Learning-Based Approach for Atmospheric Compensation of VNIR Hyperspectral Data

被引:5
作者
Acito, Nicola [1 ,2 ]
Diani, Marco [1 ,2 ]
Corsini, Giovanni [3 ]
机构
[1] Accademia Navale, Dipartimento Armi Navali, I-57127 Livorno, Italy
[2] Consorzio Nazl Interuniv Telecomunicaz CNIT, I-43124 Parma, Italy
[3] Univ Pisa, Dipartimento Ingn Informaz, I-56122 Pisa, Italy
来源
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2021年 / 59卷 / 05期
关键词
Atmospheric compensation (AC); hyperspectral imagery; learning-based (LB) approach; machine learning; RETRIEVAL; ALGORITHM;
D O I
10.1109/TGRS.2020.3016094
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
In this work, we deal with the problem of atmospheric compensation (AC) of hyperspectral data collected in the visible and near-infrared (VNIR) spectral range. We propose the "learning-based" approach which uses artificial intelligence algorithms to directly estimate the spectral reflectance from the observed at-sensor radiance image. It uses a parametric regressor whose parameters are learned by means of a strategy based on synthetic data. Such data are generated taking into account 1) the radiative transfer in the atmosphere; 2) the variability of the surface spectral reflectance; and 3) the effects of signal-dependent random noise and spectral miscalibration errors. According to this general framework, we propose a specific multilinear regressor that starting from the knowledge of the atmospheric visibility compensates the water absorption and provides the spectral reflectance of each pixel of the analyzed image. Furthermore, a specific image-based procedure is presented for visibility estimation. The experiment over simulated data is presented and discussed. The test on simulated data aims at showing the effectiveness of the proposed strategy in a completely controlled environment. Experiments are also carried out on three real hyperspectral images acquired by two hyperspectral sensors. The obtained results confirm the effectiveness of the proposed approach by comparing the retrieved reflectance spectra with in-situ measurements or with those obtained by using a well-known commercial AC software.
引用
收藏
页码:4218 / 4232
页数:15
相关论文
共 50 条
[41]   A learning-based approach to regression analysis for climate data-A case of Northeast China [J].
Guo, Jiaxu ;
Xu, Yidan ;
Hu, Liang ;
Wu, Xianwei ;
Xu, Gaochao ;
Che, Xilong .
ENGINEERING REPORTS, 2025, 7 (01)
[42]   A Machine Learning-Based Missing Data Imputation with FHIR Interoperability Approach in Sepsis Prediction [J].
Toro Beltran, Cristian Fernando ;
Villarreal Ibanez, Erick Daniel ;
Milen Orejuela, Vivian ;
Garcia Henao, John Anderson .
HIGH PERFORMANCE COMPUTING, CARLA 2022, 2022, 1660 :116-130
[43]   Machine learning-based approach to GPS antijamming [J].
Cheng-Zhen Wang ;
Ling-Wei Kong ;
Junjie Jiang ;
Ying-Cheng Lai .
GPS Solutions, 2021, 25
[44]   A machine learning-based approach for vital node identification in complex networks [J].
Rezaei, Ahmad Asgharian ;
Munoz, Justin ;
Jalili, Mahdi ;
Khayyam, Hamid .
EXPERT SYSTEMS WITH APPLICATIONS, 2023, 214
[45]   A neural network technique for atmospheric compensation and temperature/emissivity separation using LWIR/MWIR hyperspectral data [J].
Blackwell, WJ .
ALGORITHMS AND TECHNOLOGIES FOR MULTISPECTRAL, HYPERSPECTRAL, AND ULTRASPECTRAL IMAGERY X, 2004, 5425 :604-615
[46]   Flexible atmospheric compensation technique (FACT): a 6S based atmospheric correction scheme for remote sensing data [J].
Jha, Sudhanshu Shekhar ;
Kumar, C. V. S. S. Manohar ;
Nidamanuri, Rama Rao .
GEOCARTO INTERNATIONAL, 2021, 36 (01) :28-46
[47]   Optimal selection of learning data for highly accurate QSAR prediction of chemical biodegradability: a machine learning-based approach [J].
Takeda, K. ;
Takeuchi, K. ;
Sakuratani, Y. ;
Kimbara, K. .
SAR AND QSAR IN ENVIRONMENTAL RESEARCH, 2023, 34 (09) :729-743
[48]   Hepatitis C Prediction Using Machine Learning and Deep Learning-Based Hybrid Approach with Biomarker and Clinical Data [J].
Rokiya Ripa ;
Khandaker Mohammad Mohi Uddin ;
Mir Jafikul Alam ;
Md. Mahbubur Rahman .
Biomedical Materials & Devices, 2025, 3 (1) :558-575
[49]   Development of a Deep Learning-Based Atmospheric Correction Algorithm for Oligotrophic Oceans [J].
Men, Jilin ;
Tian, Liqiao ;
Zhao, Dan ;
Wei, Jianwei ;
Feng, Lian .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[50]   Learning-based pattern-data-driven forecast approach for predicting future well responses [J].
Yeongju Kim ;
Baehyun Min ;
Alexander Sun ;
Bo Ren ;
Hoonyoung Jeong .
Journal of Petroleum Exploration and Production Technology, 2025, 15 (2)