{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T06:44:04Z","timestamp":1764225844446,"version":"build-2065373602"},"reference-count":48,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T00:00:00Z","timestamp":1672012800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42171335","22511102800"],"award-info":[{"award-number":["42171335","22511102800"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["42171335","22511102800"],"award-info":[{"award-number":["42171335","22511102800"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>It has been widely certified that hyperspectral images can be effectively used to monitor soil organic matter (SOM). Though numerous bands reveal more details in spectral features, information redundancy and noise interference also come accordingly. Due to the fact that, nowadays, prevailing dimensionality reduction methods targeted to hyperspectral images fail to make effective band selections, it is hard to capture the spectral features of ground objects quickly and accurately. In this paper, to solve the inefficiency and instability of hyperspectral feature selection, we proposed a feature selection framework named reinforcement learning for feature selection in hyperspectral regression (RLFSR). Specifically, the Markov Decision Process (MDP) was used to simulate the hyperspectral band selection process, and reinforcement learning agents were introduced to improve model performance. Then two spectral feature evaluation methods were introduced to find internal relationships between the hyperspectral features and thus comprehensively evaluate all hyperspectral bands aimed at the soil. The feature selection methods\u2014RLFSR-Net and RLFSR-Cv\u2014were based on pre-trained deep networks and cross-validation, respectively, and achieved excellent results on airborne hyperspectral images from Yitong Manchu Autonomous County in China. The feature subsets achieved the highest accuracy for most inversion models, with inversion R2 values of 0.7506 and 0.7518, respectively. The two proposed methods showed slight differences in spectral feature extraction preferences and hyperspectral feature selection flexibilities in deep reinforcement learning. The experiments showed that the proposed RLFSR framework could better capture the spectral characteristics of SOM than the existing methods.<\/jats:p>","DOI":"10.3390\/rs15010127","type":"journal-article","created":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T02:53:11Z","timestamp":1672109591000},"page":"127","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Hyperspectral Feature Selection for SOM Prediction Using Deep Reinforcement Learning and Multiple Subset Evaluation Strategies"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7821-2837","authenticated-orcid":false,"given":"Linya","family":"Zhao","sequence":"first","affiliation":[{"name":"Key Laboratory of Geographic Information Science (Ministry of Education), East China Normal University, Shanghai 200241, China"},{"name":"School of Geographic Sciences, East China Normal University, Shanghai 200241, China"},{"name":"Key Laboratory of Spatial-Temporal Big Data Analysis and Application of Natural Resources in Megacities (Ministry of Natural Resources), East China Normal University, Shanghai 200241, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6353-0146","authenticated-orcid":false,"given":"Kun","family":"Tan","sequence":"additional","affiliation":[{"name":"Key Laboratory of Geographic Information Science (Ministry of Education), East China Normal University, Shanghai 200241, China"},{"name":"School of Geographic Sciences, East China Normal University, Shanghai 200241, China"},{"name":"Key Laboratory of Spatial-Temporal Big Data Analysis and Application of Natural Resources in Megacities (Ministry of Natural Resources), East China Normal University, Shanghai 200241, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Geographic Information Science (Ministry of Education), East China Normal University, Shanghai 200241, China"},{"name":"School of Geographic Sciences, East China Normal University, Shanghai 200241, China"},{"name":"Key Laboratory of Spatial-Temporal Big Data Analysis and Application of Natural Resources in Megacities (Ministry of Natural Resources), East China Normal University, Shanghai 200241, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwei","family":"Ding","sequence":"additional","affiliation":[{"name":"The Second Surveying and Mapping Institute of Hebei, Shijiazhuang 050037, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoxian","family":"Liu","sequence":"additional","affiliation":[{"name":"The Second Surveying and Mapping Institute of Hebei, Shijiazhuang 050037, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huilin","family":"Ma","sequence":"additional","affiliation":[{"name":"The Second Surveying and Mapping Institute of Hebei, Shijiazhuang 050037, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Han","sequence":"additional","affiliation":[{"name":"Institute of Remote Sensing Satellite, China Academy of Space Technology, Beijing 100094, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,12,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.soilbio.2018.01.030","article-title":"Soil quality\u2013A critical review","volume":"120","author":"Bongiorno","year":"2018","journal-title":"Soil Biol. Biochem."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"123288","DOI":"10.1016\/j.jhazmat.2020.123288","article-title":"Estimating the distribution trend of soil heavy metals in mining area from HyMap airborne hyperspectral imagery based on ensemble learning","volume":"401","author":"Tan","year":"2021","journal-title":"J. Hazard. Mater."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"120987","DOI":"10.1016\/j.jhazmat.2019.120987","article-title":"Estimation of the spatial distribution of heavy metal in agricultural soils using airborne hyperspectral imaging and random forest","volume":"382","author":"Tan","year":"2020","journal-title":"J. Hazard. Mater."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Meng, X., Bao, Y., Ye, Q., Liu, H., Zhang, X., Tang, H., and Zhang, X. (2021). Soil organic matter prediction model with satellite hyperspectral image based on optimized denoising method. Remote Sens., 13.","DOI":"10.3390\/rs13122273"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Nanni, M.R., Dematt\u00ea, J.A.M., Rodrigues, M., Santos, G.L.A.A.d., Reis, A.S., Oliveira, K.M.d., Cezar, E., Furlanetto, R.H., Crusiol, L.G.T., and Sun, L. (2021). Mapping particle size and soil organic matter in tropical soil based on hyperspectral imaging and non-imaging sensors. Remote Sens., 13.","DOI":"10.3390\/rs13091782"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"114875","DOI":"10.1016\/j.geoderma.2020.114875","article-title":"Semi-supervised DNN regression on airborne hyperspectral imagery for improved spatial soil properties prediction","volume":"385","author":"Ou","year":"2021","journal-title":"Geoderma"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"211","DOI":"10.6029\/smartcr.2014.03.007","article-title":"Feature selection: A literature review","volume":"4","author":"Kumar","year":"2014","journal-title":"SmartCR"},{"key":"ref_8","first-page":"5132","article-title":"Feature selection algorithm for intrusions detection system using sequential forward search and random forest classifier","volume":"11","author":"Lee","year":"2017","journal-title":"KSII Trans. Internet Inf. Syst. (TIIS)"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Marcano-Cede\u00f1o, A., Quintanilla-Dom\u00ednguez, J., Cortina-Januchs, M., and Andina, D. (2010, January 7\u201310). Feature selection using sequential forward selection and classification applying artificial metaplasticity neural network. Proceedings of the IECON 2010-36th Annual Conference on IEEE Industrial Electronics Society, Glendale, AZ, USA.","DOI":"10.1109\/IECON.2010.5675075"},{"key":"ref_10","unstructured":"Ververidis, D., and Kotropoulos, C. (2005, January 4\u20138). Sequential forward feature selection with low computational cost. Proceedings of the 2005 13th European Signal Processing Conference, Antalya, Turkey."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1109\/TSMCB.2002.804363","article-title":"Orthogonal forward selection and backward elimination algorithms for feature subset selection","volume":"34","author":"Mao","year":"2004","journal-title":"IEEE Trans. Syst. Man Cybern. Part B Cybern."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1849","DOI":"10.1016\/S0165-1684(01)00064-0","article-title":"Backward sequential elimination for sparse vector subset selection","volume":"81","author":"Cotter","year":"2001","journal-title":"Signal Process."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"131","DOI":"10.3233\/IDA-1997-1302","article-title":"Feature selection for classification","volume":"1","author":"Dash","year":"1997","journal-title":"Intell. Data Anal."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"106036","DOI":"10.1016\/j.compag.2021.106036","article-title":"Sequential forward selection and support vector regression in comparison to LASSO regression for spring wheat yield prediction based on UAV imagery","volume":"183","author":"Shafiee","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"842","DOI":"10.1016\/j.ejor.2004.09.010","article-title":"Using simulated annealing to optimize the feature selection problem in marketing applications","volume":"171","author":"Meiri","year":"2006","journal-title":"Eur. J. Oper. Res."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1016\/j.eswa.2005.09.024","article-title":"A GA-based feature selection and parameters optimizationfor support vector machines","volume":"31","author":"Huang","year":"2006","journal-title":"Expert Syst. Appl."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1002\/widm.1106","article-title":"Evolutionary computation for feature selection in classification problems","volume":"3","year":"2013","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1656","DOI":"10.1109\/TSMCB.2012.2227469","article-title":"Particle swarm optimization for feature selection in classification: A multi-objective approach","volume":"43","author":"Xue","year":"2012","journal-title":"IEEE Trans. Cybern."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1016\/j.patrec.2006.09.003","article-title":"Feature selection based on rough sets and particle swarm optimization","volume":"28","author":"Wang","year":"2007","journal-title":"Pattern Recognit. Lett."},{"key":"ref_20","unstructured":"Zabinsky, Z.B. (2009). Random Search Algorithms, Department of Industrial and Systems Engineering, University of Washington."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/0004-3702(94)90084-1","article-title":"Learning boolean concepts in the presence of many irrelevant features","volume":"69","author":"Almuallim","year":"1994","journal-title":"Artif. Intell."},{"key":"ref_22","first-page":"773","article-title":"Pattern recognition and reduction of dimensionality","volume":"2","year":"1982","journal-title":"Handb. Stat."},{"key":"ref_23","unstructured":"Devijver, P.A., and Kittler, J. (1982). Pattern Recognition: A Statistical Approach, Prentice Hall."},{"key":"ref_24","unstructured":"Hall, M.A. (2000). Correlation-Based Feature Selection of Discrete and Numeric Class Machine Learning, University of Waikato."},{"key":"ref_25","unstructured":"Hall, M.A. (1999). Correlation-Based Feature Selection for Machine Learning. [Ph.D. Thesis, The University of Waikato]."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1016\/S0377-2217(02)00911-6","article-title":"Evaluating feature selection methods for learning in data mining applications","volume":"156","author":"Piramuthu","year":"2004","journal-title":"Eur. J. Oper. Res."},{"key":"ref_27","unstructured":"Liu, H., and Motoda, H. (2012). Feature Selection for Knowledge Discovery and Data Mining, Springer Science & Business Media."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"John, G.H., Kohavi, R., and Pfleger, K. (1994). Irrelevant features and the subset selection problem. Machine Learning Proceedings 1994, Elsevier.","DOI":"10.1016\/B978-1-55860-335-6.50023-4"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2158573","DOI":"10.1155\/2020\/2158573","article-title":"Predicting soil organic carbon content using hyperspectral remote sensing in a degraded mountain landscape in lesotho","volume":"2020","author":"Bangelesa","year":"2020","journal-title":"Appl. Environ. Soil Sci."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Song, Y.-Q., Zhao, X., Su, H.-Y., Li, B., Hu, Y.-M., and Cui, X.-S. (2018). Predicting spatial variations in soil nutrients with hyperspectral remote sensing at regional scale. Sensors, 18.","DOI":"10.3390\/s18093086"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Wei, L., Yuan, Z., Zhong, Y., Yang, L., Hu, X., and Zhang, Y. (2019). An improved gradient boosting regression tree estimation model for soil heavy metal (Arsenic) pollution monitoring using hyperspectral remote sensing. Appl. Sci., 9.","DOI":"10.3390\/app9091943"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Kawamura, K., Tsujimoto, Y., Nishigaki, T., Andriamananjara, A., Rabenarivo, M., Asai, H., Rakotoson, T., and Razafimbelo, T. (2019). Laboratory visible and near-infrared spectroscopy with genetic algorithm-based partial least squares regression for assessing the soil phosphorus content of upland and lowland rice fields in Madagascar. Remote Sens., 11.","DOI":"10.3390\/rs11050506"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Feng, J., Li, D., Chen, J., Zhang, X., Tang, X., and Wu, X. (August, January 28). Hyperspectral band selection based on ternary weight convolutional neural network. Proceedings of the IGARSS 2019\u20142019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan.","DOI":"10.1109\/IGARSS.2019.8898889"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"42384","DOI":"10.1109\/ACCESS.2020.2977454","article-title":"Hyperspectral band selection using attention-based convolutional neural networks","volume":"8","author":"Lorenzo","year":"2020","journal-title":"IEEE Access"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Ortiz, A., Granados, A., Fuentes, O., Kiekintveld, C., Rosario, D., and Bell, Z. (2018, January 18\u201322). Integrated learning and feature selection for deep neural networks in multispectral images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPRW.2018.00165"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Bernal, E.A. (2019, January 16\u201317). Surrogate Contrastive Network for Supervised Band Selection in Multispectral Computer Vision Tasks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00131"},{"key":"ref_37","first-page":"5504414","article-title":"Deep reinforcement learning for band selection in hyperspectral image classification","volume":"60","author":"Mou","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_38","first-page":"5501719","article-title":"Deep reinforcement learning for semisupervised hyperspectral band selection","volume":"60","author":"Feng","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Berk, A., Anderson, G.P., Bernstein, L.S., Acharya, P.K., Dothe, H., Matthew, M.W., Adler-Golden, S.M., Chetwynd, J.H., Richtsmeier, S.C., and Pukall, B. (1999, January 19\u201321). MODTRAN4 radiative transfer modeling for atmospheric correction. Proceedings of the Optical Spectroscopic Techniques and Instrumentation for Atmospheric and Space Research III, Denver, CO, USA.","DOI":"10.1117\/12.366388"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Yu, J., Yan, B., Liu, W., Li, Y., and He, P. (2017, January 5\u20137). Seamless Mosaicking of Multi-strip Airborne Hyperspectral Images Based on Hapke Model. Proceedings of the International Conference on Sensing and Imaging, Chengdu, China.","DOI":"10.1007\/978-3-319-91659-0_22"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.rse.2018.09.020","article-title":"New methods for improving the remote sensing estimation of soil organic matter content (SOMC) in the Ebinur Lake Wetland National Nature Reserve (ELWNNR) in northwest China","volume":"218","author":"Wang","year":"2018","journal-title":"Remote Sens. Environ."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1016\/j.rse.2003.11.001","article-title":"Predicting in situ pasture quality in the Kruger National Park, South Africa, using continuum-removed absorption features","volume":"89","author":"Mutanga","year":"2004","journal-title":"Remote Sens. Environ."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"113896","DOI":"10.1016\/j.geoderma.2019.113896","article-title":"Prediction of soil organic matter using multi-temporal satellite images in the Songnen Plain, China","volume":"356","author":"Dou","year":"2019","journal-title":"Geoderma"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Jaffel, Z., and Farah, M. (2018, January 21\u201324). A symbiotic organisms search algorithm for feature selection in satellite image classification. Proceedings of the 2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), Sousse, Tunisia.","DOI":"10.1109\/ATSIP.2018.8364494"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1007\/s10661-008-0385-4","article-title":"Novel hyperspectral reflectance models for estimating black-soil organic matter in Northeast China","volume":"154","author":"Liu","year":"2009","journal-title":"Environ. Monit. Assess."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1016\/S0034-4257(01)00347-9","article-title":"Relating soil surface moisture to reflectance","volume":"81","author":"Weidong","year":"2002","journal-title":"Remote Sens. Environ."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Shen, L., Gao, M., Yan, J., Li, Z.-L., Leng, P., Yang, Q., and Duan, S.-B. (2020). Hyperspectral estimation of soil organic matter content using different spectral preprocessing techniques and PLSR method. Remote Sens., 12.","DOI":"10.3390\/rs12071206"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"115845","DOI":"10.1016\/j.geoderma.2022.115845","article-title":"Modified soil scattering coefficients for organic matter inversion based on Kubelka-Munk theory","volume":"418","author":"Ou","year":"2022","journal-title":"Geoderma"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/1\/127\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:51:47Z","timestamp":1760147507000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/1\/127"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,26]]},"references-count":48,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,1]]}},"alternative-id":["rs15010127"],"URL":"https:\/\/doi.org\/10.3390\/rs15010127","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2022,12,26]]}}}