Pub Date : 2019-07-01DOI: 10.1109/Agro-Geoinformatics.2019.8820632
Chuan Wang, Lizhen Lu
Plastic-mulched landcover (PML) is an important type of agricultural landscape and remote sensing is an effective way for monitoring and mapping PML. Based on Gaofen-2 (GF-2) and Landsat-8 operational land imager (OLI) fused data, this study applied an object-based random forest classification (OBRFC) method, which combines object-based image analysis (OBIA) technology with random forest (RF) model, to map PML. The method consists of the following steps: (1) image segmentation with a multiresolution segmentation (MRS) algorithm; (2) selection of sample objects (or segments) and 50 features of index, texture, and shape based on prior knowledge and relevant references; and (3) determination of two particularly important parameters, the number of decision trees-T and the feature number of split nodes -F, by comparing classification accuracy of a series of experiments. The results from applying the OBRFC method on the study area show: 1) the best overall accuracy (OA) of OBARFC reaches 91.73%; 2) by setting T to 50, OA curve presents a downward trend with the highest value of 91.72% at F =5; and 3) by setting F to 5, OA reaches its best value at T = 50.
{"title":"Object-based random forest classification for detecting plastic-mulched landcover from Gaofen-2 and Landsat-8 OLI fused data","authors":"Chuan Wang, Lizhen Lu","doi":"10.1109/Agro-Geoinformatics.2019.8820632","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820632","url":null,"abstract":"Plastic-mulched landcover (PML) is an important type of agricultural landscape and remote sensing is an effective way for monitoring and mapping PML. Based on Gaofen-2 (GF-2) and Landsat-8 operational land imager (OLI) fused data, this study applied an object-based random forest classification (OBRFC) method, which combines object-based image analysis (OBIA) technology with random forest (RF) model, to map PML. The method consists of the following steps: (1) image segmentation with a multiresolution segmentation (MRS) algorithm; (2) selection of sample objects (or segments) and 50 features of index, texture, and shape based on prior knowledge and relevant references; and (3) determination of two particularly important parameters, the number of decision trees-T and the feature number of split nodes -F, by comparing classification accuracy of a series of experiments. The results from applying the OBRFC method on the study area show: 1) the best overall accuracy (OA) of OBARFC reaches 91.73%; 2) by setting T to 50, OA curve presents a downward trend with the highest value of 91.72% at F =5; and 3) by setting F to 5, OA reaches its best value at T = 50.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124406962","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 : 2019-07-01DOI: 10.1109/Agro-Geoinformatics.2019.8820637
Ziyan Zhou, Xiao-qun Wang, Zhenping Wang
The water discharge and sediment load of rivers are changing substantially under the impacts of climate change and human activities, becoming a hot issue in hydro-environmental research. Quantitative analysis of the impacts of natural facts and human activities on water and sediment changes has important practical significance for the rational development and utilization of water resources and the control of soil and water conservation in the region. In this study, the water discharge and sediment load of GuanYin Bridge and ShangHang Stations in the Tingjiang River were investigated by using long-term hydro-meteorological data from 1982-2013. And then the Cumulative Anomaly method and Multivariate Linear Ridge Regression were used to detect trends and abrupt change-points in water dischange and sediment load based on long-term observation data and GIMMS NDVI and other data and to quantify the effects of climate change and human activities on water discharge and sediment load. The results are as follows: (1) the runoff and sediment series of changring section from 1982 to 2013 mutate in 1991 and 2000, and the runoff and sediment had a similar time change trend in different stages; (2) the change trend of GuanYin Bridge and ShangHang stations was slightly different in 1982-1991, with the GuanYin Bridge showed a decreasing trend and the shanghang station showed a non-significant increasing trend. During 1991-2000, the two sites increased significantly, while the trends in 2000-2013 were significant decreasing; (3) the contributions of natural and human activities to changes in runoff and sediment are different at different time periods. However, the contributions of natural factors are generally greater than those of human activities during 1982-2013.Rainfall factor has its maximum effect of all the influence factors in changting section of Tingjiang river, with the contribution rate of more than 50% while the temperature has its minimum effect with the contribution rate of less than 10%,the proportion of NDVI and government funds is about 10%-15%; (4) in 1982-1991 and 1991-2000, the contribution of natural factors to runoff and sediment dominated by about 80%, with a weak impact on human activities of about 20%. As 2000-2013, with the continuous large amount of government funding investment, soil and water conservation projects have achieved more significant results, human activities greatly contribute to changes in runoff and sediment, accounting for about 45%.This shows that the impact of human activities on runoff and sediment has a good response to the intensity of soil erosion control in Changting County.
{"title":"Quantitative analysis of the impacts of natural factors and human activities on runoff and sediment change in Tingjiang River","authors":"Ziyan Zhou, Xiao-qun Wang, Zhenping Wang","doi":"10.1109/Agro-Geoinformatics.2019.8820637","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820637","url":null,"abstract":"The water discharge and sediment load of rivers are changing substantially under the impacts of climate change and human activities, becoming a hot issue in hydro-environmental research. Quantitative analysis of the impacts of natural facts and human activities on water and sediment changes has important practical significance for the rational development and utilization of water resources and the control of soil and water conservation in the region. In this study, the water discharge and sediment load of GuanYin Bridge and ShangHang Stations in the Tingjiang River were investigated by using long-term hydro-meteorological data from 1982-2013. And then the Cumulative Anomaly method and Multivariate Linear Ridge Regression were used to detect trends and abrupt change-points in water dischange and sediment load based on long-term observation data and GIMMS NDVI and other data and to quantify the effects of climate change and human activities on water discharge and sediment load. The results are as follows: (1) the runoff and sediment series of changring section from 1982 to 2013 mutate in 1991 and 2000, and the runoff and sediment had a similar time change trend in different stages; (2) the change trend of GuanYin Bridge and ShangHang stations was slightly different in 1982-1991, with the GuanYin Bridge showed a decreasing trend and the shanghang station showed a non-significant increasing trend. During 1991-2000, the two sites increased significantly, while the trends in 2000-2013 were significant decreasing; (3) the contributions of natural and human activities to changes in runoff and sediment are different at different time periods. However, the contributions of natural factors are generally greater than those of human activities during 1982-2013.Rainfall factor has its maximum effect of all the influence factors in changting section of Tingjiang river, with the contribution rate of more than 50% while the temperature has its minimum effect with the contribution rate of less than 10%,the proportion of NDVI and government funds is about 10%-15%; (4) in 1982-1991 and 1991-2000, the contribution of natural factors to runoff and sediment dominated by about 80%, with a weak impact on human activities of about 20%. As 2000-2013, with the continuous large amount of government funding investment, soil and water conservation projects have achieved more significant results, human activities greatly contribute to changes in runoff and sediment, accounting for about 45%.This shows that the impact of human activities on runoff and sediment has a good response to the intensity of soil erosion control in Changting County.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133794574","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 : 2019-07-01DOI: 10.1109/Agro-Geoinformatics.2019.8820209
S. Aksoy, Ozge Gorucu, Elif Sertel
Drought is one of the frequently observed natural hazard resulting from precipitation deficit and increased evapotranspiration caused by high temperatures. Remote sensing indices are used to analyze spatio-temporal distribution of drought conditions and identify drought severity. In this study, we analyzed the spatio-temporal distribution of drought conditions in Turkey from February 2000 to January 2019 by using different drought indices produced from MODIS satellite data in Google Earth Engine (GEE) platform. Vegetation Health Index (VHI), Normalized Multiband Drought Index(NMDI) and Normalized Difference Drought Index (NDDI) maps in country level for different years and months of the related years were utilized to assess the drought conditions. Time series were also created for some specific locations to deeply analyze the drought conditions in 20-year period. Our results show that MODIS derived drought indices provide useful geospatial information to assess drought conditions in country level. Moreover, GEE platform is very handy and rapid tool to reach related satellite images and conduct remote sensing analysis of huge and long term date efficiently. Geospatial big data could be successfully accessed and processed in this platform not only for drought monitoring but also for other environmental monitoring applications.
{"title":"Drought Monitoring using MODIS derived indices and Google Earth Engine Platform","authors":"S. Aksoy, Ozge Gorucu, Elif Sertel","doi":"10.1109/Agro-Geoinformatics.2019.8820209","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820209","url":null,"abstract":"Drought is one of the frequently observed natural hazard resulting from precipitation deficit and increased evapotranspiration caused by high temperatures. Remote sensing indices are used to analyze spatio-temporal distribution of drought conditions and identify drought severity. In this study, we analyzed the spatio-temporal distribution of drought conditions in Turkey from February 2000 to January 2019 by using different drought indices produced from MODIS satellite data in Google Earth Engine (GEE) platform. Vegetation Health Index (VHI), Normalized Multiband Drought Index(NMDI) and Normalized Difference Drought Index (NDDI) maps in country level for different years and months of the related years were utilized to assess the drought conditions. Time series were also created for some specific locations to deeply analyze the drought conditions in 20-year period. Our results show that MODIS derived drought indices provide useful geospatial information to assess drought conditions in country level. Moreover, GEE platform is very handy and rapid tool to reach related satellite images and conduct remote sensing analysis of huge and long term date efficiently. Geospatial big data could be successfully accessed and processed in this platform not only for drought monitoring but also for other environmental monitoring applications.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114506550","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 : 2019-07-01DOI: 10.1109/Agro-Geoinformatics.2019.8820252
F. Balcik, G. Senel, C. Goksel
Efficient methodologies to map greenhouses are very important for the implementation of sustainable agricultural practices, natural resource management, and sustainable urban and rural development. Remote sensing imagery provides a great potential with different spatial and spectral resolutions for greenhouse monitoring and mapping. The conventional techniques for greenhouse mapping are time consuming, and expensive. Because of this reason, many different image processing methods such as classification methods including pixel-based or object based classification and remote sensing indices have been applied for greenhouse mapping. In this study, greenhouses in Anamur, Mersin, Turkey were determined by using object based classification and selected remote sensing indices. Freely available new generation 2018 dated Sentinel-2 MSI data which has 10-meters spatial resolution was used to detect the greenhouse in the selected region. Multi-resolution segmentation (MRS) method was conducted to Sentinel-2 MSI data for object-based image analysis (OBIA). In the first stage, the image segmentation process was performed. Spectral features (mean values of the layers) and remote sensing indices such as Normalized difference vegetation index (NDVI), Normalized difference water index (NDWI) and Retrogressive plastic greenhouse index (RPGI) were extracted from the segmented image. Then, four different datasets were created and the OBIA classification process was performed by applying the nearest neighbor classifier to the created data sets. Reference dataset for training and validation has been created by field survey, apart from this some of the sample are taken with the help of high resolution Google earth images. On the final stage, the accuracy assessment analysis was performed to test the agreement between classification results and ground truth data using error matrix. Dataset-4 (mean values of the layers, NDVI, NDWI and RPGI) has the highest producer and overall accuracies with 82% and 74%, respectively.
{"title":"Greenhouse Mapping using Object Based Classification and Sentinel-2 Satellite Imagery","authors":"F. Balcik, G. Senel, C. Goksel","doi":"10.1109/Agro-Geoinformatics.2019.8820252","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820252","url":null,"abstract":"Efficient methodologies to map greenhouses are very important for the implementation of sustainable agricultural practices, natural resource management, and sustainable urban and rural development. Remote sensing imagery provides a great potential with different spatial and spectral resolutions for greenhouse monitoring and mapping. The conventional techniques for greenhouse mapping are time consuming, and expensive. Because of this reason, many different image processing methods such as classification methods including pixel-based or object based classification and remote sensing indices have been applied for greenhouse mapping. In this study, greenhouses in Anamur, Mersin, Turkey were determined by using object based classification and selected remote sensing indices. Freely available new generation 2018 dated Sentinel-2 MSI data which has 10-meters spatial resolution was used to detect the greenhouse in the selected region. Multi-resolution segmentation (MRS) method was conducted to Sentinel-2 MSI data for object-based image analysis (OBIA). In the first stage, the image segmentation process was performed. Spectral features (mean values of the layers) and remote sensing indices such as Normalized difference vegetation index (NDVI), Normalized difference water index (NDWI) and Retrogressive plastic greenhouse index (RPGI) were extracted from the segmented image. Then, four different datasets were created and the OBIA classification process was performed by applying the nearest neighbor classifier to the created data sets. Reference dataset for training and validation has been created by field survey, apart from this some of the sample are taken with the help of high resolution Google earth images. On the final stage, the accuracy assessment analysis was performed to test the agreement between classification results and ground truth data using error matrix. Dataset-4 (mean values of the layers, NDVI, NDWI and RPGI) has the highest producer and overall accuracies with 82% and 74%, respectively.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124284306","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}
In recent years, with the rapid development of regional economy in the Pearl River Estuary, drastic change in the content and transport patterns of suspended sediment in water bodies, which mainly caused by variations in land use patterns and bank erosion, imposed a profound impact on the development and evolution of the estuary Delta as well as the coastal ecological environment. In this study, we used the measured spectral data to establish inversion algorithm and to inverse suspended sediment based on CASI hyperspectral data, the accuracy of the inversed CASI and MODIS suspended sediment were verified with in-situ measured data. The results show that: 1) Single-band exponential model (SSC=4.5e21.922*Rs(622.486)) can well retrieve the suspended sediment concentration in the experimental sea area, and the average relative error is approximately 11.15%; 2) The suspended sediment content lies between 0.45-12.15 mg/L over the study area, and the main input source is land-based input from the west coast of Huangmao Sea, the ecological impact on the dolphin reserve can be neglected; 3) Combined with MODIS-based remote sensing images of suspended sediment in the Pearl River Estuary, it is found that there is an obvious branching phenomena when the sediment is transported from the Huangmao Sea to the outside of the mouth. The main axis of runoff is transported along the northeast direction of Dajin Island to the southeast direction of Dajin Island in the estuary area, while the coastal current is transported along the northeast direction of Dajin Island to the southwest direction of Dajin Island. As a result, there are low suspended sediment and high transparency sea areas in the north of Dajin Island, which are suitable for aquaculture.
{"title":"Observation of Suspended Sediment in the Surrounding Sea Waters of Dajin Island Based on CASI Hyperspectral Data","authors":"Guorong Huang, Xiaoyu Zhang, Yachao Han, Jiaxing Chen, Yongjun Zhang","doi":"10.1109/Agro-Geoinformatics.2019.8820250","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820250","url":null,"abstract":"In recent years, with the rapid development of regional economy in the Pearl River Estuary, drastic change in the content and transport patterns of suspended sediment in water bodies, which mainly caused by variations in land use patterns and bank erosion, imposed a profound impact on the development and evolution of the estuary Delta as well as the coastal ecological environment. In this study, we used the measured spectral data to establish inversion algorithm and to inverse suspended sediment based on CASI hyperspectral data, the accuracy of the inversed CASI and MODIS suspended sediment were verified with in-situ measured data. The results show that: 1) Single-band exponential model (SSC=4.5e21.922*Rs(622.486)) can well retrieve the suspended sediment concentration in the experimental sea area, and the average relative error is approximately 11.15%; 2) The suspended sediment content lies between 0.45-12.15 mg/L over the study area, and the main input source is land-based input from the west coast of Huangmao Sea, the ecological impact on the dolphin reserve can be neglected; 3) Combined with MODIS-based remote sensing images of suspended sediment in the Pearl River Estuary, it is found that there is an obvious branching phenomena when the sediment is transported from the Huangmao Sea to the outside of the mouth. The main axis of runoff is transported along the northeast direction of Dajin Island to the southeast direction of Dajin Island in the estuary area, while the coastal current is transported along the northeast direction of Dajin Island to the southwest direction of Dajin Island. As a result, there are low suspended sediment and high transparency sea areas in the north of Dajin Island, which are suitable for aquaculture.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122635535","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 : 2019-07-01DOI: 10.1109/agro-geoinformatics.2019.8820481
{"title":"Agro-Geoinformatics 2019 Copyright and Reprint Permission","authors":"","doi":"10.1109/agro-geoinformatics.2019.8820481","DOIUrl":"https://doi.org/10.1109/agro-geoinformatics.2019.8820481","url":null,"abstract":"","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125595909","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}
Cropland extraction has great significance in many agricultural applications and has always been an important research focus. In this study, we proposed a contour-oriented approach that used the RCF network to extract cropland from high resolution remote sensing imagery. Weining County, Guizhou Province in China was selected to be the research area and Google Earth images were used as the data source. Compared with the canny algorithm, the RCF network detected the cropland contour much more accurately and completely, showing substantial improvement both numerically and visually. At last, we successfully employed this method to produce a cropland thematic map of a part of Weining County with 5 times increase in productivity comparing with complete manual production, suggesting the application value of such contour-oriented method.
{"title":"Contour-oriented Cropland Extraction from High Resolution Remote Sensing Imagery Using Richer Convolution Features Network","authors":"Hao Liu, Jiancheng Luo, Yingwei Sun, Liegang Xia, Wei Wu, Haiping Yang, Xiaodong Hu, Lijing Gao","doi":"10.1109/Agro-Geoinformatics.2019.8820430","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820430","url":null,"abstract":"Cropland extraction has great significance in many agricultural applications and has always been an important research focus. In this study, we proposed a contour-oriented approach that used the RCF network to extract cropland from high resolution remote sensing imagery. Weining County, Guizhou Province in China was selected to be the research area and Google Earth images were used as the data source. Compared with the canny algorithm, the RCF network detected the cropland contour much more accurately and completely, showing substantial improvement both numerically and visually. At last, we successfully employed this method to produce a cropland thematic map of a part of Weining County with 5 times increase in productivity comparing with complete manual production, suggesting the application value of such contour-oriented method.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117025627","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 : 2019-07-01DOI: 10.1109/Agro-Geoinformatics.2019.8820643
Ling Sun, Zesheng Zhu
A satellite remote sensing experiment, designed to test the difference in ratio vegetation index between monoculture cotton and cotton–rice rotation cotton, was carried out at Xinghua during 2001 and 2002 cropping seasons. The methods of analysis developed for this experiment are described in the present paper and demonstrated using ratio vegetation indexes of cotton. We conclude that the mean ratio vegetation index difference of cotton between two culture modes is often substantial That is, we have found the sufficient statistical evidence to conclude that the yield of rotation cotton is generally greater than that of monoculture cotton.
{"title":"Using Spectral Vegetation Index to Estimate Continuous Cotton and Rice-Cotton Rotation Effects on Cotton Yield","authors":"Ling Sun, Zesheng Zhu","doi":"10.1109/Agro-Geoinformatics.2019.8820643","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820643","url":null,"abstract":"A satellite remote sensing experiment, designed to test the difference in ratio vegetation index between monoculture cotton and cotton–rice rotation cotton, was carried out at Xinghua during 2001 and 2002 cropping seasons. The methods of analysis developed for this experiment are described in the present paper and demonstrated using ratio vegetation indexes of cotton. We conclude that the mean ratio vegetation index difference of cotton between two culture modes is often substantial That is, we have found the sufficient statistical evidence to conclude that the yield of rotation cotton is generally greater than that of monoculture cotton.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128495023","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 classification of crops based on remote sensing technology is a necessary measure for large-scale agricultural monitoring. In the regions with good light conditions, optical satellite data can be used for crop classification with a satisfied result. However, there are also large regions of cloudy and rainy regions on the surface of the earth. In these regions, optical images can only obtained fragmented data through the cloud gap or even impossible to get, which cannot meet the requirements of rapid and accurate agricultural monitoring. Synthetic aperture radar (SAR) data can be rarely affected by atmospheric disturbances and sensitive to surface structure characteristics, so the SAR data has good application potential in agriculture. Especially in cloudy and rainy regions, its application for crop classification has more realistic significance. In this study, we classify crops based on Sentinel-1 multi-temporal data in Xifeng County at the geo-parcel scale with a recurrent neural network, the overall accuracy could up to 69 percent. This method can solve the problem of continuous optical data loss in crop classification in cloudy and rainy regions.
{"title":"Geo-parcel based Crops Classification with Sentinel-1 Time Series Data via Recurrent Reural Network","authors":"Yingwei Sun, Jiancheng Luo, Tianjun Wu, Yingpin Yang, Hao Liu, Wen Dong, Lijing Gao, Xiaodong Hu","doi":"10.1109/Agro-Geoinformatics.2019.8820218","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820218","url":null,"abstract":"The classification of crops based on remote sensing technology is a necessary measure for large-scale agricultural monitoring. In the regions with good light conditions, optical satellite data can be used for crop classification with a satisfied result. However, there are also large regions of cloudy and rainy regions on the surface of the earth. In these regions, optical images can only obtained fragmented data through the cloud gap or even impossible to get, which cannot meet the requirements of rapid and accurate agricultural monitoring. Synthetic aperture radar (SAR) data can be rarely affected by atmospheric disturbances and sensitive to surface structure characteristics, so the SAR data has good application potential in agriculture. Especially in cloudy and rainy regions, its application for crop classification has more realistic significance. In this study, we classify crops based on Sentinel-1 multi-temporal data in Xifeng County at the geo-parcel scale with a recurrent neural network, the overall accuracy could up to 69 percent. This method can solve the problem of continuous optical data loss in crop classification in cloudy and rainy regions.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130092686","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 : 2019-07-01DOI: 10.1109/Agro-Geoinformatics.2019.8820479
Zheng Sun, Di Wang, Qingbo Zhou
Dryland crops have a long planting history in China. They are planted in a wide range and account for a high proportion of the total grain output. Quick and accurate acquisition of Dryland Crop Planting area can provide decision support for agricultural production managers, provide basis for food policy formulation, and provide guarantee for national food security. Different from the initial stage of rice growth, the underlying surface water layer and rice plant can form obvious dihedral angle, which can produce strong backscatter to microwave. Intercropping and interplanting of dryland crops are common, and the planting structure is complex, so it is difficult to identify them. At present, there is a lack of research on scattering characteristics of Dryland crops, and the universality of recognition methods is also poor, which leads to the low accuracy of dry land crop recognition based on SAR data. The purpose of studying the scattering characteristics of dryland crops and their changes with time is to provide basis for the identification of dryland crops and improve the classification accuracy. This paper chooses Jizhou City, Hebei Province as the research area, and takes corn and cotton as the research objects. The full polarization RADARSAT -2 data of three phases in 2018 (July 17, August 7 and September 24) were used. The changes of basic scattering characteristics (average scattering angle, entropy, volume scattering, dihedral angle scattering, surface scattering) of crops with different target decomposition methods (Cloude-Pottier, Freeman, Yamaguchi) were studied and compared, and the proportion of basic scattering power and its changing trend at different growth stages were analyzed. The results showed that the counter-entropy of the two crops changed little in the whole growth period, and mainly consisted of surface scattering and volume scattering. For corn, with the growth of crops, the entropy and average scattering angle increased first and then decreased, the proportion of surface scattering power decreased from 67% to 48% and then increased to 55%, and the proportion of volume scattering power increased from 33% to 52% and then decreased to 45%. On August 7, the volume scattering power is greater than the surface scattering power. For cotton, with the increase of crop growth entropy and average scattering angle, the proportion of surface scattering power decreases from 66% to 54%, and the volume scattering power increases from 33% to 46%. The surface scattering power is larger than volume scattering in the whole growth period. This study will help to determine the scattering mechanism of corn and cotton, and provide reference for the study of scattering characteristics of other dryland crops.
{"title":"Study on Scattering Characteristics of Dryland Crops using Multi-temporal Polarimetric RADARSAT-2 Imagery","authors":"Zheng Sun, Di Wang, Qingbo Zhou","doi":"10.1109/Agro-Geoinformatics.2019.8820479","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820479","url":null,"abstract":"Dryland crops have a long planting history in China. They are planted in a wide range and account for a high proportion of the total grain output. Quick and accurate acquisition of Dryland Crop Planting area can provide decision support for agricultural production managers, provide basis for food policy formulation, and provide guarantee for national food security. Different from the initial stage of rice growth, the underlying surface water layer and rice plant can form obvious dihedral angle, which can produce strong backscatter to microwave. Intercropping and interplanting of dryland crops are common, and the planting structure is complex, so it is difficult to identify them. At present, there is a lack of research on scattering characteristics of Dryland crops, and the universality of recognition methods is also poor, which leads to the low accuracy of dry land crop recognition based on SAR data. The purpose of studying the scattering characteristics of dryland crops and their changes with time is to provide basis for the identification of dryland crops and improve the classification accuracy. This paper chooses Jizhou City, Hebei Province as the research area, and takes corn and cotton as the research objects. The full polarization RADARSAT -2 data of three phases in 2018 (July 17, August 7 and September 24) were used. The changes of basic scattering characteristics (average scattering angle, entropy, volume scattering, dihedral angle scattering, surface scattering) of crops with different target decomposition methods (Cloude-Pottier, Freeman, Yamaguchi) were studied and compared, and the proportion of basic scattering power and its changing trend at different growth stages were analyzed. The results showed that the counter-entropy of the two crops changed little in the whole growth period, and mainly consisted of surface scattering and volume scattering. For corn, with the growth of crops, the entropy and average scattering angle increased first and then decreased, the proportion of surface scattering power decreased from 67% to 48% and then increased to 55%, and the proportion of volume scattering power increased from 33% to 52% and then decreased to 45%. On August 7, the volume scattering power is greater than the surface scattering power. For cotton, with the increase of crop growth entropy and average scattering angle, the proportion of surface scattering power decreases from 66% to 54%, and the volume scattering power increases from 33% to 46%. The surface scattering power is larger than volume scattering in the whole growth period. This study will help to determine the scattering mechanism of corn and cotton, and provide reference for the study of scattering characteristics of other dryland crops.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131545929","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：