DOI: 10.1016/j.jag.2014.05.009
Scopus记录号: 2-s2.0-84904761645
论文题名: Evaluating total inorganic nitrogen in coastal waters through fusion of multi-temporal RADARSAT-2 and optical imagery using random forest algorithm
作者: Liu M ; , Liu X ; , Li J ; , Ding C ; , Jiang J
刊名: International Journal of Applied Earth Observation and Geoinformation
ISSN: 15698432
出版年: 2014
卷: 33, 期: 1 起始页码: 192
结束页码: 202
语种: 英语
英文关键词: Multisensor data fusion
; Optical images
; RADARSAT-2 images
; Random forest algorithm
; Total inorganic nitrogen
Scopus关键词: algorithm
; coastal water
; inorganic nitrogen
; nutrient
; open water
; radar imagery
; RADARSAT
; remote sensing
; satellite imagery
; spatial distribution
; synthetic aperture radar
; temporal distribution
; China
; Hong Kong
英文摘要: Satellites routinely provide frequent, large-scale, near-surface views of many oceanographic variables pertinent to plankton ecology. However, the nutrient fertility of water can be challenging to detect accurately using remote sensing technology. This research has explored an approach to estimate the nutrient fertility in coastal waters through the fusion of synthetic aperture radar (SAR) images and optical image susing the random forest (RF) algorithm. The estimation of total inorganic nitrogen (TIN) in the Hong Kong Sea, China, was used as a case study. In March of 2009 and May and August of 2010, a sequence of multitemporal in situ data and CCD images from China's HJ-1 satellite and RADARSAT-2 images were acquired. Four sensitive parameters were selected as input variables to evaluate TIN: single-band reflectance, a normalized difference spectral index (NDSI) and HV and VH polarizations. The RF algorithm was used to merge the different input variables from the SAR and optical imagery to generate a new dataset (i.e., the TIN outputs). The results showed the temporal-spatial distribution of TIN. The TIN values decreased from coastal waters to the open water areas, and TIN values in the northeast area were higher than those found in the southwest region of the study area. The maximum TIN values occurred in May. Additionally, the estimation accuracy for estimating TIN was significantly improved when the SAR and optical data were used in combination rather than a single data type alone. This study suggests that this method of estimating nutrient fertility in coastal waters by effectively fusing data from multiple sensors is very promising. © 2014 Elsevier B.V. Citation statistics:
资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/79781
Appears in Collections: 气候变化事实与影响
There are no files associated with this item.
作者单位: China University of Geosciences, School of Information Engineering, 29 Xueyuan Road, Beijing 100083, China; National Marine Data and Information Service, Tianjin 300171, China
Recommended Citation:
Liu M,, Liu X,, Li J,et al. Evaluating total inorganic nitrogen in coastal waters through fusion of multi-temporal RADARSAT-2 and optical imagery using random forest algorithm[J]. International Journal of Applied Earth Observation and Geoinformation,2014-01-01,33(1)