Pub Date : 2019-07-01DOI: 10.1109/Agro-Geoinformatics.2019.8820234
Yuanyuan Chen, Xueting Li, Min Min
Mapping for terrestrial ecosystem service has exponentially soared in recent years, which provides a reliable theoretical foundation for acknowledging functions, valuation and management of various kinds of ecosystem services. This study was conducted by collecting peer reviewed papers from 2000 to 2018, and establishing a relevant database of 113 papers. Forest, grassland, wetland and desert were selected as four basic components of terrestrial ecosystem. As a result, researches on mapping for terrestrial ecosystem services in each continent could be found, and medium geographical scale is the most widely preferred by researchers. Services origined from different ecosystem might share similar qualities, thus it is hard to identify them when researches refer to only one ecosystem or specific services. Models combining with relevant approaches applied in mapping can complement each other. In conclusion, maps for demonstrating hotspots and effects of climate changes are promising to make a significant progress in the future. Moreover, it is essential for districts and countries to select adaptable mapping methods and models according to their own demands. Drivers like needs for management and governmental planning, cognition of ecosystem services and disservices will motivate researches and the application of mapping forward.
{"title":"Mapping for terrestrial ecosystem services: a review","authors":"Yuanyuan Chen, Xueting Li, Min Min","doi":"10.1109/Agro-Geoinformatics.2019.8820234","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820234","url":null,"abstract":"Mapping for terrestrial ecosystem service has exponentially soared in recent years, which provides a reliable theoretical foundation for acknowledging functions, valuation and management of various kinds of ecosystem services. This study was conducted by collecting peer reviewed papers from 2000 to 2018, and establishing a relevant database of 113 papers. Forest, grassland, wetland and desert were selected as four basic components of terrestrial ecosystem. As a result, researches on mapping for terrestrial ecosystem services in each continent could be found, and medium geographical scale is the most widely preferred by researchers. Services origined from different ecosystem might share similar qualities, thus it is hard to identify them when researches refer to only one ecosystem or specific services. Models combining with relevant approaches applied in mapping can complement each other. In conclusion, maps for demonstrating hotspots and effects of climate changes are promising to make a significant progress in the future. Moreover, it is essential for districts and countries to select adaptable mapping methods and models according to their own demands. Drivers like needs for management and governmental planning, cognition of ecosystem services and disservices will motivate researches and the application of mapping forward.","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":"114973688","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.2019.8820423
Melise Pinar, G. Erpul
Evaluation indicators and parameters of land use and cover change have been drawing a significant attention as approaches for Sustainable Land Management (SLM), Sustainable Soil Management (SSM), Land Degradation Neutrality (LDN), Conservation Agriculture (CA), Climate Smart Agriculture (CSA) etc. increasingly progress to sustain and promote above and below-ground ecosystem services for human wellbeing. Most of the relevant models duly strive to improve their capability and propriety of assessing temporal-spatial cover change trend using remote sensing tools. Exclusively, from the perspective of different earth surface hydrological and erosional processes, not only over a period of years, rotational management systems of agricultural land require understanding of variations but within a year, as well. In this study, two different NDVI(Normalized Different Vegetation Index) metrics derived from satellite images of Pleiades 1A-1B and Spot-7 (NDVIsat and NDVIgm, respectively) and ground-measurements by hand-held crop sensor to obtain LAI (Leaf Area Index) were used to determine within a year variations occurred at different crop-stages of wheat and sunflower plots in semi-arid cropping systems in Turkey. Rough Fallow (Period F), Seedbed (Period SB), Establishment (Period 1 for sunflower), Development (Period 2 for wheat) and Maturing (Period 3) constituted measurement stages. In general, correlation analysis showed results from all three methodologies (NDVIsat, NDVIgm and LAI) were highly correlated one another at each growth stage. Exceptionally, NDVIsat, NDVIgm and LAI were poorly correlated at Period 1 and Period 3, respectively, for sunflower and wheat. To a great extent this was ascribed to the fact that wheat photosynthetic activity inversely varied with its leaf area index at Period 3 and the fact that vegetation cover rate of sunflower showed kind of fluctuations that hindered a clear gradient to emerge in Period 1. Also, the means of measurements of different growth stages for each research method were compared by ANOVA test, and all three methodologies statistically detected differences as the photosynthetic activity either increased or decreased among the wheat and sunflower growth stages with few exceptions. For instance, the LAI could not mark any significant difference between Period F and Period SB in wheat plots while NDVI-sat showed no statistically significant difference between Period F and Period 3 in sunflower. For either crops it was clearly observable from both satellite and ground measurements that the NDVI values increased as photosynthetic activity was approaching its maximum level, after which it decreased with the start of maturement; on the other hand, rather than photosynthetic activity, the LAI reached maximum values as the number and periphery of leave layers increased, which was much more notable for sunflowers. Consequently, study methods led to much clearer results for horizontally growing sunflower plots than thos
{"title":"Monitoring land cover changes during different growth stages of semi-arid cropping systems of wheat and sunflower by NDVI and LAI","authors":"Melise Pinar, G. Erpul","doi":"10.1109/Agro-Geoinformatics.2019.8820423","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820423","url":null,"abstract":"Evaluation indicators and parameters of land use and cover change have been drawing a significant attention as approaches for Sustainable Land Management (SLM), Sustainable Soil Management (SSM), Land Degradation Neutrality (LDN), Conservation Agriculture (CA), Climate Smart Agriculture (CSA) etc. increasingly progress to sustain and promote above and below-ground ecosystem services for human wellbeing. Most of the relevant models duly strive to improve their capability and propriety of assessing temporal-spatial cover change trend using remote sensing tools. Exclusively, from the perspective of different earth surface hydrological and erosional processes, not only over a period of years, rotational management systems of agricultural land require understanding of variations but within a year, as well. In this study, two different NDVI(Normalized Different Vegetation Index) metrics derived from satellite images of Pleiades 1A-1B and Spot-7 (NDVIsat and NDVIgm, respectively) and ground-measurements by hand-held crop sensor to obtain LAI (Leaf Area Index) were used to determine within a year variations occurred at different crop-stages of wheat and sunflower plots in semi-arid cropping systems in Turkey. Rough Fallow (Period F), Seedbed (Period SB), Establishment (Period 1 for sunflower), Development (Period 2 for wheat) and Maturing (Period 3) constituted measurement stages. In general, correlation analysis showed results from all three methodologies (NDVIsat, NDVIgm and LAI) were highly correlated one another at each growth stage. Exceptionally, NDVIsat, NDVIgm and LAI were poorly correlated at Period 1 and Period 3, respectively, for sunflower and wheat. To a great extent this was ascribed to the fact that wheat photosynthetic activity inversely varied with its leaf area index at Period 3 and the fact that vegetation cover rate of sunflower showed kind of fluctuations that hindered a clear gradient to emerge in Period 1. Also, the means of measurements of different growth stages for each research method were compared by ANOVA test, and all three methodologies statistically detected differences as the photosynthetic activity either increased or decreased among the wheat and sunflower growth stages with few exceptions. For instance, the LAI could not mark any significant difference between Period F and Period SB in wheat plots while NDVI-sat showed no statistically significant difference between Period F and Period 3 in sunflower. For either crops it was clearly observable from both satellite and ground measurements that the NDVI values increased as photosynthetic activity was approaching its maximum level, after which it decreased with the start of maturement; on the other hand, rather than photosynthetic activity, the LAI reached maximum values as the number and periphery of leave layers increased, which was much more notable for sunflowers. Consequently, study methods led to much clearer results for horizontally growing sunflower plots than thos","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":"121218205","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.2019.8820500
A. Moomen, M. Bertolotto, Pierre Lacroix, David G. Jensen
This paper explores the spatial relationship between mining and agricultural activities towards meeting the United Nations (UN) Agenda 2030 Sustainable Development Goals (SDGs) in Northwest Ghana. Agenda 2030 SDGs highlight the importance of poverty reduction, livelihood enhancement, and food security. A state's natural resources include both nonagricultural and agricultural resources. There is a renewed interest in large-scale mining in Ghana, entering into previously underexplored areas in the Northwest, an area dominated by agriculture. With the emergence of mining in this region, this study combines both satellite imagery, covering years 2000, 2010 and 2018, and ground truthing data to conduct baseline studies and assess changes in land use over time. We compared known data sets and field knowledge with satellite data to objectively measure changes in the distribution of surface water, farmlands and grasscover over time. The study finds increasing areas of surface water, abundant grasscover and farmlands within leases in the area. These growing abundance of land use and land cover types provide opportunities for commercial livestock keeping, extensive and intensive crop farming. The classified satellite images revealed the existence of more farmlands and potential cultivable areas than reported by agriculture extension offices. Most of these areas overlap with mining concessions and could be modelled for commercial food production and local job creation. The occurrence of mining and agricultural activities in rural subsistence farming communities often indicate conflict. However, a co-exitence of both sectors has a strong opportunity to drive inclusive growth for smallholder farmers; reduce poverty, generate income and uphold sustainable development.
{"title":"Exploring Spatial Symbiosis of Agriculture and Mining for Sustainable Development in Northwest Ghana","authors":"A. Moomen, M. Bertolotto, Pierre Lacroix, David G. Jensen","doi":"10.1109/Agro-Geoinformatics.2019.8820500","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820500","url":null,"abstract":"This paper explores the spatial relationship between mining and agricultural activities towards meeting the United Nations (UN) Agenda 2030 Sustainable Development Goals (SDGs) in Northwest Ghana. Agenda 2030 SDGs highlight the importance of poverty reduction, livelihood enhancement, and food security. A state's natural resources include both nonagricultural and agricultural resources. There is a renewed interest in large-scale mining in Ghana, entering into previously underexplored areas in the Northwest, an area dominated by agriculture. With the emergence of mining in this region, this study combines both satellite imagery, covering years 2000, 2010 and 2018, and ground truthing data to conduct baseline studies and assess changes in land use over time. We compared known data sets and field knowledge with satellite data to objectively measure changes in the distribution of surface water, farmlands and grasscover over time. The study finds increasing areas of surface water, abundant grasscover and farmlands within leases in the area. These growing abundance of land use and land cover types provide opportunities for commercial livestock keeping, extensive and intensive crop farming. The classified satellite images revealed the existence of more farmlands and potential cultivable areas than reported by agriculture extension offices. Most of these areas overlap with mining concessions and could be modelled for commercial food production and local job creation. The occurrence of mining and agricultural activities in rural subsistence farming communities often indicate conflict. However, a co-exitence of both sectors has a strong opportunity to drive inclusive growth for smallholder farmers; reduce poverty, generate income and uphold sustainable development.","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":"122747200","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.2019.8820656
Xin Chen, Li Jiang, Guoliang Zhang, Lijun Meng, Pingli An
Agricultural production capacity in Farmingpastoral Ecotone of Northern China (FPENC) has been limited to long-standing water shortage and drought. In this context, the center pivot irrigation (CPI) exhibited a widespread adoption in recent years to increase utilization efficiency of agricultural water and crop yield. However, the high rate of groundwater extraction by CPI, reducing the aquifer saturated thickness, has large potential impacts on aboveground vegetation growth. And, we lack the knowledge of the temporal and spatial variations of CPI in FPENC. In this paper, taking Ulanqab as an example, we measured spatio-temporal patterns of CPI from 2008 to 2017 using Landsat TM/ETM+/OLI data and spatial autocorrelation methods. The results indicated that the number of CPI increased first and then decreased, reaching a peak of 1243 in 2015. There was a positive spatial autocorrelation in the spatial distribution of CPI, that is, it had a very obvious spatial clustering characteristics. The degree of spatial agglomeration increased from 0.283 in 2008 to 0.526 in 2017. The results of local spatial autocorrelation showed that the spatial agglomeration pattern of Ulanqab was dominated by High-High agglomeration. These obtained results can provide a strong basis for decision-making in formulating sustainable agricultural development strategies.
{"title":"Spatial differentiation of center pivot irrigation in a farming-pastoral ecotone of Northern China: A case study in Ulanqab","authors":"Xin Chen, Li Jiang, Guoliang Zhang, Lijun Meng, Pingli An","doi":"10.1109/Agro-Geoinformatics.2019.8820656","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820656","url":null,"abstract":"Agricultural production capacity in Farmingpastoral Ecotone of Northern China (FPENC) has been limited to long-standing water shortage and drought. In this context, the center pivot irrigation (CPI) exhibited a widespread adoption in recent years to increase utilization efficiency of agricultural water and crop yield. However, the high rate of groundwater extraction by CPI, reducing the aquifer saturated thickness, has large potential impacts on aboveground vegetation growth. And, we lack the knowledge of the temporal and spatial variations of CPI in FPENC. In this paper, taking Ulanqab as an example, we measured spatio-temporal patterns of CPI from 2008 to 2017 using Landsat TM/ETM+/OLI data and spatial autocorrelation methods. The results indicated that the number of CPI increased first and then decreased, reaching a peak of 1243 in 2015. There was a positive spatial autocorrelation in the spatial distribution of CPI, that is, it had a very obvious spatial clustering characteristics. The degree of spatial agglomeration increased from 0.283 in 2008 to 0.526 in 2017. The results of local spatial autocorrelation showed that the spatial agglomeration pattern of Ulanqab was dominated by High-High agglomeration. These obtained results can provide a strong basis for decision-making in formulating sustainable agricultural development strategies.","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":"125773539","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.2019.8820469
Xiaomei Zhang, T. Long, G. He, Yantao Guo
Nowadays, the access of Landsat data-sets and the ever-lowering costs of computing make it feasible to monitor the Earth’s land cover at Landsat resolutions of 30 meter. However, the rapid forest-covered products on a large scale, such as intercontinental or global, is still challenging. By utilizing the huge catalog of satellite imagery as well as the high-performance computing capacity of Google Earth Engine, we proposed an automated pipeline for generating 30-meter resolution global-scale forest map from time-series of Landsat images, and a novel 30-meter resolution global forest map of 2018 is released. In this paper, we describe the methods to create products of forest cover at Landsat resolutions. First, we partitioned the landscapes into sub-regions of similar forest type and spatial continuity, thus maximizing spectral differentiation, simplifying classifier model and improving classification accuracy. Then, with the existing forest cover, which come from a variety of sources, a multi-source forest/non-forest sample set was established for machine algorithm learning training. Finally, a machine learning algorithm was used to obtain samples automatically, extract the characteristics of satellite images and establish the forest / non-forest classifier models. Taking the Landsat8 images in 2018 as a case, selecting satellite image features based on the study of forest reflectance, including onboard reflectivity, the index of forest vegetation and the texture features of each band, using established forest eco-zoning and multi-source forest / non-forest sample points, we realized automated learning and classification of forest cover for three initial zones. The accuracy verification of forest cover products in the three region was carried on two aspects: collecting verification points on high resolution satellite imagery (e.g. google earth), and cross-validating the current globally disclosed forest cover products. These two methods will illustrate the accuracy of the forest cover product.
{"title":"Gobal Forest Cover Mapping using Landsat and Google Earth Engine cloud computing","authors":"Xiaomei Zhang, T. Long, G. He, Yantao Guo","doi":"10.1109/Agro-Geoinformatics.2019.8820469","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820469","url":null,"abstract":"Nowadays, the access of Landsat data-sets and the ever-lowering costs of computing make it feasible to monitor the Earth’s land cover at Landsat resolutions of 30 meter. However, the rapid forest-covered products on a large scale, such as intercontinental or global, is still challenging. By utilizing the huge catalog of satellite imagery as well as the high-performance computing capacity of Google Earth Engine, we proposed an automated pipeline for generating 30-meter resolution global-scale forest map from time-series of Landsat images, and a novel 30-meter resolution global forest map of 2018 is released. In this paper, we describe the methods to create products of forest cover at Landsat resolutions. First, we partitioned the landscapes into sub-regions of similar forest type and spatial continuity, thus maximizing spectral differentiation, simplifying classifier model and improving classification accuracy. Then, with the existing forest cover, which come from a variety of sources, a multi-source forest/non-forest sample set was established for machine algorithm learning training. Finally, a machine learning algorithm was used to obtain samples automatically, extract the characteristics of satellite images and establish the forest / non-forest classifier models. Taking the Landsat8 images in 2018 as a case, selecting satellite image features based on the study of forest reflectance, including onboard reflectivity, the index of forest vegetation and the texture features of each band, using established forest eco-zoning and multi-source forest / non-forest sample points, we realized automated learning and classification of forest cover for three initial zones. The accuracy verification of forest cover products in the three region was carried on two aspects: collecting verification points on high resolution satellite imagery (e.g. google earth), and cross-validating the current globally disclosed forest cover products. These two methods will illustrate the accuracy of the forest cover product.","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":"127737258","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.2019.8820604
R. Nasirzadehdizaji, F. B. Sanli, Z. Çakır, Elif Sertel
Investigation of radar and optical data indices that contain a lot more information on landscapes and vegetation dynamics can be useful to identify opportunities and challenges in agricultural activities. In addition, the potential of synchronous implications of radar and optical data will be an effective method for agro-environmental monitoring and management to promote economic and environmental sustainability as monitoring programs. Crop discrimination as an agricultural monitoring system is a critical step regarding to estimate the area allocated to each crop type, computing statistics for crop control of area-based subsidies or crop production forecasting, environmental impact analysis and some other applications. Integrating both optical (reflectance) and Synthetic Aperture Radar (backscatter) multi-temporal features provides some advantages in terms of a more reliable crop map. We utilize multi-temporal Sentinel-1 Synthetic Aperture Radar (SAR) imagery and Sentinel-2 optical datasets in order to investigate the performance of the sensors backscatter and reflectance for temporal crop type mapping and the sustainable management of agricultural activities. Multi-temporal Sentinel-1, C-band VV and VH polarized SAR data and Sentinel2 optical data were acquired simultaneously by in-situ measurements for the study area. As preliminary results, it is concluded that the classification accuracies were improved results (5%) with using combinations of sensors. Classification accuracies of 93% were achieved in this study with integration use of SAR and optical data.
{"title":"Crop Mapping Improvement by Combination of Optical and SAR datasets","authors":"R. Nasirzadehdizaji, F. B. Sanli, Z. Çakır, Elif Sertel","doi":"10.1109/Agro-Geoinformatics.2019.8820604","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820604","url":null,"abstract":"Investigation of radar and optical data indices that contain a lot more information on landscapes and vegetation dynamics can be useful to identify opportunities and challenges in agricultural activities. In addition, the potential of synchronous implications of radar and optical data will be an effective method for agro-environmental monitoring and management to promote economic and environmental sustainability as monitoring programs. Crop discrimination as an agricultural monitoring system is a critical step regarding to estimate the area allocated to each crop type, computing statistics for crop control of area-based subsidies or crop production forecasting, environmental impact analysis and some other applications. Integrating both optical (reflectance) and Synthetic Aperture Radar (backscatter) multi-temporal features provides some advantages in terms of a more reliable crop map. We utilize multi-temporal Sentinel-1 Synthetic Aperture Radar (SAR) imagery and Sentinel-2 optical datasets in order to investigate the performance of the sensors backscatter and reflectance for temporal crop type mapping and the sustainable management of agricultural activities. Multi-temporal Sentinel-1, C-band VV and VH polarized SAR data and Sentinel2 optical data were acquired simultaneously by in-situ measurements for the study area. As preliminary results, it is concluded that the classification accuracies were improved results (5%) with using combinations of sensors. Classification accuracies of 93% were achieved in this study with integration use of SAR and optical data.","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":"124700403","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.2019.8820237
Ying Zhang, Di Wang, Qingbo Zhou
Classification and recognition of crops is an important prerequisite for crop yield estimation and crop growth monitoring. Rapid and accurate acquisition of crop type, spatial distribution and area information can provide basic basis for crop planting structure optimization and structural reform of agricultural supply side. It is of great significance to the formulation of agricultural policy, the development of social economy and the guarantee of national food security. In recent years, hyperspectral remote sensing has been able to fine classify crop types and varieties and obtain spatial distribution maps and planting structure information of crops by virtue of its many bands, abundant spectral information and sensitivity to small spectral differences among ground objects. This paper summarizes the application of hyperspectral remote sensing in crop fine classification, summarizes the hyperspectral data sources commonly used in crop fine classification at home and abroad, such as Hyperion data, environmental satellite data, CASI data and OMIS data, and analyses the applicability of various data. Meanwhile, the methods of crop fine classification using hyperspectral remote sensing are summarized, including decision tree classification, support vector machine classification, multi-classifier integration, spatial-spectral feature classification, hyperspectral data and radar data fusion classification, and the characteristics of various classification methods are analyzed. It was found that the classification accuracy of crop fine classification based on hyperspectral data was higher (better than 90%). But there are still some shortcomings: (1) At present, scholars at home and abroad focus on areas with simple planting structure. Most of the crop types in these areas are rice, wheat and other large-scale food crops, but less on cash crops such as sesame, rape, peanut and so on. (2) Hyperspectral remote sensing has high classification accuracy for regions with fewer crop types, but the classification accuracy needs to be improved in regions with many crop types. (3) Hyperspectral data has a high dimension and a large amount of data processing workload, which is not suitable for fine classification of crops in large-scale areas. Future research directions: (1) Expanding the scope of hyperspectral remote sensing monitoring objects, mainly cash crops. (2) Selecting areas with complex planting structure, fragmented plots, fluctuating topography and various crop types for fine classification of crops. (3) Attaching importance to the essential features of hyperspectral remote sensing fine classification and finding a stable classifier which is generally suitable for crop fine classification. (4) The mechanism of crop fine classification using hyperspectral remote sensing and the method of multi-source data fusion need to be further studied.
{"title":"Advances in crop fine classification based on Hyperspectral Remote Sensing","authors":"Ying Zhang, Di Wang, Qingbo Zhou","doi":"10.1109/Agro-Geoinformatics.2019.8820237","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820237","url":null,"abstract":"Classification and recognition of crops is an important prerequisite for crop yield estimation and crop growth monitoring. Rapid and accurate acquisition of crop type, spatial distribution and area information can provide basic basis for crop planting structure optimization and structural reform of agricultural supply side. It is of great significance to the formulation of agricultural policy, the development of social economy and the guarantee of national food security. In recent years, hyperspectral remote sensing has been able to fine classify crop types and varieties and obtain spatial distribution maps and planting structure information of crops by virtue of its many bands, abundant spectral information and sensitivity to small spectral differences among ground objects. This paper summarizes the application of hyperspectral remote sensing in crop fine classification, summarizes the hyperspectral data sources commonly used in crop fine classification at home and abroad, such as Hyperion data, environmental satellite data, CASI data and OMIS data, and analyses the applicability of various data. Meanwhile, the methods of crop fine classification using hyperspectral remote sensing are summarized, including decision tree classification, support vector machine classification, multi-classifier integration, spatial-spectral feature classification, hyperspectral data and radar data fusion classification, and the characteristics of various classification methods are analyzed. It was found that the classification accuracy of crop fine classification based on hyperspectral data was higher (better than 90%). But there are still some shortcomings: (1) At present, scholars at home and abroad focus on areas with simple planting structure. Most of the crop types in these areas are rice, wheat and other large-scale food crops, but less on cash crops such as sesame, rape, peanut and so on. (2) Hyperspectral remote sensing has high classification accuracy for regions with fewer crop types, but the classification accuracy needs to be improved in regions with many crop types. (3) Hyperspectral data has a high dimension and a large amount of data processing workload, which is not suitable for fine classification of crops in large-scale areas. Future research directions: (1) Expanding the scope of hyperspectral remote sensing monitoring objects, mainly cash crops. (2) Selecting areas with complex planting structure, fragmented plots, fluctuating topography and various crop types for fine classification of crops. (3) Attaching importance to the essential features of hyperspectral remote sensing fine classification and finding a stable classifier which is generally suitable for crop fine classification. (4) The mechanism of crop fine classification using hyperspectral remote sensing and the method of multi-source data fusion need to be further studied.","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":"127197229","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.2019.8820678
C. Ikiel, B. Ustaoğlu, D. Koç, A. A. Dutucu
In this study, land cover in Datça - Bozburun Special Environmental Protection Area was determined and limited changes were analyzed with satellite images and field research. The study area is the two peninsulas at the south west of Turkey surrounded by the Aegean Sea and Mediterranean Sea. The land is generally composed of mountainous and hilly terrains where mesozoic limestones are common. There are many gulfs and bays on the shores of both peninsulas. Mediterranean climate and vegetation are observed in the study area. Although there have been human settlements since ancient times, the land structure and limited agricultural areas prevented the presence of excess population. The port of Knidos on the western end of the Datça Peninsula was an important settlement developed in the past by maritime exportation, especially with the export of wine. Today, it attracts attention with its coastal tourism and some agricultural products (Olive, Almond, Carob etc.). The fact that the research area was announced as a special environmental-protection area prevented the changes in large-scale land cover and use. However, there are some limited changes around the bays and settlements. In this research, LANDSAT 7 ETM + (1997), SPOT 6/7 (2016), SPOT 6/7 (2018) satellite images and topographic maps were used. Satellite images were analyzed with ERDAS imagine software. Land cover was classified according to CORINE land cover classification system. Supervised classification was applied according to maximum likelihood method in remote sensing systems. Accuracy analysis of the classification was performed with Kappa statistics and it was determined as over 80%. The results obtained were also confirmed by the findings obtained from land studies. Accordingly, a decrease was identified in forests and semi-natural areas and agricultural areas and an increase was identified in artificial surfaces and open space with little or no vegetation.
{"title":"Determination of Land Cover Change in Datça and Bozburun Peninsula in Turkey (1997-2018)","authors":"C. Ikiel, B. Ustaoğlu, D. Koç, A. A. Dutucu","doi":"10.1109/Agro-Geoinformatics.2019.8820678","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820678","url":null,"abstract":"In this study, land cover in Datça - Bozburun Special Environmental Protection Area was determined and limited changes were analyzed with satellite images and field research. The study area is the two peninsulas at the south west of Turkey surrounded by the Aegean Sea and Mediterranean Sea. The land is generally composed of mountainous and hilly terrains where mesozoic limestones are common. There are many gulfs and bays on the shores of both peninsulas. Mediterranean climate and vegetation are observed in the study area. Although there have been human settlements since ancient times, the land structure and limited agricultural areas prevented the presence of excess population. The port of Knidos on the western end of the Datça Peninsula was an important settlement developed in the past by maritime exportation, especially with the export of wine. Today, it attracts attention with its coastal tourism and some agricultural products (Olive, Almond, Carob etc.). The fact that the research area was announced as a special environmental-protection area prevented the changes in large-scale land cover and use. However, there are some limited changes around the bays and settlements. In this research, LANDSAT 7 ETM + (1997), SPOT 6/7 (2016), SPOT 6/7 (2018) satellite images and topographic maps were used. Satellite images were analyzed with ERDAS imagine software. Land cover was classified according to CORINE land cover classification system. Supervised classification was applied according to maximum likelihood method in remote sensing systems. Accuracy analysis of the classification was performed with Kappa statistics and it was determined as over 80%. The results obtained were also confirmed by the findings obtained from land studies. Accordingly, a decrease was identified in forests and semi-natural areas and agricultural areas and an increase was identified in artificial surfaces and open space with little or no vegetation.","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":"114574196","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.2019.8820487
Jiahui Wang, Liang Liang, Han Li, Chunyang Chen, Ting Huang, Di Geng
The thematic report on "Temporal and Spatial Distribution of Global Carbon Sources and Sinks" is an important part of "Annual Report on Remote Sensing Monitoring of Global Ecological Environment" in 2018. The thematic report gives full play to the technological advantages of TanSat, the first global scientific experimental satellite for monitoring atmospheric carbon dioxide in China, monitors and analyses the temporal and spatial distribution pattern of global atmospheric carbon dioxide from 2010 to 2017 combining with multi-source remote sensing data, generates the first TanSat global chlorophyll fluorescence product in 2017, analyses the temporal and spatial distribution of carbon sources and sinks in the world and key regions, discusses the driving mechanism of global carbon source and sink change, and provides effective scientific data for realizing national emission reduction targets and coping with climate change. The report pointed out that TanSat can accurately retrieve the atmosphericCO2 column concentration and monitor the atmospheric CO2 concentration distribution. TanSat is an important part of the global multi-satellite carbon concentration observation platform and contributes to the construction of the GEO carbon concentration observation system. However, the global carbon concentration remote sensing observation is difficult to achieve all-weather, All-perspective and all-round real-time monitoring of carbon emissions and terrestrial carbon sources and sinks. The construction of global carbon concentration satellite monitoring network still needs the joint efforts of all countries to improve.
{"title":"Interpretation of the Report on Temporal Dynamics and Spatial Distribution of Global Carbon Source and Sink","authors":"Jiahui Wang, Liang Liang, Han Li, Chunyang Chen, Ting Huang, Di Geng","doi":"10.1109/Agro-Geoinformatics.2019.8820487","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820487","url":null,"abstract":"The thematic report on \"Temporal and Spatial Distribution of Global Carbon Sources and Sinks\" is an important part of \"Annual Report on Remote Sensing Monitoring of Global Ecological Environment\" in 2018. The thematic report gives full play to the technological advantages of TanSat, the first global scientific experimental satellite for monitoring atmospheric carbon dioxide in China, monitors and analyses the temporal and spatial distribution pattern of global atmospheric carbon dioxide from 2010 to 2017 combining with multi-source remote sensing data, generates the first TanSat global chlorophyll fluorescence product in 2017, analyses the temporal and spatial distribution of carbon sources and sinks in the world and key regions, discusses the driving mechanism of global carbon source and sink change, and provides effective scientific data for realizing national emission reduction targets and coping with climate change. The report pointed out that TanSat can accurately retrieve the atmosphericCO2 column concentration and monitor the atmospheric CO2 concentration distribution. TanSat is an important part of the global multi-satellite carbon concentration observation platform and contributes to the construction of the GEO carbon concentration observation system. However, the global carbon concentration remote sensing observation is difficult to achieve all-weather, All-perspective and all-round real-time monitoring of carbon emissions and terrestrial carbon sources and sinks. The construction of global carbon concentration satellite monitoring network still needs the joint efforts of all countries to improve.","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":"128203544","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.2019.8820664
Yiting Liu, Wenjiao Shi
The disturbance of food production and the reduction of crop yields were observed due to droughts and flood locally and globally in recent decades. Previous studies used crop models to simulate the response of crop yields to some indices of extreme weather. However, most of these studies did not detect the impacts of droughts and floods quantitatively. In this paper, the statistical data of sown area (SA), covered area (CA) and affected area (AA) during 1982-2012, and crop yields and production of maize, rice, wheat and soybean in China during 1979-2015 in provincial level were collected. Using these data, we counted the occurrence frequency of droughts and floods. In different major grain-producing areas (MGPA) of China, the superposed epoch analysis (SEA) method was applied to detect the quantitative impacts of droughts and floods on the crop yields and production during different periods (1982-1997, 1998-2012). The results presented that main crops had a 4.4%-6.8% yield and production reduction due to flood, and wider impacts on production and yield of main crops due to droughts were observed, with decreases ranging from 3.7% to 9.2%. Maize and soybean were more sensitive to drought in the whole China, especially in the NEC, with the significant reduction of 10.4%-17.2% in the NEC and 6.4%9.2% in the whole China. In China, both droughts and floods affected wheat yield with significant decreases of 4.3% and 6.1%, respectively. Moreover, different types of rice had various responses to droughts and floods. Early rice was sensitive to floods in China and in the mid-lower reaches of the Yangtze River (MLYR), but middle-season rice seemed to be sensitive to both droughts and flood in China. Meanwhile, crops responses during different periods varied, but did not have great difference of reduction between two periods. The spatio-temporal identification of quantitative impacts of drought and flood on crop yields and production in China is essential for applying suitable adaptions, such as better irrigation and basic construction in cropland to decrease the negative effects of droughts and floods on crops to guarantee the food security in China.
{"title":"The quantitative impacts of drought and flood on crop yields and production in China","authors":"Yiting Liu, Wenjiao Shi","doi":"10.1109/Agro-Geoinformatics.2019.8820664","DOIUrl":"https://doi.org/10.1109/Agro-Geoinformatics.2019.8820664","url":null,"abstract":"The disturbance of food production and the reduction of crop yields were observed due to droughts and flood locally and globally in recent decades. Previous studies used crop models to simulate the response of crop yields to some indices of extreme weather. However, most of these studies did not detect the impacts of droughts and floods quantitatively. In this paper, the statistical data of sown area (SA), covered area (CA) and affected area (AA) during 1982-2012, and crop yields and production of maize, rice, wheat and soybean in China during 1979-2015 in provincial level were collected. Using these data, we counted the occurrence frequency of droughts and floods. In different major grain-producing areas (MGPA) of China, the superposed epoch analysis (SEA) method was applied to detect the quantitative impacts of droughts and floods on the crop yields and production during different periods (1982-1997, 1998-2012). The results presented that main crops had a 4.4%-6.8% yield and production reduction due to flood, and wider impacts on production and yield of main crops due to droughts were observed, with decreases ranging from 3.7% to 9.2%. Maize and soybean were more sensitive to drought in the whole China, especially in the NEC, with the significant reduction of 10.4%-17.2% in the NEC and 6.4%9.2% in the whole China. In China, both droughts and floods affected wheat yield with significant decreases of 4.3% and 6.1%, respectively. Moreover, different types of rice had various responses to droughts and floods. Early rice was sensitive to floods in China and in the mid-lower reaches of the Yangtze River (MLYR), but middle-season rice seemed to be sensitive to both droughts and flood in China. Meanwhile, crops responses during different periods varied, but did not have great difference of reduction between two periods. The spatio-temporal identification of quantitative impacts of drought and flood on crop yields and production in China is essential for applying suitable adaptions, such as better irrigation and basic construction in cropland to decrease the negative effects of droughts and floods on crops to guarantee the food security in China.","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":"128702867","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：