Pub Date : 2019-07-16DOI: 10.1109/Agro-Geoinformatics.2019.8820646
Z. M. Sahin, E. Erten, Gülsen Taskin Kaya
Application of regression models through remote sensing for estimating biophysical parameters of crops is one of the key elements for precision agriculture studies. Numerically, this problem is solved separately for each biophysical parameter such as leaf area index, soil moisture, crop height and etc. However, this approach ignores tight relationship among the biophysical parameters, which is essential for driving estimation performance with a limited number of in-situ measurements. As an alternative strategy, a multi-output regression, which also learns the relationship among biophysical parameters in the regression model, is considered. In order to see how multi-output regression models capture the plausible physical relationship between crops biophysical parameters and polarimetric features, RadarSAT-2 images acquired over agriculture fields in the context of the AgriSAR 2009 campaign were used. Specifically, multioutput Gaussian Processes and multi-output Support Vector Machines, which are two powerful kernel-based methods, are implemented and assessed in the context of accuracy assessment of the biophysical parameter estimation.
{"title":"Multi-Output Regressions For Estimating Canola Biophysical Parameters From PolSAR Data","authors":"Z. M. Sahin, E. Erten, Gülsen Taskin Kaya","doi":"10.1109/Agro-Geoinformatics.2019.8820646","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820646","url":null,"abstract":"Application of regression models through remote sensing for estimating biophysical parameters of crops is one of the key elements for precision agriculture studies. Numerically, this problem is solved separately for each biophysical parameter such as leaf area index, soil moisture, crop height and etc. However, this approach ignores tight relationship among the biophysical parameters, which is essential for driving estimation performance with a limited number of in-situ measurements. As an alternative strategy, a multi-output regression, which also learns the relationship among biophysical parameters in the regression model, is considered. In order to see how multi-output regression models capture the plausible physical relationship between crops biophysical parameters and polarimetric features, RadarSAT-2 images acquired over agriculture fields in the context of the AgriSAR 2009 campaign were used. Specifically, multioutput Gaussian Processes and multi-output Support Vector Machines, which are two powerful kernel-based methods, are implemented and assessed in the context of accuracy assessment of the biophysical parameter estimation.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134298028","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 : 2019-07-16DOI: 10.1109/Agro-Geoinformatics.2019.8820686
Yuan Li, Hongshuo Wang, Yan Wang, Jianxi Huang, Xiaodong Zhang
In recent years, frequent droughts have caused serious harm to the sustainable development of agriculture and food security. Based on the wide range and real time data, remote sensing was widely employed in drought monitoring. Many researchers have proposed a series of drought monitoring methods based on MODIS data over the past few decades. The AquaCrop model was released by FAO, which is suitable for crop growth monitoring in arid area with its simple interface, less input parameters and good simulation effect. AquaCrop model was applied to the researches on climate change, irrigation strategy, planting management and so on. Many scholars have verified the efficiency of AquaCrop model in arid areas of China. Since AquaCrop model is driven by water, it is reasonable to use it to monitor and reflect the drought process. This study was based on Terra-MODIS data products and agro-meteorological data during the year of 2007-2008, 2008-2009, 2009-2010 and 2011-2012 of Winter Wheat growth periods in Henan Province. In this study, firstly, localizing the AquaCrop by the simulated and observed Canopy Cover (CC), Biomass (B), Yield (Y) and 0-50cm Soil Water Content (SWC). The values between observed and simulated have good consistency, with R2 = 0.9289 of CC, R2 =0.9418 of B, R2 = 0.8309 of SWC. Meanwhile, the simulation results of four growth stages of winter wheat show that the model has good applicability and stability in Henan Province. Secondly, calculating TVDI using MODIS data in the same time range. Finally, analyzing the correlation between the results of two models and observed soil water content in different depth of soil layers. Similarly, the simulation accuracy of two models are better with shallow soil moisture. MODIS TVDI has a highest correlation with 30cm soil water content (r= -0.344), while AquaCrop model with 10cm (r=0.819). The research can provide important reference for drought monitoring of winter wheat and it is helpful for effective agriculture drought monitoring and decision-making.
{"title":"Winter Wheat Drought Monitoring with Multi-temporal MODIS data and AquaCrop Model—A Case Study in Henan Province","authors":"Yuan Li, Hongshuo Wang, Yan Wang, Jianxi Huang, Xiaodong Zhang","doi":"10.1109/Agro-Geoinformatics.2019.8820686","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820686","url":null,"abstract":"In recent years, frequent droughts have caused serious harm to the sustainable development of agriculture and food security. Based on the wide range and real time data, remote sensing was widely employed in drought monitoring. Many researchers have proposed a series of drought monitoring methods based on MODIS data over the past few decades. The AquaCrop model was released by FAO, which is suitable for crop growth monitoring in arid area with its simple interface, less input parameters and good simulation effect. AquaCrop model was applied to the researches on climate change, irrigation strategy, planting management and so on. Many scholars have verified the efficiency of AquaCrop model in arid areas of China. Since AquaCrop model is driven by water, it is reasonable to use it to monitor and reflect the drought process. This study was based on Terra-MODIS data products and agro-meteorological data during the year of 2007-2008, 2008-2009, 2009-2010 and 2011-2012 of Winter Wheat growth periods in Henan Province. In this study, firstly, localizing the AquaCrop by the simulated and observed Canopy Cover (CC), Biomass (B), Yield (Y) and 0-50cm Soil Water Content (SWC). The values between observed and simulated have good consistency, with R2 = 0.9289 of CC, R2 =0.9418 of B, R2 = 0.8309 of SWC. Meanwhile, the simulation results of four growth stages of winter wheat show that the model has good applicability and stability in Henan Province. Secondly, calculating TVDI using MODIS data in the same time range. Finally, analyzing the correlation between the results of two models and observed soil water content in different depth of soil layers. Similarly, the simulation accuracy of two models are better with shallow soil moisture. MODIS TVDI has a highest correlation with 30cm soil water content (r= -0.344), while AquaCrop model with 10cm (r=0.819). The research can provide important reference for drought monitoring of winter wheat and it is helpful for effective agriculture drought monitoring and decision-making.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114341747","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}
Timely and accurate prediction of rice yield information is closely related to the people’s livelihood, which has been attached great importance by all levels of government. Satellite remote sensing provides the possibility for large-scale crop yield estimation, but they are usually limited by spatial and spectral resolution. Unmanned Aerial Vehicles (UAV) remote sensing with hyperspectral sensors can obtain high spatial-temporal resolution and hyperspectral images on demand. Generally, time-series Vegetation Indices (VIs) are used for estimating grain yield. But multi-day vegetation indices may be affected by different background and illumination condition, so the differences between vegetation indices may include the effects induced from external condition, which will pose a negative effect on the accuracy of crop yield estimation. Therefore, in this study, the relative vegetation index and relative yield were proposed and used to estimate rice yield at pixel scale. And the optimal growth stages for crop yield estimation would also be determined. Hyperspectral images of critical rice growth stages at tillering stage, jointing stage, booting stage, heading stage, filling stage, ripening stage were obtained from July 28 to November 24 in 2017. Firstly, all possible two-band combinations of discrete channels from 500nm to 900nm was used to create Relative Normalized Difference Vegetation Index (RNDVI). Then the best RNDVI at different growth stages were determined for rice yield estimation. Finally, different combinations of growth stages were tested to obtain the optimal combinations for yield estimation. These models were validated at pixel scale using the measured yields. The result shows that four-growth-stage model with RNDVI[635, 784] at tillering stage, RNDVI[744,807] at jointing stage, RNDVI[712,784] at booting stage, RNDVI[736,816] at heading stage with the multiple linear regression function gain a higher R2 (0.74) and lower RMSE (248.97kg/ha). The mean absolute percentage error of estimated rice yield of 4.31%. Results shows that the yield estimations at pixel scale with relative vegetation indices were acceptable. In the study, a yield estimation method with relative vegetation indices is proposed and the optimal growth stage combinations for rice yield estimation were determined. This study explores the possibility of yield estimation at pixel scale using hyperspectral images from UAV platform, which will further improve the method system for remote sensing of yield estimation.
{"title":"Rice yield estimation at pixel scale using relative vegetation indices from unmanned aerial systems","authors":"Feilong Wang, Fumin Wang, Yao Zhang, Jinghui Hu, Jingfeng Huang, Lili Xie, Jingkai Xie","doi":"10.1109/Agro-Geoinformatics.2019.8820226","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820226","url":null,"abstract":"Timely and accurate prediction of rice yield information is closely related to the people’s livelihood, which has been attached great importance by all levels of government. Satellite remote sensing provides the possibility for large-scale crop yield estimation, but they are usually limited by spatial and spectral resolution. Unmanned Aerial Vehicles (UAV) remote sensing with hyperspectral sensors can obtain high spatial-temporal resolution and hyperspectral images on demand. Generally, time-series Vegetation Indices (VIs) are used for estimating grain yield. But multi-day vegetation indices may be affected by different background and illumination condition, so the differences between vegetation indices may include the effects induced from external condition, which will pose a negative effect on the accuracy of crop yield estimation. Therefore, in this study, the relative vegetation index and relative yield were proposed and used to estimate rice yield at pixel scale. And the optimal growth stages for crop yield estimation would also be determined. Hyperspectral images of critical rice growth stages at tillering stage, jointing stage, booting stage, heading stage, filling stage, ripening stage were obtained from July 28 to November 24 in 2017. Firstly, all possible two-band combinations of discrete channels from 500nm to 900nm was used to create Relative Normalized Difference Vegetation Index (RNDVI). Then the best RNDVI at different growth stages were determined for rice yield estimation. Finally, different combinations of growth stages were tested to obtain the optimal combinations for yield estimation. These models were validated at pixel scale using the measured yields. The result shows that four-growth-stage model with RNDVI[635, 784] at tillering stage, RNDVI[744,807] at jointing stage, RNDVI[712,784] at booting stage, RNDVI[736,816] at heading stage with the multiple linear regression function gain a higher R2 (0.74) and lower RMSE (248.97kg/ha). The mean absolute percentage error of estimated rice yield of 4.31%. Results shows that the yield estimations at pixel scale with relative vegetation indices were acceptable. In the study, a yield estimation method with relative vegetation indices is proposed and the optimal growth stage combinations for rice yield estimation were determined. This study explores the possibility of yield estimation at pixel scale using hyperspectral images from UAV platform, which will further improve the method system for remote sensing of yield estimation.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114703711","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 : 2019-07-16DOI: 10.1109/Agro-Geoinformatics.2019.8820699
Luyi Sun, Jinsong Chen, Yu Han
Cotton is an important crop playing a key role in both economy and regional environment. In recent years, remote sensing has become the most feasible tool of crop field mapping in large-scale. This study evaluates the feature fusion of time series Sentinel-1 (S1) and Sentienl-2 (S2) data for cotton filed mapping in heterogeneous smallholder agricultural systems in Xinjiang, China. A SHP (Statistically Homogeneous Pixel) algorithm originally used for identification of distributed scatterers in Interferometric Synthetic Aperture Radar (InSAR) applications was implemented in de-speckling of SAR intensities. A semi-automated approach based on Jeffries-Matusita (J-M) distance and Recursive Feature Elimination (RFE) algorithm was used to select optimal combination of SAR or/and optical features in the cotton field mapping to achieve highest accuracy. In experiments, we demonstrated that feature fusion of Sentinel-1&2 is able to improve the cotton mapping accuracy.
{"title":"Joint use of time series Sentinel-1 and Sentinel-2 imagery for cotton field mapping in heterogeneous cultivated areas of Xinjiang, China","authors":"Luyi Sun, Jinsong Chen, Yu Han","doi":"10.1109/Agro-Geoinformatics.2019.8820699","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820699","url":null,"abstract":"Cotton is an important crop playing a key role in both economy and regional environment. In recent years, remote sensing has become the most feasible tool of crop field mapping in large-scale. This study evaluates the feature fusion of time series Sentinel-1 (S1) and Sentienl-2 (S2) data for cotton filed mapping in heterogeneous smallholder agricultural systems in Xinjiang, China. A SHP (Statistically Homogeneous Pixel) algorithm originally used for identification of distributed scatterers in Interferometric Synthetic Aperture Radar (InSAR) applications was implemented in de-speckling of SAR intensities. A semi-automated approach based on Jeffries-Matusita (J-M) distance and Recursive Feature Elimination (RFE) algorithm was used to select optimal combination of SAR or/and optical features in the cotton field mapping to achieve highest accuracy. In experiments, we demonstrated that feature fusion of Sentinel-1&2 is able to improve the cotton mapping accuracy.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128511352","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}
Monitoring the spatial pattern and growth of sugarcane timely and accurately is of great importance at regional and global scales. In this paper, the focus was on sugarcane identification in Southern China with FuSui country as the study area. Classification was based on sentinel-1 different polarizations and sugarcane phenology. In order to explore the optimum periods and polar metric characters, time series of C-band dual polarization sentinel-1 data in 2017 totally 130 images were collected over the whole sugarcane growth season. Then the growth curve was built based on the former exploration. After that, there was a following analysis by combining growth curve and polarimetric characters of sugarcane, which contributes to setting attribute to identity. At last, the advanced rules were built to identify sugarcane according to growth curve above and subordinating degree function. Sugarcane extraction accuracy was verified by numerous ground data. The conclusions are as follows: (1) The results of this study show the importance of using C-band muti-temporal dual polarization data on crop identification especially for sugarcane comparing with traditional optical data. In other words, it’s crucial for crop identification to extract the backscattering coefficient. When combining with a part of samples, the curve of crop growth used for classification can be portrayed. To deepen the difference between sugarcane and other typical features, additional three kinds of reference object like eucalyptus, water and buildings, all of which distributes in the experimental area, with an extensive representation. (2) The analysis of polarimetric characters has shown that the inherent SAR backscatter feature VH is superior in classification accuracy to the VV, which achieved an accuracy of 88.07%. During the stage of seedling and tillering, the amplitude from sugarcane is higher than that in other objects, proving the advantage of VV in sugarcane identification. On the contrary, the giant grass and aiphyllium appearing stable in sequential variation, corresponding banana and eucalyptus respectively. (3) Moreover, the sugarcane has shown strong difference in March when it comes to the optimum periods, the data is more sensitive to the change of sugarcane. There was an evidently reduction as time goes by, so choosing the data from March makes higher accuracy. Therefore, the data from March with the polarimetric character VH was used as the optimum periods.
{"title":"Monitoring of Sugarcane Crop based on Time Series of Sentinel-1 data: a case study of Fusui, Guangxi","authors":"Xing Yuan, Hongzhong Li, Yu Han, Jinsong Chen, Xiaoning Chen","doi":"10.1109/Agro-Geoinformatics.2019.8820221","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820221","url":null,"abstract":"Monitoring the spatial pattern and growth of sugarcane timely and accurately is of great importance at regional and global scales. In this paper, the focus was on sugarcane identification in Southern China with FuSui country as the study area. Classification was based on sentinel-1 different polarizations and sugarcane phenology. In order to explore the optimum periods and polar metric characters, time series of C-band dual polarization sentinel-1 data in 2017 totally 130 images were collected over the whole sugarcane growth season. Then the growth curve was built based on the former exploration. After that, there was a following analysis by combining growth curve and polarimetric characters of sugarcane, which contributes to setting attribute to identity. At last, the advanced rules were built to identify sugarcane according to growth curve above and subordinating degree function. Sugarcane extraction accuracy was verified by numerous ground data. The conclusions are as follows: (1) The results of this study show the importance of using C-band muti-temporal dual polarization data on crop identification especially for sugarcane comparing with traditional optical data. In other words, it’s crucial for crop identification to extract the backscattering coefficient. When combining with a part of samples, the curve of crop growth used for classification can be portrayed. To deepen the difference between sugarcane and other typical features, additional three kinds of reference object like eucalyptus, water and buildings, all of which distributes in the experimental area, with an extensive representation. (2) The analysis of polarimetric characters has shown that the inherent SAR backscatter feature VH is superior in classification accuracy to the VV, which achieved an accuracy of 88.07%. During the stage of seedling and tillering, the amplitude from sugarcane is higher than that in other objects, proving the advantage of VV in sugarcane identification. On the contrary, the giant grass and aiphyllium appearing stable in sequential variation, corresponding banana and eucalyptus respectively. (3) Moreover, the sugarcane has shown strong difference in March when it comes to the optimum periods, the data is more sensitive to the change of sugarcane. There was an evidently reduction as time goes by, so choosing the data from March makes higher accuracy. Therefore, the data from March with the polarimetric character VH was used as the optimum periods.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133359510","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 : 2019-07-16DOI: 10.1109/Agro-Geoinformatics.2019.8820240
M. S. Rahman, L. Di, Zhiqi Yu, E. Yu, Junmei Tang, Li Lin, Chen Zhang, Juozas Gaigalas
GIS data layer on crop field boundary has many applications in agricultural research, ecosystem study, crop monitoring, and land management. Crop field boundary mapping through field survey is not time and cost effective for vast agriculture areas. Onscreen digitization on fine-resolution satellite image is also labor-intensive and error-prone. The recent development in image segmentation based on their spectral characteristics is promising for cropland boundary detection. However, processing of large volume multi-band satellite images often required high-performance computation systems. This study utilized crop rotation information for the delineation of field boundaries. In this study, crop field boundaries of Iowa in the United States are extracted using multi-year (2007-2018) CDL data. The process is simple compared to boundary extraction from multi-date remote sensing data. Although this process was unable to distinguish some adjacent fields, the overall accuracy is promising. Utilization of advanced geoprocessing algorithms and tools on polygon correction may improve the result significantly. Extracted field boundaries are validated by superimposing on fine resolution Google Earth images. The result shows that crop field boundaries can easily be extracted with reasonable accuracy using crop rotation information.
{"title":"Crop Field Boundary Delineation using Historical Crop Rotation Pattern","authors":"M. S. Rahman, L. Di, Zhiqi Yu, E. Yu, Junmei Tang, Li Lin, Chen Zhang, Juozas Gaigalas","doi":"10.1109/Agro-Geoinformatics.2019.8820240","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820240","url":null,"abstract":"GIS data layer on crop field boundary has many applications in agricultural research, ecosystem study, crop monitoring, and land management. Crop field boundary mapping through field survey is not time and cost effective for vast agriculture areas. Onscreen digitization on fine-resolution satellite image is also labor-intensive and error-prone. The recent development in image segmentation based on their spectral characteristics is promising for cropland boundary detection. However, processing of large volume multi-band satellite images often required high-performance computation systems. This study utilized crop rotation information for the delineation of field boundaries. In this study, crop field boundaries of Iowa in the United States are extracted using multi-year (2007-2018) CDL data. The process is simple compared to boundary extraction from multi-date remote sensing data. Although this process was unable to distinguish some adjacent fields, the overall accuracy is promising. Utilization of advanced geoprocessing algorithms and tools on polygon correction may improve the result significantly. Extracted field boundaries are validated by superimposing on fine resolution Google Earth images. The result shows that crop field boundaries can easily be extracted with reasonable accuracy using crop rotation information.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122632791","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 : 2019-07-16DOI: 10.1109/Agro-Geoinformatics.2019.8820242
U. Alganci, Elif Sertel, S. Kaya
This research aims to determine the flooded agricultural lands after the flood that occurred in April 2015 on the Menderes Plain. The unexpected heavy and continuous precipitation in spring season induced a flash flood on the Menderes River, which directly damaged the agricultural lands. The flooded areas are determined by geographic object based GEOBIA classification of normalized difference water index (NDWI) data calculated from after-disaster SPOT 6 satellite image and land cover type of the flooded areas are verified from pre-disaster SPOT 6 satellite image. Moreover, topographic characteristics of the flooded areas are produced from open access ALOS W3D DSM data in order to investigate the relationship between the flood and topography. Results of this research exhibited that, optical satellite images are feasible data sources in determining flooded areas due to unique reflectance responses of them especially in the green and near infrared portions of the spectrum. Both flood extent and agricultural parcels affected by the flood are accurately mapped by using SPOT 6 image and GEOBIA approach.
{"title":"Determination of the Flooded Agricultural Lands with Spot 6 High Resolution Satellite Images: A Case Study of Menderes Plain, Turkey","authors":"U. Alganci, Elif Sertel, S. Kaya","doi":"10.1109/Agro-Geoinformatics.2019.8820242","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820242","url":null,"abstract":"This research aims to determine the flooded agricultural lands after the flood that occurred in April 2015 on the Menderes Plain. The unexpected heavy and continuous precipitation in spring season induced a flash flood on the Menderes River, which directly damaged the agricultural lands. The flooded areas are determined by geographic object based GEOBIA classification of normalized difference water index (NDWI) data calculated from after-disaster SPOT 6 satellite image and land cover type of the flooded areas are verified from pre-disaster SPOT 6 satellite image. Moreover, topographic characteristics of the flooded areas are produced from open access ALOS W3D DSM data in order to investigate the relationship between the flood and topography. Results of this research exhibited that, optical satellite images are feasible data sources in determining flooded areas due to unique reflectance responses of them especially in the green and near infrared portions of the spectrum. Both flood extent and agricultural parcels affected by the flood are accurately mapped by using SPOT 6 image and GEOBIA approach.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133335934","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}
Due to the fact that volume of the national rural land contract management right data is large, the data are in different formats, the data types are many, and each single file is small, it introduces great challenges to the data transmission in distributed storage system. Data transmission rate is extremely slow, as most of data is small. This article aims to solve the data transmission problem when the rural land contract management right data is archived to the distributed storage system, and to further improve the efficiency of data backup. Firstly, according to the characteristics of rural land contract management right data, this article designs the framework model of distributed storage system, to archive the unstructured original data files. Secondly, based on a single-threaded tool RoboCopy, which is archiving tool and can be used to preserve a subset of data on target systems, this paper uses multi thread technology and design an archiving algorithm. The archiving algorithm assigns each copy task to multiple threads or multiple RoboCopy functions, so that multiple threads are processed concurrently and independently. Although the origin single thread copy ability is better that each thread in multiple threads in the archiving process, but the overall multi-threaded concurrent processing is superior to the origin single thread. Thirdly, using the multiple threaded archiving algorithm, this article design and implement an archiving system for administrator to archive the rural land contract management rights data. The archiving system contains a control flow for administrator to select administrative division, select data list, fill in ID, upload data list, select source data path, add notes, upload data, check consistence, and preserve the data to storage system. Lastly, this article uses and distributed storage system, presents a multi thread transmission algorithm, designs and implements an archiving system based on multithread technology. Finally, this paper takes the real rural land contract management right in Liuhe District of Jiangsu Province as an experiment dataset, and examines the overall effectiveness and usability of the archiving system. The experiment results demonstrate that multithreading technology can reduce the time of data transmission, and improve the efficiency of archiving process effectively; by increasing the number of threads, the efficiency of the data backup system reaches a stable optimal value in a certain number of threads, and although the number of threads is increased indefinitely, the performance of the archiving system will no longer improve. The archiving system designed in this paper can well solve the problem of storage of rural land contract management right data, which provides reference experience and assistance for similar research and application.
{"title":"Archiving System of Rural Land Contractual Management Right Data using Multithreading and Distributed Storage Technology","authors":"Jiajun Xu, Zhiyuan Pei, Lin Guo, Chunmei Zhao, Yin Zhang, Yuhang Liu, Fei Wang, Hualang Hu, Yanpeng Huang, Xuegang Zhang, Tuqiang Mai","doi":"10.1109/Agro-Geoinformatics.2019.8820485","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820485","url":null,"abstract":"Due to the fact that volume of the national rural land contract management right data is large, the data are in different formats, the data types are many, and each single file is small, it introduces great challenges to the data transmission in distributed storage system. Data transmission rate is extremely slow, as most of data is small. This article aims to solve the data transmission problem when the rural land contract management right data is archived to the distributed storage system, and to further improve the efficiency of data backup. Firstly, according to the characteristics of rural land contract management right data, this article designs the framework model of distributed storage system, to archive the unstructured original data files. Secondly, based on a single-threaded tool RoboCopy, which is archiving tool and can be used to preserve a subset of data on target systems, this paper uses multi thread technology and design an archiving algorithm. The archiving algorithm assigns each copy task to multiple threads or multiple RoboCopy functions, so that multiple threads are processed concurrently and independently. Although the origin single thread copy ability is better that each thread in multiple threads in the archiving process, but the overall multi-threaded concurrent processing is superior to the origin single thread. Thirdly, using the multiple threaded archiving algorithm, this article design and implement an archiving system for administrator to archive the rural land contract management rights data. The archiving system contains a control flow for administrator to select administrative division, select data list, fill in ID, upload data list, select source data path, add notes, upload data, check consistence, and preserve the data to storage system. Lastly, this article uses and distributed storage system, presents a multi thread transmission algorithm, designs and implements an archiving system based on multithread technology. Finally, this paper takes the real rural land contract management right in Liuhe District of Jiangsu Province as an experiment dataset, and examines the overall effectiveness and usability of the archiving system. The experiment results demonstrate that multithreading technology can reduce the time of data transmission, and improve the efficiency of archiving process effectively; by increasing the number of threads, the efficiency of the data backup system reaches a stable optimal value in a certain number of threads, and although the number of threads is increased indefinitely, the performance of the archiving system will no longer improve. The archiving system designed in this paper can well solve the problem of storage of rural land contract management right data, which provides reference experience and assistance for similar research and application.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114107157","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 : 2019-07-16DOI: 10.1109/Agro-Geoinformatics.2019.8820608
Sercan Aygün, Ece Olcay Günes, Mehmet Ali Subasi, Selim Alkan
Sensors in agriculture are in use from weather monitoring to autonomous watering. Using low-cost sensors allows designers to create a prototype for a hardware environment to implement data acquisition and mining process. Thus, the relation between sensors can be understood and a test environment for sensor fusion can be created. In this paper, different input devices are synchronized by using a microcontroller system and each data, obtained from the sensors, are sent wirelessly by an (Internet of Things) IoT device to the cloud, by recording and monitoring from the graphical user interface on the web as a real-time environment to apply data mining algorithms thereafter. This study uses the regression trees to obtain the sensor data relations from 8 different data related to light, temperature, humidity, rain, soil moisture, atmospheric pressure, air quality, and dew point. Each sensor data has a different effect on the agricultural monitoring, however, reducing the number of sensors can reduce the cost of a system, by giving still accurate observations via sensor substitution proposed. Therefore, by using the regression trees, the classification of sensor data is inspected in this study. A test prototype of the hardware together with the software design is created for data monitoring and sensor fusion in different combinations. In the end, after fusion tests for all possible cases, outstanding results for each sensor substitution is presented. Temperature and dew point can be obtained using other sensors by fusing the train data on the regression tree by 92% and 84% accuracy respectively with a 5% numerical error margin in the leaf nodes on the regression tree.
{"title":"Sensor Fusion for IoT-based Intelligent Agriculture System","authors":"Sercan Aygün, Ece Olcay Günes, Mehmet Ali Subasi, Selim Alkan","doi":"10.1109/Agro-Geoinformatics.2019.8820608","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820608","url":null,"abstract":"Sensors in agriculture are in use from weather monitoring to autonomous watering. Using low-cost sensors allows designers to create a prototype for a hardware environment to implement data acquisition and mining process. Thus, the relation between sensors can be understood and a test environment for sensor fusion can be created. In this paper, different input devices are synchronized by using a microcontroller system and each data, obtained from the sensors, are sent wirelessly by an (Internet of Things) IoT device to the cloud, by recording and monitoring from the graphical user interface on the web as a real-time environment to apply data mining algorithms thereafter. This study uses the regression trees to obtain the sensor data relations from 8 different data related to light, temperature, humidity, rain, soil moisture, atmospheric pressure, air quality, and dew point. Each sensor data has a different effect on the agricultural monitoring, however, reducing the number of sensors can reduce the cost of a system, by giving still accurate observations via sensor substitution proposed. Therefore, by using the regression trees, the classification of sensor data is inspected in this study. A test prototype of the hardware together with the software design is created for data monitoring and sensor fusion in different combinations. In the end, after fusion tests for all possible cases, outstanding results for each sensor substitution is presented. Temperature and dew point can be obtained using other sensors by fusing the train data on the regression tree by 92% and 84% accuracy respectively with a 5% numerical error margin in the leaf nodes on the regression tree.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125725823","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 : 2019-07-16DOI: 10.1109/Agro-Geoinformatics.2019.8820595
Zhiqi Yu, L. Di, Ruixin Yang, Junmei Tang, Li Lin, Chen Zhang, M. S. Rahman, Haoteng Zhao, Juozas Gaigalas, E. Yu, Ziheng Sun
Land use and land cover (LULC) classification using satellite images is an important approach to monitor changes on earth. To produce LULC maps, supervised classification methods are often used. For many supervised classification algorithms, independence of features is an implied assumption. However, this assumption is rarely tested. For LULC classification, using all bands as input features to models is the default approach. However, some of the bands may be highly correlated, which may cause model performances unstable. In this research, correlations and multicollinearity among multi-spectral bands are analyzed for four major LULC types, i.e. cropland, forest, developed area and water bodies. Guided by the correlation analysis, different band combinations were used to train Support Vector Machines (SVM) for four-class LULC classification and the results were compared. From our experiments, band 4, 5, 6 is the best three-band combination and band 1, 2, 5, 7 is the best four-band combination which achieved almost identical performance as using all bands for LULC classification.
{"title":"Selection of Landsat 8 OLI Band Combinations for Land Use and Land Cover Classification","authors":"Zhiqi Yu, L. Di, Ruixin Yang, Junmei Tang, Li Lin, Chen Zhang, M. S. Rahman, Haoteng Zhao, Juozas Gaigalas, E. Yu, Ziheng Sun","doi":"10.1109/Agro-Geoinformatics.2019.8820595","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820595","url":null,"abstract":"Land use and land cover (LULC) classification using satellite images is an important approach to monitor changes on earth. To produce LULC maps, supervised classification methods are often used. For many supervised classification algorithms, independence of features is an implied assumption. However, this assumption is rarely tested. For LULC classification, using all bands as input features to models is the default approach. However, some of the bands may be highly correlated, which may cause model performances unstable. In this research, correlations and multicollinearity among multi-spectral bands are analyzed for four major LULC types, i.e. cropland, forest, developed area and water bodies. Guided by the correlation analysis, different band combinations were used to train Support Vector Machines (SVM) for four-class LULC classification and the results were compared. From our experiments, band 4, 5, 6 is the best three-band combination and band 1, 2, 5, 7 is the best four-band combination which achieved almost identical performance as using all bands for LULC classification.","PeriodicalId":143731,"journal":{"name":"2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133011848","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：