Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849359
Zhi He, Man Xiao, Dan He, Anjun Lou, Xinyuan Li
Anomaly detection plays an essential role in hyperspectral remote sensing. Various widespread detectors, such as ReedXiaoli (RX), sparse representation, or deep learning-based methods, have been developed by using the original spectral or spatial-spectral features. However, most of the existing methods cannot adaptively extract spatial-spectral information by integrating traditional and deep learning methods. In this paper, we propose a variational mode decomposition (VMD)-inspired bidirectional long short-term memory (termed as VbiLSTM) for anomaly detection of hyperspectral images (HSI). The VbiLSTM consists of three main modules, i.e., noise reduction module, intrinsic feature extraction module, and anomaly detection module. First, wavelet transform is performed on the original HSI datasets to reduce the noise. Second, VMD-guided biLSTM is proposed for intrinsic feature extraction of the denoised image. Finally, a one-class support vector machine (OCSVM) is adopted for anomaly detection by feeding the extracted features and the final detection results are an ensemble of detection results over all the features. Experiments performed on two HSI datasets demonstrate that the VbiLSTM achieves superior detection results compared with current state-of-the-art methods.
{"title":"VMD-Inspired Bidirectional LSTM for Anomaly Detection of Hyperspectral Images","authors":"Zhi He, Man Xiao, Dan He, Anjun Lou, Xinyuan Li","doi":"10.1109/ICGMRS55602.2022.9849359","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849359","url":null,"abstract":"Anomaly detection plays an essential role in hyperspectral remote sensing. Various widespread detectors, such as ReedXiaoli (RX), sparse representation, or deep learning-based methods, have been developed by using the original spectral or spatial-spectral features. However, most of the existing methods cannot adaptively extract spatial-spectral information by integrating traditional and deep learning methods. In this paper, we propose a variational mode decomposition (VMD)-inspired bidirectional long short-term memory (termed as VbiLSTM) for anomaly detection of hyperspectral images (HSI). The VbiLSTM consists of three main modules, i.e., noise reduction module, intrinsic feature extraction module, and anomaly detection module. First, wavelet transform is performed on the original HSI datasets to reduce the noise. Second, VMD-guided biLSTM is proposed for intrinsic feature extraction of the denoised image. Finally, a one-class support vector machine (OCSVM) is adopted for anomaly detection by feeding the extracted features and the final detection results are an ensemble of detection results over all the features. Experiments performed on two HSI datasets demonstrate that the VbiLSTM achieves superior detection results compared with current state-of-the-art methods.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114862390","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849308
Yuan-bo Wang
Remote sensing scene classification has been a research hotspot in recent years, and convolution neural networks have been widely used in this field. However, remote sensing scene images have large-scale variance with regard to a specific category, making it still difficult to individually train and obtain an excellent classifier by adopting features of single sample extracted by a CNN model to make prediction. To tackle above issue, a novel framework named Comparison Graph Neural Networks (CGNN) is proposed for remote sensing scene classification. The framework constructs comparison graph based on sample features extracted by CNN model. Then CGNN is employed on the graph for sample comparison and aggregates node features according to node connection weights learned by metric-learning neural networks from node similarities. Experiments are conducted on the benchmark dataset and the proposed framework obtains competitive performance compared with powerful baselines.
{"title":"Comparison Graph Neural Networks for Remote Sensing Scene Classification","authors":"Yuan-bo Wang","doi":"10.1109/ICGMRS55602.2022.9849308","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849308","url":null,"abstract":"Remote sensing scene classification has been a research hotspot in recent years, and convolution neural networks have been widely used in this field. However, remote sensing scene images have large-scale variance with regard to a specific category, making it still difficult to individually train and obtain an excellent classifier by adopting features of single sample extracted by a CNN model to make prediction. To tackle above issue, a novel framework named Comparison Graph Neural Networks (CGNN) is proposed for remote sensing scene classification. The framework constructs comparison graph based on sample features extracted by CNN model. Then CGNN is employed on the graph for sample comparison and aggregates node features according to node connection weights learned by metric-learning neural networks from node similarities. Experiments are conducted on the benchmark dataset and the proposed framework obtains competitive performance compared with powerful baselines.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116929404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849223
Guanzhe Li, Hongxiong Hao, Lingda Wu, Boyu Liu
Hyperspectral images technology can greatly enhance the extraction ability of ground object information. It is a research hotspot and frontier field in the field of remote sensing in recent years, and has great application value and broad development prospects in many related fields This paper summarizes the methods of denoising and target detection in hyperspectral images.To help researchers better sort out the relevant algorithms.
{"title":"Current Situation of Denoising And Target Detection In Hyperspectral Images","authors":"Guanzhe Li, Hongxiong Hao, Lingda Wu, Boyu Liu","doi":"10.1109/ICGMRS55602.2022.9849223","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849223","url":null,"abstract":"Hyperspectral images technology can greatly enhance the extraction ability of ground object information. It is a research hotspot and frontier field in the field of remote sensing in recent years, and has great application value and broad development prospects in many related fields This paper summarizes the methods of denoising and target detection in hyperspectral images.To help researchers better sort out the relevant algorithms.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"11 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120846830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849286
Man Xiao, Zhi He, Anjun Lou, Xinyuan Li
Recently, deep learning-based methods have gained great attention in ship detection of synthetic aperture radar (SAR) images. However, the mismatch between horizontal detection boxes and real targets poses big challenges to the improvement of detection accuracy, especially for the densely arranged ships. Therefore, how to achieve precise arbitrary-oriented ship detection is particularly important. In this paper, we propose a novel center-to-corner vector guided network named CCVNet for SAR ship detection. Different from angle regression and classification, our CCVNet adopts an anchor-free method to directly predict the vectors from center to corners, which can reduce the error accumulation caused by predicting angles and scales separately. In addition, data augmentation methods with random rotation and power transformations are put forward to keep the rotation invariance and enhance the information of SAR images, which are proved to be effective in promoting detection performance. Experimental results on the SSDD dataset demonstrate the superiority of our method.
{"title":"Center-to-Corner Vector Guided Network for Arbitrary-Oriented Ship Detection in Synthetic Aperture Radar Images","authors":"Man Xiao, Zhi He, Anjun Lou, Xinyuan Li","doi":"10.1109/ICGMRS55602.2022.9849286","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849286","url":null,"abstract":"Recently, deep learning-based methods have gained great attention in ship detection of synthetic aperture radar (SAR) images. However, the mismatch between horizontal detection boxes and real targets poses big challenges to the improvement of detection accuracy, especially for the densely arranged ships. Therefore, how to achieve precise arbitrary-oriented ship detection is particularly important. In this paper, we propose a novel center-to-corner vector guided network named CCVNet for SAR ship detection. Different from angle regression and classification, our CCVNet adopts an anchor-free method to directly predict the vectors from center to corners, which can reduce the error accumulation caused by predicting angles and scales separately. In addition, data augmentation methods with random rotation and power transformations are put forward to keep the rotation invariance and enhance the information of SAR images, which are proved to be effective in promoting detection performance. Experimental results on the SSDD dataset demonstrate the superiority of our method.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129882205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849397
Cheng Hu, Yungang Cao
As one of the most prosperous arteries of the Silk Road and a transit point for trade between East and West, Qinghai Silk Road is an important part of the "One Belt, One Road", and remote sensing monitoring of its vegetation is a crucial part of the ecological study of the Silk Road. In this paper, we use MODIS high-resolution remote sensing images and meteorological data in 2000, 2005, 2010 and 2015 to simulate the spatial and temporal changes of vegetation productivity at the county scale along the Silk Road in Qinghai Province with the aid of GIS and RS technology. The results show that the vegetation productivity in the Qinghai Silk Road area of the Silk Road showed a spatial pattern of high in the east and low in the west over the past 15 years, with the highest NPP of 163.09 g C/m2 in Datong County and the lowest NPP of 55.00 g C/m2 in Haixi Mongolian and Tibetan Autonomous Prefecture, and the annual average NPP of 86.99 g C/m2; the high values of NPP during the year were concentrated in June to August; interannually, NPP showed a fluctuating growth trend from 2000 to 2015 in general, with a decreasing trend from 2000 to 2005, and an obvious increasing trend from 2005 to 2015, with a maximum value of 327.943 g C/m2, a net increase of 448,885 km2 and a decrease of 24,968 km2, indicating that the vegetation growth in the Qinghai Silk Road area of the Silk Road has been improved.
青海丝绸之路是丝绸之路最繁华的要道之一，是东西方贸易往来的中转站，是“一带一路”的重要组成部分，青海丝绸之路植被遥感监测是丝绸之路生态研究的重要组成部分。本文利用2000年、2005年、2010年和2015年的MODIS高分辨率遥感影像和气象数据，结合GIS和RS技术，模拟了青海省丝绸之路沿线县域植被生产力的时空变化。结果表明:近15 a来，丝绸之路青海丝绸之路区域的植被生产力呈现东高西低的空间格局，NPP最高的是大同县(163.09 g C/m2)，最低的是海西蒙古族藏族自治州(55.00 g C/m2)，年平均NPP为86.99 g C/m2;全年NPP高值集中在6 ~ 8月;年际NPP总体呈波动增长趋势，2000 - 2005年呈下降趋势，2005 - 2015年呈明显上升趋势，最大值为327.943 g C/m2，净增加448,885 km2，减少24,968 km2，表明丝绸之路青海丝绸之路地区植被生长得到改善。
{"title":"Spatio-Temporal Change of County Vegetation Net Primary Productivity in Qinghai Silk Road region","authors":"Cheng Hu, Yungang Cao","doi":"10.1109/ICGMRS55602.2022.9849397","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849397","url":null,"abstract":"As one of the most prosperous arteries of the Silk Road and a transit point for trade between East and West, Qinghai Silk Road is an important part of the \"One Belt, One Road\", and remote sensing monitoring of its vegetation is a crucial part of the ecological study of the Silk Road. In this paper, we use MODIS high-resolution remote sensing images and meteorological data in 2000, 2005, 2010 and 2015 to simulate the spatial and temporal changes of vegetation productivity at the county scale along the Silk Road in Qinghai Province with the aid of GIS and RS technology. The results show that the vegetation productivity in the Qinghai Silk Road area of the Silk Road showed a spatial pattern of high in the east and low in the west over the past 15 years, with the highest NPP of 163.09 g C/m2 in Datong County and the lowest NPP of 55.00 g C/m2 in Haixi Mongolian and Tibetan Autonomous Prefecture, and the annual average NPP of 86.99 g C/m2; the high values of NPP during the year were concentrated in June to August; interannually, NPP showed a fluctuating growth trend from 2000 to 2015 in general, with a decreasing trend from 2000 to 2005, and an obvious increasing trend from 2005 to 2015, with a maximum value of 327.943 g C/m2, a net increase of 448,885 km2 and a decrease of 24,968 km2, indicating that the vegetation growth in the Qinghai Silk Road area of the Silk Road has been improved.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127124683","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849334
Fang Zhou
A kind of constant slope surface whose tangent planes have a fixed inclination angle with xy-plane is commonly applied in civil engineering. With the idea of any horizantal curve on the surface being the envelope of family of circles, the equations of the surface are built. Also, it is proved that the normal vector of the surface is always enclosed to the z-axis. Finally, with the help the Maple, the parameterized 3D surface model is implemented. By two examples and an engineering examples of multi-level dam modelling, the equations proposed are verified and its results are accurate.
{"title":"A constant slope surface and its application","authors":"Fang Zhou","doi":"10.1109/ICGMRS55602.2022.9849334","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849334","url":null,"abstract":"A kind of constant slope surface whose tangent planes have a fixed inclination angle with xy-plane is commonly applied in civil engineering. With the idea of any horizantal curve on the surface being the envelope of family of circles, the equations of the surface are built. Also, it is proved that the normal vector of the surface is always enclosed to the z-axis. Finally, with the help the Maple, the parameterized 3D surface model is implemented. By two examples and an engineering examples of multi-level dam modelling, the equations proposed are verified and its results are accurate.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123270670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849278
Yan Liang, Rong Xie, Changqing Liu, Aiqing Ye
The construction and precision control of the global control field is the basis of precision measurement in large-scale spaces. The total station as a measuring equipment is selected to establish a high precision measurement control field. Firstly, the three-dimensional coordinates of the global control points are obtained from multiple stations based on the total station. Then the parameters of registration are solved using Singular Value Decomposition algorithm. Next, with the constraint of high precision angle measurement value, the coordinate registration results are optimized by Jacobian matrix iteration algorithm and the measurement precision is increased. Finally, this method is applied to shape measurement of ship section surface. The effectiveness of the method is proved by comparing the distances between control points at different stations.
{"title":"Construction and Optimization Method of Large-scale Space Control Field based on Total Station","authors":"Yan Liang, Rong Xie, Changqing Liu, Aiqing Ye","doi":"10.1109/ICGMRS55602.2022.9849278","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849278","url":null,"abstract":"The construction and precision control of the global control field is the basis of precision measurement in large-scale spaces. The total station as a measuring equipment is selected to establish a high precision measurement control field. Firstly, the three-dimensional coordinates of the global control points are obtained from multiple stations based on the total station. Then the parameters of registration are solved using Singular Value Decomposition algorithm. Next, with the constraint of high precision angle measurement value, the coordinate registration results are optimized by Jacobian matrix iteration algorithm and the measurement precision is increased. Finally, this method is applied to shape measurement of ship section surface. The effectiveness of the method is proved by comparing the distances between control points at different stations.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126208750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849264
Anxiang Wang, Ke Liu, Linshan Zhong
The extraction of urban built-up areas based on nighttime light images by deep learning algorithms is a new exploration in remote sensing research in recent years. An improved DeepLabV3+ network is proposed to address the phenomenon that ordinary convolutional neural networks processing remote sensing images will lose a large amount of detail information in the coded feature extraction stage, which in turn leads to poor edge segmentation and low accuracy. The network performs 2D decomposition of the asymmetric convolution in the ADSPP convolution layer, and then combines it with the null convolution to form an asymmetric null convolution for feature extraction, capturing more features by enhancing the skeleton part of the convolution kernel to improve the classification accuracy of urban built-up areas without increasing the computing time. This paper shows that the improved DeepLabV3+ network is more objective in characterizing urbanization development than the original DeepLabV3+ network in terms of the extent of built-up areas extracted from night-time light images.
{"title":"Extraction of built-up areas from nighttime light images based on improved DeepLabV3+ network","authors":"Anxiang Wang, Ke Liu, Linshan Zhong","doi":"10.1109/ICGMRS55602.2022.9849264","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849264","url":null,"abstract":"The extraction of urban built-up areas based on nighttime light images by deep learning algorithms is a new exploration in remote sensing research in recent years. An improved DeepLabV3+ network is proposed to address the phenomenon that ordinary convolutional neural networks processing remote sensing images will lose a large amount of detail information in the coded feature extraction stage, which in turn leads to poor edge segmentation and low accuracy. The network performs 2D decomposition of the asymmetric convolution in the ADSPP convolution layer, and then combines it with the null convolution to form an asymmetric null convolution for feature extraction, capturing more features by enhancing the skeleton part of the convolution kernel to improve the classification accuracy of urban built-up areas without increasing the computing time. This paper shows that the improved DeepLabV3+ network is more objective in characterizing urbanization development than the original DeepLabV3+ network in terms of the extent of built-up areas extracted from night-time light images.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121347828","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1109/ICGMRS55602.2022.9849301
Zhiwei Xie, Ruizhao Liu, Chao Huang, Guangming Song
In order to be able to describe the boundary and evolution of urban agglomeration in Liaoning in real time and quantitatively, this paper designs and implements a method to identify the spatial structure of urban agglomeration based on nighttime light data and graph theory. The neighborhood extreme value method is used to identify the feature points, and the hydrological analysis method is used to indirectly extract the feature lines, then construct the nighttime light intensity map. The innovative graph theory is applied to the node clustering set detection of the nighttime light intensity map, and the agglomeration characteristics of cities are discovered by establishing the geographic mapping relationship between nodes and cities. In this paper, major cities in Liaoning, China, are taken as the study area, and NPP/VIIRS (NPOESS Preparatory Project/Visible Infrared Imaging Radiometer) data in 2016 and 2020 are used. The experimental results prove that the development momentum of southern Liaoning is stronger, the central Liaoning absorbs part of the western Liaoning, and the western Liaoning further shrinks.
{"title":"Spatial Structure Identification of Urban Agglomeration in Liaoning Province Based on Luminous Data and Graph Theory","authors":"Zhiwei Xie, Ruizhao Liu, Chao Huang, Guangming Song","doi":"10.1109/ICGMRS55602.2022.9849301","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849301","url":null,"abstract":"In order to be able to describe the boundary and evolution of urban agglomeration in Liaoning in real time and quantitatively, this paper designs and implements a method to identify the spatial structure of urban agglomeration based on nighttime light data and graph theory. The neighborhood extreme value method is used to identify the feature points, and the hydrological analysis method is used to indirectly extract the feature lines, then construct the nighttime light intensity map. The innovative graph theory is applied to the node clustering set detection of the nighttime light intensity map, and the agglomeration characteristics of cities are discovered by establishing the geographic mapping relationship between nodes and cities. In this paper, major cities in Liaoning, China, are taken as the study area, and NPP/VIIRS (NPOESS Preparatory Project/Visible Infrared Imaging Radiometer) data in 2016 and 2020 are used. The experimental results prove that the development momentum of southern Liaoning is stronger, the central Liaoning absorbs part of the western Liaoning, and the western Liaoning further shrinks.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121615920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The North China Plain is an important agricultural production base for China with its flat terrain and ease of cultivation. However, its severe drought problems limit the use of its resource advantages. Crop growth is affected by multi-source compound stresses such as soil moisture stress, pest and disease stress, and heavy metal stress, and accurate screening and monitoring of soil moisture stress is the key to the research. In this paper, the Normalized Difference Vegetation Index (NDVI) long time series curves of winter wheat were constructed using the NDVI as the response parameter by combining the remote sensing image data from the GF-1 satellite and Landsat satellite. Using the Ensemble Empirical Mode Decomposition (EEMD) algorithm to decompose the long time series, make the statistical description of each decomposed Intrinsic Mode Function (IMF), and combined it with the analysis of soil moisture stress mechanism to achieve an effective screening and extraction of soil moisture stress. Partial Least Squares Regression (PLSR) was used to establish the quantitative relationship between remote sensing monitoring indicators and ground-based indicators for soil moisture monitoring and prediction. The results show that: 1) Among the six decomposed IMF components, the statistical descriptors of IMF1 and IMF2 are the most consistent with the characteristics of the mechanism analysis, and the soil moisture stress sequences synthesized from them can better reflect the soil moisture stress conditions in the study area; 2) Chlorophyll Response to Soil Moisture Stress (CR_SMS) and Wheat Moisture Content Response to Soil Moisture Stress (WMCR_SMS) can effectively reflect the response of chlorophyll content of winter wheat leaves and wheat moisture content to soil moisture stress in the study area; 3) The coefficient of determination of the quantitative inversion model based on PLSR is 0.879, with a high degree of model fit and low error. However, the combination of the EEMD algorithm and PLSR modelling can effectively identify and extract soil moisture stress and achieve accurate monitoring and quantitative inversion of soil moisture in cropland, so as to provide reference for irrigation and rational use of water resources in farmland.
{"title":"Comprehensive evaluation of soil moisture in farmland based on Ensemble Empirical Mode Decomposition and Partial Least Squares Regression","authors":"Xiaodan Wang, Xuqing Li, Yongtao Jin, Liangpeng Zhang, Chenyu Zhao, Wenlong Zhang","doi":"10.1109/ICGMRS55602.2022.9849368","DOIUrl":"https://doi.org/10.1109/ICGMRS55602.2022.9849368","url":null,"abstract":"The North China Plain is an important agricultural production base for China with its flat terrain and ease of cultivation. However, its severe drought problems limit the use of its resource advantages. Crop growth is affected by multi-source compound stresses such as soil moisture stress, pest and disease stress, and heavy metal stress, and accurate screening and monitoring of soil moisture stress is the key to the research. In this paper, the Normalized Difference Vegetation Index (NDVI) long time series curves of winter wheat were constructed using the NDVI as the response parameter by combining the remote sensing image data from the GF-1 satellite and Landsat satellite. Using the Ensemble Empirical Mode Decomposition (EEMD) algorithm to decompose the long time series, make the statistical description of each decomposed Intrinsic Mode Function (IMF), and combined it with the analysis of soil moisture stress mechanism to achieve an effective screening and extraction of soil moisture stress. Partial Least Squares Regression (PLSR) was used to establish the quantitative relationship between remote sensing monitoring indicators and ground-based indicators for soil moisture monitoring and prediction. The results show that: 1) Among the six decomposed IMF components, the statistical descriptors of IMF1 and IMF2 are the most consistent with the characteristics of the mechanism analysis, and the soil moisture stress sequences synthesized from them can better reflect the soil moisture stress conditions in the study area; 2) Chlorophyll Response to Soil Moisture Stress (CR_SMS) and Wheat Moisture Content Response to Soil Moisture Stress (WMCR_SMS) can effectively reflect the response of chlorophyll content of winter wheat leaves and wheat moisture content to soil moisture stress in the study area; 3) The coefficient of determination of the quantitative inversion model based on PLSR is 0.879, with a high degree of model fit and low error. However, the combination of the EEMD algorithm and PLSR modelling can effectively identify and extract soil moisture stress and achieve accurate monitoring and quantitative inversion of soil moisture in cropland, so as to provide reference for irrigation and rational use of water resources in farmland.","PeriodicalId":129909,"journal":{"name":"2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126292842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：