{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T12:01:32Z","timestamp":1790942492091,"version":"4.1.0"},"reference-count":51,"publisher":"SAGE Publications","issue":"3","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"name":"The Ministry of Education Humanities and Social Science Projects","award":["25YJCZH140"],"award-info":[{"award-number":["25YJCZH140"]}]},{"name":"Science Research Project of Hebei Education Department","award":["QN2026184"],"award-info":[{"award-number":["QN2026184"]}]},{"name":"Langfang City Science and Technology Research and Development Program - Self-financed Project","award":["2025011032"],"award-info":[{"award-number":["2025011032"]}]},{"name":"The Fundamental Research Funds for the Central Universities","award":["ZY20250211"],"award-info":[{"award-number":["ZY20250211"]}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Science Progress"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:p>Leaf Area Index (LAI) estimation via remote sensing is critical for large-scale vegetation monitoring. To clarify feature utilization, model generalization, and deep-learning interpretability, this study designed two input schemes: \u201craw reflectance bands\u201d and \u201creflectance bands + vegetation indices (VIs)\u201d. We systematically compared LAI-estimation performance of two traditional machine-learning models, Random Forest (RF) and Light Gradient Boosting Machine (LightGBM), and two deep-learning models, Multilayer Perceptron (MLP) and Convolutional Neural Network (CNN). Taking CNN as a representative, we analysed how input-feature configurations shape internal feature-learning behavior via feature-correlation analysis, activation-weighted encoding-intensity quantification, and SHapley Additive exPlanations (SHAP) attribution analysis. The results reveal: 1) Using only raw bands, RF and LightGBM suffer severe overfitting without manual feature engineering, whereas MLP and CNN show good stability and relative robustness in this study. 2) The inclusion of VIs mitigates overfitting and improves the training stability of RF and LightGBM. In contrast, MLP and CNN maintain high robustness, demonstrating insensitivity to such feature variations on our dataset. 3) CNN internal feature representations are strongly shaped by input composition. When VIs are provided, internal features correlate strongly with these artificial features; when only raw reflectance is available, they anchor to spectral bands and show weak alignment with external VIs. Under raw-band-only input, the NIR band delivers the largest SHAP predictive contribution for LAI estimation, confirming the essential predictive role of NIR in this context. This study constructed a multi-perspective interpretability framework to disentangle CNN feature-learning behavior under different input settings. It clarifies model boundaries, generalization, and applicable scenarios, supporting model-and-feature selection for LAI estimation and deep-learning interpretability in remote-sensing applications.<\/jats:p>","DOI":"10.1177\/00368504261494045","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T08:57:18Z","timestamp":1790672238000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Physically interpretable feature learning and model robustness analysis for remote sensing LAI retrieval"],"prefix":"10.1177","volume":"109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9568-4913","authenticated-orcid":false,"given":"Yan","family":"Li","sequence":"first","affiliation":[{"name":"University of Emergency Management"},{"name":"Hebei Key Laboratory of Intelligent Prevention and Emergency Rescue for Deep Underground Engineering Disasters, Langfang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,9,29]]},"reference":[{"key":"e_1_3_5_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2022.109926"},{"key":"e_1_3_5_3_2","doi-asserted-by":"publisher","DOI":"10.1029\/2018RG000608"},{"key":"e_1_3_5_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2023.03.010"},{"key":"e_1_3_5_5_2","first-page":"2451","article-title":"Review of forest Leaf Area Index retrieval over rugged terrain based on remotely sensed data","volume":"26","author":"He M","year":"2024","unstructured":"He M, Wen J, You D, et al. Review of forest Leaf Area Index retrieval over rugged terrain based on remotely sensed data. Nat. Remote Sens. Bull 2024; 26: 2451\u20132472. https:\/\/doi.org\/10.11834\/jrs.20210244","journal-title":"Nat. Remote Sens. Bull"},{"key":"e_1_3_5_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11119-022-09893-4"},{"key":"e_1_3_5_7_2","doi-asserted-by":"publisher","DOI":"10.1002\/rse2.315"},{"key":"e_1_3_5_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.108165"},{"key":"e_1_3_5_9_2","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2023.1214801"},{"key":"e_1_3_5_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compscitech.2024.110947"},{"key":"e_1_3_5_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asr.2024.02.031"},{"key":"e_1_3_5_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.110947"},{"key":"e_1_3_5_13_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs16244725"},{"key":"e_1_3_5_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109790"},{"key":"e_1_3_5_15_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs14020331"},{"key":"e_1_3_5_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.04.006"},{"key":"e_1_3_5_17_2","first-page":"1","article-title":"Semi-supervised locality preserving dense graph neural network with ARMA filters and context-aware learning for hyperspectral image classification","volume":"60","author":"Ding Y","year":"2021","unstructured":"Ding Y, Zhao X, Zhang Z, et al. Semi-supervised locality preserving dense graph neural network with ARMA filters and context-aware learning for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens 2021; 60: 1\u201312. https:\/\/doi.org\/10.1109\/TGRS.2021.3100578","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"e_1_3_5_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130376"},{"key":"e_1_3_5_19_2","first-page":"104290","article-title":"SGDFuse: SAM-guided diffusion for high-fidelity infrared and visible image fusion","author":"Zhang X","year":"2025","unstructured":"Zhang X, Fan G, Ju Y, et al. SGDFuse: SAM-guided diffusion for high-fidelity infrared and visible image fusion. Information Fusion 2025: 104290. https:\/\/doi.org\/10.48550\/arXiv.2508.05264","journal-title":"Information Fusion"},{"key":"e_1_3_5_20_2","doi-asserted-by":"publisher","DOI":"10.1093\/plphys\/kiab322"},{"key":"e_1_3_5_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.fcr.2022.108452"},{"key":"e_1_3_5_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.107723"},{"key":"e_1_3_5_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.108421"},{"key":"e_1_3_5_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109758"},{"key":"e_1_3_5_25_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs12203304"},{"key":"e_1_3_5_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2014.08.003"},{"key":"e_1_3_5_27_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs12162595"},{"key":"e_1_3_5_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2015.11.016"},{"key":"e_1_3_5_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.fcr.2023.109016"},{"key":"e_1_3_5_30_2","first-page":"1","article-title":"A review of random forest-based feature selection methods for data science education and applications","volume":"20","author":"Iranzad R","year":"2024","unstructured":"Iranzad R, Liu X. A review of random forest-based feature selection methods for data science education and applications. Int. J. Data Sci. Anal 2024; 20: 1\u201315. https:\/\/doi.org\/10.1016\/j.fcr.2023.109016.","journal-title":"Int. J. Data Sci. Anal"},{"key":"e_1_3_5_31_2","doi-asserted-by":"publisher","DOI":"10.58496\/BJML\/2024\/007"},{"key":"e_1_3_5_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121530"},{"key":"e_1_3_5_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-023-01098-0"},{"key":"e_1_3_5_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.desal.2024.117849"},{"key":"e_1_3_5_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-023-10032-z"},{"key":"e_1_3_5_36_2","first-page":"482","article-title":"Enhancing maize LAI estimation accuracy using unmanned aerial vehicle remote sensing and deep learning techniques","volume":"15","author":"Chen Z","year":"2025","unstructured":"Chen Z, Zhai W, Chen Q. Enhancing maize LAI estimation accuracy using unmanned aerial vehicle remote sensing and deep learning techniques. Artif. Intell. Agric 2025; 15: 482\u2013495. https:\/\/doi.org\/10.1016\/j.aiia.2025.04.008","journal-title":"Artif. Intell. Agric"},{"key":"e_1_3_5_37_2","doi-asserted-by":"publisher","DOI":"10.1080\/17538947.2025.2497488"},{"key":"e_1_3_5_38_2","doi-asserted-by":"publisher","DOI":"10.1080\/10106040108542184"},{"key":"e_1_3_5_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.fcr.2008.11.004"},{"key":"e_1_3_5_40_2","doi-asserted-by":"publisher","DOI":"10.1006\/anbo.1997.0544"},{"key":"e_1_3_5_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0034-4257(01)00289-9"},{"key":"e_1_3_5_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/0034-4257(79)90013-0"},{"key":"e_1_3_5_43_2","first-page":"309","volume-title":"Third Earth Re-sources Technology Satellite\u20131 Symposium","author":"Rouse J","year":"1973","unstructured":"Rouse J, Haas R, Schell J, et al. Monitoring vegetation systems in the Great Plains with ERTS. In: Freden C, Becker M (eds). Third Earth Re-sources Technology Satellite\u20131 Symposium. National Aeronautics and Space Administration, 1973, vol 1, pp. 309\u2013317."},{"key":"e_1_3_5_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0034-4257(96)00072-7"},{"key":"e_1_3_5_45_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.agrformet.2009.03.016"},{"key":"e_1_3_5_46_2","doi-asserted-by":"publisher","DOI":"10.2307\/1936256"},{"key":"e_1_3_5_47_2","doi-asserted-by":"publisher","DOI":"10.1016\/0034-4257(94)00114-3"},{"key":"e_1_3_5_48_2","first-page":"1541","article-title":"Distinguishing vegetation from soil background information","volume":"43","author":"Richardson AJ","year":"1997","unstructured":"Richardson AJ, Wiegand CL. Distinguishing vegetation from soil background information. Photogramm Eng. Rem. S 1997; 43: 1541\u20131552. https:\/\/doi.org\/10.1109\/TGE.1977.294499","journal-title":"Photogramm Eng. Rem. S"},{"key":"e_1_3_5_49_2","doi-asserted-by":"publisher","DOI":"10.1016\/0034-4257(94)90134-1"},{"key":"e_1_3_5_50_2","doi-asserted-by":"publisher","DOI":"10.1080\/07038992.1996.10855178"},{"key":"e_1_3_5_51_2","doi-asserted-by":"publisher","DOI":"10.1016\/0034-4257(88)90106-X"},{"key":"e_1_3_5_52_2","unstructured":"Dw D. Measuring forage production of grazing units from Landsat MSS data. In: Proceedings of 10th international symposium on remote sensing of environment. October 6-10 1975."}],"container-title":["Science Progress"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/00368504261494045","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/00368504261494045","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/00368504261494045","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T11:49:11Z","timestamp":1790941751000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/00368504261494045"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":51,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1177\/00368504261494045"],"URL":"https:\/\/doi.org\/10.1177\/00368504261494045","relation":{},"ISSN":["0036-8504","2047-7163"],"issn-type":[{"value":"0036-8504","type":"print"},{"value":"2047-7163","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]},"article-number":"00368504261494045"}}