检索结果-内蒙古大学图书馆

A Deep-Learning and Transfer-Learning Hybrid Aerosol retrieval algorithm for FY4-AGRI:Development and Verification over Asia

引用

Engineering 2024年第7期38卷 164-174页

作者： Disong Fu Hongrong Shi Christian AGueymard Dazhi Yang Yu Zheng Huizheng Che Xuehua Fan Xinlei Han Lin Gao Jianchun Bian Minzheng Duan Xiangao Xia Key Laboratory of Middle Atmosphere and Global Environment Observation Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing 10029China Key Laboratory of Cloud-Precipitation Physics and Severe Storms Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing 100029China Solar Consulting Services ColebrookNH 03576USA School of Electrical Engineering and Automation Harbin Institute of TechnologyHarbin 150006China State Key Laboratory of Severe Weather&Key Laboratory of Atmospheric Chemistry Institute of Atmospheric Composition and Environmental MeteorologyChinese Academy of Meteorological SciencesChina Meteorological AdministrationBeijing 100081China National Institute of Natural Hazards Ministry of Emergency Management of ChinaBeijing100085China Key Laboratory of Compound and Chained Natural Hazards Dynamics Ministry of Emergency Management of ChinaBeijing 100085China h National Satellite Meteorological Center China Meteorological AdministrationBeijing 100081China University of Chinese Academy of Sciences Beijing 100049China

The Advanced Geosynchronous Radiation Imager(AGRI)is a mission-critical instrument for the Fengyun series of *** acquires full-disk images every 15 min and views East Asia every 5 min through 14 spectral bands,enabling the detection of highly variable aerosol optical depth(AOD).Quantitative retrieval of AOD has hitherto been challenging,especially over *** this study,an AOD retrieval algorithm is proposed that combines deep learning and transfer *** algorithm uses core concepts from both the Dark Target(DT)and Deep Blue(DB)algorithms to select features for the machinelearning(ML)algorithm,allowing for AOD retrieval at 550 nm over both dark and bright *** algorithm consists of two steps:①A baseline deep neural network(DNN)with skip connections is developed using 10 min Advanced Himawari Imager(AHI)AODs as the target variable,and②sunphotometer AODs from 89 ground-based stations are used to fine-tune the DNN ***-of-station validation shows that the retrieved AOD attains high accuracy,characterized by a coefficient of determination(R2)of 0.70,a mean bias error(MBE)of 0.03,and a percentage of data within the expected error(EE)of 70.7%.A sensitivity study reveals that the top-of-atmosphere reflectance at 650 and 470 nm,as well as the surface reflectance at 650 nm,are the two largest sources of uncertainty impacting the *** a case study of monitoring an extreme aerosol event,the AGRI AOD is found to be able to capture the detailed temporal evolution of the *** work demonstrates the superiority of the transfer-learning technique in satellite AOD retrievals and the applicability of the retrieved AGRI AOD in monitoring extreme pollution events.

关键词： Aerosol optical depth retrieval algorithm Deep learning Transfer learning Advanced Geosynchronous Radiation Imager

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Aerosol Optical Depth retrieval algorithm for Particulate Observing Scanning Polarimeter (POSP) Data Over Land

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Ji, Zhe Ma, Yan de Leeuw, Gerrit Shi, Zheng Li, Zhengqiang Chinese Acad Sci Aerosp Informat Res Inst State Environm Protect Key Lab Satellite Remote Se Beijing 100101 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Key Lab Remote Sensing & Digital Earth Beijing 100101 Peoples R China Univ Chinese Acad Sci Beijing 101408 Peoples R China Royal Netherlands Meteorol Inst KNMI R&D Satellite Observat NL-3730 AE De Bilt Netherlands Adm Ctr Chinas Agenda 21 Beijing 100098 Peoples R China Henan Univ Coll Geog & Environm Sci Zhengzhou 450000 Peoples R China

Single-angle sensors typically use radiative transfer simulations based on Lambertian surface, even though the surface reflectance obtained exhibits directional characteristics. Fully accounting for the contribution of surface directional characteristics to the top of atmosphere (TOA) reflectances can further improve the accuracy of aerosol retrievals. In this study, we propose an enhanced aerosol retrieval algorithm for the Particulate Observing Scanning Polarimeter (POSP), by further considering the surface directional characteristics. Combined with an updated aerosol model, this approach achieves high-accuracy retrievals. We used historical bidirectional reflectance distribution function (BRDF) products to construct stable surface constraints. By exploring the strong empirical statistical relationships between adjacent blue bands, we have realized the joint inversion of multiple blue bands. In addition, we used an optimization algorithm that incorporates boundary constraints, simultaneously accounting for errors in the surface constraint model, and satellite observation errors. The global aerosol optical thickness (AOD) at 550 nm over land was retrieved from November 2021 to April 2022. Validation of POSP AOD versus AErosol RObotic NETwork (AERONET) data shows a high consistency, with correlation coefficient (R) of 0.93, root mean square error (RMSE) of 0.086, bias of 0.004, fraction within expected error (EE) of 80.8%, and fraction within Global Climate Observing System (GCOS) of 52.1%. Comparison with MODIS aerosol products shows that the accuracy of POSP AOD is better than that of MODIS AOD. According to the matching results, for DB, R of 0.936/0.907 and fraction within EE of 82.2%/74.9% (POSP/MODIS DB);for DT, R of 0.937/0.915 and fraction within EE of 83.5%/ 72.0% (POSP/MODIS DT). The spatial distribution difference between POSP AOD and DB AOD is small, indicating good consistency, and POSP AOD captured the intensity of aerosol pollution well. In summary, th

关键词： Aerosols Atmospheric modeling Satellite broadcasting MODIS Accuracy Laboratories Surface waves Surface reconstruction Radiometry Protection Aerosol optical depth (AOD) bidirectional reflectance distribution function (BRDF) Particulate Observing Scanning Polarimeter (POSP) retrieval algorithm surface constraint

来源：评论

学校读者我要写书评

暂无评论

SIFFI: Bayesian solar-induced fluorescence retrieval algorithm for remote sensing of vegetation

引用

REMOTE SENSING OF ENVIRONMENT 2025年 318卷

作者： Kukkurainen, Antti Lipponen, Antti Kolehmainen, Ville Arola, Antti Cogliati, Sergio Sabater, Neus Finnish Meteorol Inst Kuopio Finland Univ Eastern Finland Kuopio Finland Univ Milano Bicocca Milan Italy

Remote sensing of solar-induced vegetation chlorophyll fluorescence (SIF) has a rich history of more than 50 years of research covering active and passive techniques from leaf, canopy, and satellite scale. Current satellite- derived SIF products primarily focus on the far-red spectral range, with variations in techniques dependent on sensor capabilities. However, these retrieval methods often rely on parametric spectral models and are constrained to narrow absorption regions. In this paper, we introduce a novel Bayesian retrieval technique, referred to as SIFFI (Siffi Is For Fluorescence Inference), designed for the flexible and robust estimation of spectrally resolved fluorescence spectra. SIFFI utilizes spectral representations for both fluorescence and surface reflectance, enabling its application to distinct spectral ranges, e.g., red, far-red, and full spectral range. Also, its applicability extends to top-of-canopy (TOC) and top-of-atmosphere (TOA) measurements, with the latter being possible when auxiliary information about the atmospheric state is available. For the assessment of SIFFI, we performed an extensive proof-of-concept simulation exercise involving diverse scenarios that integrated measured leaf-level fluorescence and reflectance signals, propagated them to the TOC and TOA levels, and perturbed the resultant signal with instrument Gaussian noise to simulate realistic conditions. Additionally, we extend our assessment exercise to TOC measurements acquired by a fluorescence box (FloX) instrument during two diurnal cycles on sunlit and cloudy conditions. In all the TOC cases, simulations- and measured- based scenarios, we compared our SIF estimates with the results from two well-established methods: the improved Fraunhofer line discrimination method (iFLD) and the Spectral Fitting (SpecFit) method covering the full fluorescence spectra. Notably, our results highlight the versatility and accuracy of SIFFI in estimating spectrally resolved fluorescence,

关键词： Solar-Induced Chlorophyll Fluorescence (SIF) retrieval algorithm Bayesian inversion Satellite observations Radiative transfer

来源：评论

学校读者我要写书评

暂无评论

An Intelligent retrieval algorithm for Digital Literature Promotion Information Based on TRS Information retrieval

引用

INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGIES AND SYSTEMS APPROACH 2023年第2期16卷 1-14页

作者： Ni, Tong Yanan Univ Xian Innovat Coll Xian Peoples R China

The world has entered the information age, and one of the main factors of social development is various information resources. Word processing is one of the first information technologies to be developed that has grown very rapidly and successfully. As a category of multimedia resources, documents are widely used in institutions, such as corporations, governments, and digital libraries. Traditional search technology has been unable to meet the needs of this development, and how to find information in this sea of digital information has become an urgent problem. Therefore, this study has conducted a research experiment on promoting digital literature for text retrieval system information retrieval. The experimental data have shown that 310 (73.81%) students wanted WeChat and Weibo as a way of digital literature retrieval and promotion. Moreover, 267 (63.57%) students wanted e-books as a way to promote, and 172 (40.95%) students would like to participate in novel digital literature retrieval promotion activities.

关键词： Digital Literature Information retrieval Literature Promotion retrieval algorithm TRS Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Application of a Change Detection Soil Moisture retrieval algorithm to Combined, Semiconcurrent Radiometer, and Radar Observations

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2022年 15卷 9716-9721页

作者： Ouellette, Jeffrey D. Himani, Tanish Li, Li Twarog, Elizabeth M. Colliander, Andreas Goodrich, David Collins, Chandra Holifield Cosh, Michael Walker, Jeffrey P. Naval Res Lab Remote Sensing Div Washington DC 20375 USA CALTECH NASA Jet Prop Lab Pasadena CA 91109 USA ARS USDA Southwest Watershed Res Ctr Tucson AZ 85719 USA ARS USDA Beltsville MD 20705 USA Monash Univ Dept Civil Engn Clayton Vic 3800 Australia

This article extends the application of an existing change-detection-based, time-series soil moisture retrieval algorithm to nonconcurrent active and passive measurements from WindSat/AMSR2 and the Soil Moisture Active Passive radar, which was active from late April until mid-July of 2015. A time series of L-band radar backscatter observations was used to populate an underdetermined matrix equation whose optimal solution was derived via a bounded linear least squares estimator, and whose bounds were derived from a time series of radiometer-derived soil moisture estimates (taken by either WindSat or AMSR2). Surface soil moisture estimates are compared with in-situ measurement probes, which were treated as ground truth. Error statistics and time-series results for the validation sites are presented here and conclusions derived therefrom. The overall RMSE and unbiased RMSE for the retrieval algorithm, taken across all reference pixels considered in the study, were 0.070 m(3)/m(3) and 0.067 m(3)/m(3), respectively, when using WindSat to constrain the algorithm. When using AMSR2 to constrain the algorithm, the RMSE and unbiased RMSE were 0.093 m(3)/m(3) and 0.090 m(3)/m(3), respectively.

关键词： Change detection data fusion hydrology radar radiometer remote sensing retrieval algorithm soil moisture time series

来源：评论

学校读者我要写书评

暂无评论

Two-step hybrid retrieval algorithm for characterizing ultrashort optical pulse from its SHG-FROG trace

引用

OPTICS COMMUNICATIONS 2025年 587卷

作者： Dong, Xiaowei Wei, Xingmi North China Univ Technol Coll Informat Engn Beijing 100144 Peoples R China

In this paper, we propose a two-step hybrid retrieval algorithm for characterizing ultrashort optical pulse from its measured SHG-FROG trace. In the first step, we use a modified ResNet50 deep neural network and a very small training datasets containing only 4000 FROG-trace samples to quickly obtain the rough characteristics of the pulse to be retrieved. Then, we use the results obtained in the first step as the initial values of the iterative optimization in the second step, which can further obtain more accurate characteristics of ultrashort optical pulse. Results demonstrate that the two-step hybrid retrieval algorithm can achieve very high accuracy in characterizing ultrashort optical pulses. And the correlation coefficient between the reconstructed FROG trace based on the retrieved ultrashort optical pulse and the original measured FROG trace can approximately reach 1.

关键词： retrieval algorithm Ultrashort optical pulse FROG ResNet50 neural network

来源：评论

学校读者我要写书评

暂无评论

Development of China's atmospheric environment monitoring satellite CO2 IPDA lidar retrieval algorithm based on airborne campaigns

引用

REMOTE SENSING OF ENVIRONMENT 2024年 315卷

作者： Wang, Shuaibo Cheng, Chonghui Chen, Sijie Liu, Jiqiao Zhang, Xingying Bu, Lingbing Zhang, Jingxin Zhang, Kai Deng, Jiesong Xu, Wentao Chen, Weibiao Liu, Dong Zhejiang Univ Coll Opt Sci & Engn State Key Lab Modern Opt Instrumentat Hangzhou 310027 Peoples R China Zhejiang Univ ZJU Hangzhou Global Sci & Technol Innovat Ctr Hangzhou 311200 Peoples R China China Meteorol Adm Natl Satellite Meteorol Ctr Natl Ctr Space Weather Key Lab Radiometr Calibrat & Validat Environm Sate Beijing 100081 Peoples R China Chinese Acad Sci Shanghai Inst Opt & Fine Mech Shanghai 201800 Peoples R China China Meteorol Adm Dept Sci & Technol & Climate Change Beijing 100081 Peoples R China Nanjing Univ Informat Sci & Technol Collaborat Innovat Ctr Forecast & Evaluat Meteorol Nanjing 210044 Peoples R China

China successfully launched the Atmospheric Environment Monitoring Satellite (AEMS) equipped with an Atmospheric Carbon Dioxide Lidar (ACDL) on April 16, 2022, which is the world's first satellite based on Integrated Path Differential Absorption (IPDA) technique to detect the atmospheric CO2 column-weighted dry-air mixing ratio (XCO2). In order to accurately and quickly process the AEMS measurements, we proposed a systematic retrieval algorithm for the AEMS ACDL and conducted two airborne campaigns to validate its performance. The first airborne campaign was conducted in the land-sea interface region of northeast China in 2019. The CO2 retrieval algorithm distinguished significant horizontal XCO2 gradients over different underlying surfaces and obtained an apparent XCO2 enhancement of 8-18 ppm between the urban and forests. The CO2 retrievals not only demonstrated the excellent detection capability of the ACDL for carbon sources and sinks, but also proved the feasibility of the retrieval algorithm in complex terrain and variable atmospheric conditions. The second airborne experiment was conducted in 2021 in the interior desert region of China, which is an excellent flight field to explore the accuracy and precision limits of the retrieval algorithm. We validated the XCO2 retrievals with the airborne in-situ CO2 profiles and demonstrated that the XCO2 accuracy and precision were 0.29 ppm and 0.63 ppm with 1.5-km averages over the desert surface, indicating the accuracy of the retrieval algorithm. The hard target elevation (HTE) retrieval validation results indicate that the IPDA lidar ranging precision is 0.69 m and 6.29 m for the ocean and land surface, respectively. In addition, further analysis combined with the spaceborne IPDA lidar simulator showed high consistency in CO2 precision between airborne measurements and simulation results in East Asia, demonstrating the robustness of the retrieval algorithm at continental scales.

关键词： IPDA lidar ACDL retrieval algorithm Airborne campaigns CO2

来源：评论

学校读者我要写书评

暂无评论

A Thermal Infrared Land Surface Temperature retrieval algorithm for Thin Cirrus Skies Using Cirrus Optical Properties

引用

IEEE ACCESS 2021年 9卷 82380-82389页

作者： Fan, Xiwei Nie, Gaozhong Liu, Yaohui Ni, Li China Earthquake Adm Key Lab Seism & Volcan Hazards Beijing 100029 Peoples R China China Earthquake Adm Inst Geol Beijing 100029 Peoples R China Shandong Jianzhu Univ Sch Surveying & Geoinformat Jinan 250101 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Key Lab Digital Earth Sci Beijing 100094 Peoples R China

To acquire daytime land surface temperature (LST) in thin cirrus cloudy skies, we have developed a three-channel LST retrieval algorithm based on a widely used two-channel LST retrieval algorithm for the clear-sky conditions. In this algorithm, the LST is expressed as a multiple linear function of MODIS channels 29, 31 and 32 with the coefficients of the linear function dependent on the cirrus optical depth (COD) and cirrus effective radius (R). The influences from land surface emissivities (LSEs) are also considered in this algorithm. The simulated dataset shows that the LST could be estimated using the proposed algorithm with the root mean squire error (RMSE) less than 2.2 K in thin cirrus cloudy skies (COD less than 0.7) when viewing zenith angle (VZA) equivalent to 0 degrees. As VZA is equivalent to 60 degrees, the maximum RMSE are 2.7 K. The widely used generalized split-window (GSW) algorithm proposed for clear-sky conditions are used in cirrus cloudy skies, and the RMSEs of GSW algorithm estimated LST are 16.89 K and 22.32 K for VZA =0 degrees and VZA =60 degrees respectively when COD is 0.7. It indicates that the proposed three-channel algorithm can significantly improve the LST retrieval accuracy using thermal infrared data in cirrus cloudy skies. To estimate the LST errors caused by the uncertainties of COD, R, LSE and instrument noise, a sensitivity analysis was performed. It shows that the accuracy of cirrus COD is more important for the retrieval of LST compared with other parameters. The maximum total LST errors, taking into account all the input parameters' uncertainty and algorithm error itself, are 3.8 K and 4.3 K when VZA =0 degrees and VZA =60 degrees respectively.

关键词： Clouds Land surface temperature MODIS Land surface Atmospheric modeling Satellites Channel estimation Land surface temperature thermal infrared remote sensing retrieval algorithm thin cirrus clouds MODIS

来源：评论

学校读者我要写书评

暂无评论

Phase retrieval algorithm for the reconstruction of scattered images for visible and X-ray light sources

引用

OPTICAL ENGINEERING 2024年第2期63卷 023105-023105页

作者： Lei, Yaohu Luo, Senlong Liu, Lang Huang, Jianheng Liu, Xin Shenzhen Univ Coll Phys & Optoelect Engn Key Lab Optoelect Devices & Syst Minist Educ & Guangdong Prov Shenzhen Peoples R China

. Single-shot non-invasive imaging through a scattering medium has been an area of research focus for several years. Achieving an accurate autocorrelation distribution is crucial for effective image reconstruction. However, the obtained autocorrelation is always contaminated by various types of noise. In this study, we propose an effective method to extract the autocorrelation distribution of the sample from the noise-laden raw data before image retrieval. This is accomplished by incorporating an intensity threshold and a spatial Gaussian filter into the retrieval algorithm, which effectively eliminates the noise artifacts in the reconstructed image. The proposed algorithm exhibited remarkable robustness for both visible (laser, white light, and light-emitting diode light) and X-ray light sources, and its efficacy was verified through multiple experiments.

关键词： Scattering imaging autocorrelation distribution retrieval algorithm

来源：评论

学校读者我要写书评

暂无评论

A robust and flexible satellite aerosol retrieval algorithm for multi-angle polarimetric measurements with physics-informed deep learning method

引用

REMOTE SENSING OF ENVIRONMENT 2023年第1期297卷

作者： Tao, Minghui Chen, Jinxi Xu, Xiaoguang Man, Wenjing Xu, Lina Wang, Lunche Wang, Yi Wang, Jun Fan, Meng Shahzad, Muhammad Imran Chen, Liangfu China Univ Geosci Sch Geog & Informat Engn Hubei Key Lab Reg Ecol & Environm Change Wuhan 430074 Peoples R China Univ Maryland Baltimore Cty Joint Ctr Earth Syst Technol Baltimore MD 21250 USA China Univ Geosci Sch Geophys & Geomat Subsurface Multiscale Imaging Key Lab Wuhan 430074 Peoples R China Univ Iowa Dept Chem & Environm Engn Iowa City IA 52242 USA Chinese Acad Sci State Key Lab Remote Sensing Sci Aerosp Informat Res Inst Beijing 100101 Peoples R China COMSATS Univ Islamabad Dept Meteorol Earth & Atmospher Remote Sensing Lab EARL Islamabad 45550 Pakistan 388 Lumo Rd Wuhan 430074 Peoples R China

The multi-angle polarimetric (MAP) satellite measurements provide abundant information concerning aerosol optical/microphysical properties. In this study, we present a robust and flexible aerosol retrieval algorithm for MAP measurements based on physics-informed deep learning (PDL) method. Different from optimized inversion that needs iterative Radiative Transfer (RT) calculations of all the unknowns, the PDL method can model the whole MAP observations with each retrieved aerosol parameter separately with the pre-training of RT simulations. Furthermore, the training of PDL can make full use of the prior information from ground-based aerosol inversions and satellite surface products, and provides an effective constraint to avoid unphysical values. To examine performance of PDL algorithm, we retrieve aerosols over eastern China from POLDER-3 measurements during 2007-2009. Comparison with AERONET products shows high correlations (R > 0.91) for both POLDER-3 PDL Aerosol Optical Depth (AOD) and fine AOD. Despite lower correlations caused by a small portion of poor retrievals, PDL coarse AOD and Single Scattering Albdeo (SSA) is very consistent with AERONET results. Also, PDL retrievals perform well as the best estimates of optimized methods such as GRASP (Generalized retrieval of Aerosol and Surface Properties). With an outstanding performance in accuracy and efficiency, the flexible PDL algorithm exhibits great potential for operational retrieval of MAP satellite measurements.

关键词： Aerosols Multi-angle polarization POLDER-3 retrieval algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：