0","year":"2019","journal-title":"Hydrobiologia"},{"key":"B47","doi-asserted-by":"publisher","first-page":"105415","DOI":"10.1016\/j.jag.2026.105415","article-title":"Machine learning correction of c2-net for chlorophyll-a retrieval in optically complex small reservoirs","volume":"152","author":"Torrecilla-Pinero","year":"2026","journal-title":"Int. J. Appl. Earth Observ. Geoinform"},{"key":"B48","doi-asserted-by":"publisher","first-page":"1570827","DOI":"10.3389\/frsen.2025.1570827","article-title":"Combination of neural network models for estimating Chlorophyll-a over turbid and clear waters (CONNECT)","volume":"6","author":"Tran","year":"2025","journal-title":"Front. Remote Sens"},{"key":"B49","doi-asserted-by":"publisher","first-page":"112284","DOI":"10.1016\/j.rse.2021.112284","article-title":"Atmospheric correction of sentinel-3\/OLCI data for mapping of suspended particulate matter and chlorophyll-a concentration in belgian turbid coastal waters","volume":"256","author":"Vanhellemont","year":"2021","journal-title":"Remote Sens. Environ"},{"key":"B50","volume-title":"Eutrophication of Waters: Monitoring, Assessment and Control","author":"Vollenweider","year":"1982"},{"key":"B51","doi-asserted-by":"publisher","first-page":"108737","DOI":"10.1016\/j.ecolind.2022.108737","article-title":"Validity evaluation of a machine-learning model for chlorophyll a retrieval using Sentinel-2 from inland and coastal waters","volume":"137","author":"Wang","year":"2022","journal-title":"Ecol. Indic"},{"key":"B52","doi-asserted-by":"publisher","first-page":"10672","DOI":"10.1109\/JSTARS.2026.3674122","article-title":"Dual-consistency input-space domain adaptation for remote sensing image semantic segmentation via SSC-cycleGAN","volume":"19","author":"Wang","year":"2026","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens"},{"key":"B53","doi-asserted-by":"publisher","first-page":"3226","DOI":"10.3390\/rs17183226","article-title":"Bias correction of SMAP l2 sea surface salinity based on physics-informed neural network","volume":"17","author":"Wu","year":"2025","journal-title":"Remote Sens"},{"key":"B54","doi-asserted-by":"publisher","first-page":"113738","DOI":"10.1016\/j.ecolind.2025.113738","article-title":"Advanced classification of optical water types and ensemble learning models for Chl-a inversion in Dongting and Poyang lakes using Sentinel-2 remote sensing: assessing the impact of extreme drought events","volume":"177","author":"Xiong","year":"2025","journal-title":"Ecol. Indic"},{"key":"B55","doi-asserted-by":"publisher","first-page":"4194","DOI":"10.3390\/app16094194","article-title":"Knowledge-guided multi-source time-series approach for spatially robust crop type classification","volume":"16","author":"Xu","year":"2026","journal-title":"Appl. Sci"},{"key":"B56","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1016\/j.isprsjprs.2023.09.011","article-title":"Monitoring inland water via Sentinel satellite constellation: a review and perspective","volume":"204","author":"Zeng","year":"2023","journal-title":"ISPRS J. Photogram. Remote Sens"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1947948\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T06:05:06Z","timestamp":1790748306000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1947948\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,30]]},"references-count":56,"alternative-id":["10.3389\/frai.2026.1947948"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1947948","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,30]]},"article-number":"1947948"}}