LiDAR data are becoming increasingly available,which has opened up many new applications.One such application is crop type mapping.Accurate crop type maps are critical for monitoring water use,estimating harvests and ...LiDAR data are becoming increasingly available,which has opened up many new applications.One such application is crop type mapping.Accurate crop type maps are critical for monitoring water use,estimating harvests and in precision agriculture.The traditional approach to obtaining maps of cultivated fields is by manually digitizing the fields from satellite or aerial imagery and then assigning crop type labels to each field-often informed by data collected during ground and aerial surveys.However,manual digitizing and labeling is time-consuming,expensive and subject to human error.Automated remote sensing methods is a cost-effective alternative,with machine learning gaining popularity for classifying crop types.This study evaluated the use of LiDAR data,Sentinel-2 imagery,aerial imagery and machine learning for differentiating five crop types in an intensively cultivated area.Different combinations of the three datasets were evaluated along with ten machine learning.The classification results were interpreted by comparing overall accuracies,kappa,standard deviation and f-score.It was found that LiDAR data successfully differentiated between different crop types,with XGBoost providing the highest overall accuracy of 87.8%.Furthermore,the crop type maps produced using the LiDAR data were in general agreement with those obtained by using Sentinel-2 data,with LiDAR obtaining a mean overall accuracy of 84.3%and Sentinel-2 a mean overall accuracy of 83.6%.However,the combination of all three datasets proved to be the most effective at differentiating between the crop types,with RF providing the highest overall accuracy of 94.4%.These findings provide a foundation for selecting the appropriate combination of remotely sensed data sources and machine learning algorithms for operational crop type mapping.展开更多
Present study attempts to understand the potential of multispectral ASTER (Advanced space borne thermal emission and reflection radiometer) data for spatial mapping of kimberlite. Kimberlite is an economic rock known ...Present study attempts to understand the potential of multispectral ASTER (Advanced space borne thermal emission and reflection radiometer) data for spatial mapping of kimberlite. Kimberlite is an economic rock known for hosting diamond. Kimberlite also has petrogenetic importance for giving us clue on the composition of lower part of the mantle. Kimberlites often contain serpentine, carbonate minerals;which have their diagnostic spectral signatures in short wave infrared (SWIR) domain. In the present study, attempt is made to delineate kimberlite from adjacent granite-granodiorite gneiss based on processing of the ASTER data as ASTER’s spectral channels can detect some of the diagnostic absorption features of kimberlites. But it has been observed that the kimberlites are difficult to be delineated by processing the ASTER data using correlative information of both sub-pixel and per-pixel mapping. Moreover, smaller spatial size of kimberlites with respect to pixel size of ASTER SWIR channels further obscures the spectral feature of kimberlite. Therefore, an attempt is also made to understand how intra pixel spectral mixing of kimberlite and granite granodiorite-gneiss modifies the diagnostic spectral feature of kimberlite. It is observed that spectral feature of kimberlites would be obscured when it is has very small spatial size (one-tenth of pixel) with respect to pixel size. Moreover, calcrete developed in the adjacent soil has identical absorption feature similar to the spectral features of kimberlites imprinted in the respective ASTER convolved spectral profiles. This also has resulted false-positives in ASTER image when we use spectral feature as a tool for spatial mapping of kimberlite. Therefore hyperspectral data with high spatial and spectral resolution is required for targeting kimberlites instead of using broad band spectral feature of kimberlites.展开更多
Accurate impervious surface estimation(ISE)is challenging due to the diversity of land covers and the vegetation phenology and climate.This study investigates the variation of impervious surfaces estimated from differ...Accurate impervious surface estimation(ISE)is challenging due to the diversity of land covers and the vegetation phenology and climate.This study investigates the variation of impervious surfaces estimated from different seasons of satellite images and the seasonal sensitivity of different methods.Four Landsat ETM?images of four different seasons and two popular methods(i.e.artificial neural network(ANN)and support vector machine(SVM))are employed to estimate the impervious surface on the pixel level.Results indicate that winter(dry season)is the best season to estimate impervious surface even though plants are not in their growing season.Less cloud and less variable source areas(VSA)(seasonal water body)become the major advantages of winter for the ISE,as cloud is easily confusedwith bright impervious surfaces,andwater in VSA is confusedwith dark impervious surfaces due to their similar spectral reflectance.For the seasonal sensitivity of methods,ANN appears more stable as its accuracy varied less than that obtained with SVM.However,both the methods showed a general consistency of the seasonal changes of the accuracy,indicating that winter time is the best season for impervious surfaces estimation with optical satellite images in subtropical monsoon regions.展开更多
基金This work forms part of a larger project titled“Salt Accumulation and Waterlogging Monitoring System(SAWMS)Development”which was initiated and funded by the Water Research Commission(WRC)of South Africa(contract number K5/2558//4)More information about this project is available in WRC Report No TT 782/18,titled SALT ACCUMULATION AND WATERLOGGING MONITORING SYSTEM(SAWMS)DEVELOPMENT(ISBN 978-0-6392-0084-2)+1 种基金available at www.wrc.org.za.This work was also supported by the National Research Foundation(grant number 112300)The authors would also like to thank www.linguafix.net for their language editing services.
文摘LiDAR data are becoming increasingly available,which has opened up many new applications.One such application is crop type mapping.Accurate crop type maps are critical for monitoring water use,estimating harvests and in precision agriculture.The traditional approach to obtaining maps of cultivated fields is by manually digitizing the fields from satellite or aerial imagery and then assigning crop type labels to each field-often informed by data collected during ground and aerial surveys.However,manual digitizing and labeling is time-consuming,expensive and subject to human error.Automated remote sensing methods is a cost-effective alternative,with machine learning gaining popularity for classifying crop types.This study evaluated the use of LiDAR data,Sentinel-2 imagery,aerial imagery and machine learning for differentiating five crop types in an intensively cultivated area.Different combinations of the three datasets were evaluated along with ten machine learning.The classification results were interpreted by comparing overall accuracies,kappa,standard deviation and f-score.It was found that LiDAR data successfully differentiated between different crop types,with XGBoost providing the highest overall accuracy of 87.8%.Furthermore,the crop type maps produced using the LiDAR data were in general agreement with those obtained by using Sentinel-2 data,with LiDAR obtaining a mean overall accuracy of 84.3%and Sentinel-2 a mean overall accuracy of 83.6%.However,the combination of all three datasets proved to be the most effective at differentiating between the crop types,with RF providing the highest overall accuracy of 94.4%.These findings provide a foundation for selecting the appropriate combination of remotely sensed data sources and machine learning algorithms for operational crop type mapping.
文摘Present study attempts to understand the potential of multispectral ASTER (Advanced space borne thermal emission and reflection radiometer) data for spatial mapping of kimberlite. Kimberlite is an economic rock known for hosting diamond. Kimberlite also has petrogenetic importance for giving us clue on the composition of lower part of the mantle. Kimberlites often contain serpentine, carbonate minerals;which have their diagnostic spectral signatures in short wave infrared (SWIR) domain. In the present study, attempt is made to delineate kimberlite from adjacent granite-granodiorite gneiss based on processing of the ASTER data as ASTER’s spectral channels can detect some of the diagnostic absorption features of kimberlites. But it has been observed that the kimberlites are difficult to be delineated by processing the ASTER data using correlative information of both sub-pixel and per-pixel mapping. Moreover, smaller spatial size of kimberlites with respect to pixel size of ASTER SWIR channels further obscures the spectral feature of kimberlite. Therefore, an attempt is also made to understand how intra pixel spectral mixing of kimberlite and granite granodiorite-gneiss modifies the diagnostic spectral feature of kimberlite. It is observed that spectral feature of kimberlites would be obscured when it is has very small spatial size (one-tenth of pixel) with respect to pixel size. Moreover, calcrete developed in the adjacent soil has identical absorption feature similar to the spectral features of kimberlites imprinted in the respective ASTER convolved spectral profiles. This also has resulted false-positives in ASTER image when we use spectral feature as a tool for spatial mapping of kimberlite. Therefore hyperspectral data with high spatial and spectral resolution is required for targeting kimberlites instead of using broad band spectral feature of kimberlites.
基金The ETM+data from USGS are highly appreciated.This study is jointly supported by the CUHK Direct Grants(2021103)Hong Kong Research Grants Council(RGC)General Research Grants(GRF)project(CUHK 459210 and 457212)+2 种基金Hong Kong Innovation and Technology Fund(GHP/002/11GD)the funding of Shenzhen Municipal Science and Technology Innovation Council(JCYJ20120619151239947)the National Key Technol-ogies R&D Program in the 12th Five Year Plan of China(2012BAH32B03).
文摘Accurate impervious surface estimation(ISE)is challenging due to the diversity of land covers and the vegetation phenology and climate.This study investigates the variation of impervious surfaces estimated from different seasons of satellite images and the seasonal sensitivity of different methods.Four Landsat ETM?images of four different seasons and two popular methods(i.e.artificial neural network(ANN)and support vector machine(SVM))are employed to estimate the impervious surface on the pixel level.Results indicate that winter(dry season)is the best season to estimate impervious surface even though plants are not in their growing season.Less cloud and less variable source areas(VSA)(seasonal water body)become the major advantages of winter for the ISE,as cloud is easily confusedwith bright impervious surfaces,andwater in VSA is confusedwith dark impervious surfaces due to their similar spectral reflectance.For the seasonal sensitivity of methods,ANN appears more stable as its accuracy varied less than that obtained with SVM.However,both the methods showed a general consistency of the seasonal changes of the accuracy,indicating that winter time is the best season for impervious surfaces estimation with optical satellite images in subtropical monsoon regions.
