- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Identifying Mangrove Species Using Field Close-Range Snapshot Hyperspectral Imaging and Machine-Learning Techniques
摘要： Investigating mangrove species composition is a basic and important topic in wetland management and conservation. This study aims to explore the potential of close-range hyperspectral imaging with a snapshot hyperspectral sensor for identifying mangrove species under field conditions. Specifically, we assessed the data pre-processing and transformation, waveband selection and machine-learning techniques to develop an optimal classification scheme for eight mangrove species in Qi’ao Island of Zhuhai, Guangdong, China. After data pre-processing and transformation, five spectral datasets, which included the reflectance spectra R and its first-order derivative d(R), the logarithm of the reflectance spectra log(R) and its first-order derivative d[log(R)], and hyperspectral vegetation indices (VIs), were used as the input data for each classifier. Consequently, three waveband selection methods, including the stepwise discriminant analysis (SDA), correlation-based feature selection (CFS), and successive projections algorithm (SPA) were used to reduce dimensionality and select the effective wavebands for identifying mangrove species. Furthermore, we evaluated the performance of mangrove species classification using four classifiers, including linear discriminant analysis (LDA), k-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM). Application of the four considered classifiers on the reflectance spectra of all wavebands yielded overall classification accuracies of the eight mangrove species higher than 80%, with SVM having the highest accuracy of 93.54% (Kappa = 0.9256). Using the selected wavebands derived from SPA, the accuracy of SVM reached 93.13% (Kappa = 0.9208). The addition of hyperspectral VIs and d[log(R)] spectral datasets further improves the accuracies to 93.54% (Kappa = 0.9253) and 96.46% (Kappa = 0.9591), respectively. These results suggest that it is highly effective to apply field close-range snapshot hyperspectral images and machine-learning classifiers to classify mangrove species.
关键词： machine learning,waveband selection,mangrove species classification,close-range hyperspectral imaging,field hyperspectral measurement
更新于2025-09-23 15:23:52
-
Individual mangrove tree measurement using UAV-based LiDAR data: Possibilities and challenges
摘要： Individual mangrove tree parameters are necessary for the efficient management and protection of this unique ecosystem, but to measure them using remote sensing (RS) is still a new and challenging task due to the high clumping density of mangrove crowns and the relatively low spatial resolution of RS data. Unmanned aerial vehicles (UAVs), as an emerging RS technique, significantly improves the spatial resolution, but has not been used for individual mangrove analysis. This study presents the first investigation into the possibility of individual tree detection and delineation (ITDD) for mangroves using light detection and ranging (LiDAR) data (91 pt./m2) collected from UAV. Specifically, we aim to detect and measure tree height (TH) and crown diameter (CD) of each mangrove tree, and analyze the impact of crown clumping density and spatial resolution on mangrove ITDD. To this end, we combined the variable window filtering method and marker controlled watershed segmentation algorithm, and successfully delineated 46.0% of the 126 field measured mangroves. This was promising considering the complexity of mangrove forest. TH and CD were estimated with higher accuracies than previous studies. The isolated trees, with the lowest clumping density, were delineated with the highest accuracy. To identify the optimal spatial resolution of canopy height model (CHM), we defined four spatial resolutions (0.1 m, 0.25 m, 0.5 m, and 1 m) and conducted a simulation. Based on the results, we propose a rule-of-thumb that the spatial resolution should be finer than one-fourth of CD for ITDD, which is also applicable to other forest types. The main difficulty for mangrove ITDD is an overall under-detection of trees, which is caused by the high clumping density and limited height difference between adjacent mangroves. We recommend combining UAV LiDAR with imagery and terrestrial LiDAR to improve the mangrove ITDD performance.
关键词： LiDAR,Unmanned aerial vehicle,Mangrove,Individual crown,Optimal spatial resolution
更新于2025-09-23 15:22:29
-
Diffuse Reflectance Spectroscopy (Vis-Nir-Swir) as a Promising Tool for Blue Carbon Quantification in Mangrove Soils: A Case of Study in Tropical Semiarid Climatic Conditions
摘要： The assessment of the soil organic carbon (SOC) stocks in mangrove ecosystems is essential for coastal management activities seeking the mitigation of CO2 emissions. However, the wet chemical analysis conventionally used to quantify SOC may overestimate SOC content due to oxidation of reduced compounds. This work focused on the use of diffuse reflectance spectroscopy (DRS) for predicting SOC in mangrove forest areas. When used properly, DRS may be, in some cases, a more accurate and more efficient method for the determination of SOC in mangrove soils than conventional analytical approaches. Furthermore, variable selection may simplify and improve prediction accuracy, reducing collinearity in the dataset used and allowing better SOC quantification through more interpretable and robust models.
关键词： Tropical semiarid climatic conditions,Mangrove soils,Vis-NIR-SWIR,Blue Carbon,Diffuse reflectance spectroscopy
更新于2025-09-23 15:21:01
-
Mapping Mangrove Forests of Dongzhaigang Nature Reserve in China Using Landsat 8 and Radarsat-2 Polarimetric SAR Data
摘要： Mangrove forests are distributed in intertidal regions that act as a “natural barrier” to the coast. They have enormous ecological, economic, and social value. However, the world’s mangrove forests are declining under immense pressure from anthropogenic and natural disturbances. Accurate information regarding mangrove forests is essential for their protection and restoration. The main objective of this study was to develop a method to improve the classification of mangrove forests using C-band quad-pol Synthetic Aperture Radar (SAR) data (Radarsat-2) and optical data (Landsat 8), and to analyze the spectral and backscattering signatures of mangrove forests. We used a support vector machine (SVM) classification method to classify the land use in Hainan Dongzhaigang National Nature Reserve (HDNNR). The results showed that the overall accuracy using only optical information was 83.5%. Classification accuracy was improved to a varying extent by the addition of different radar data. The highest overall accuracy was 95.0% based on a combination of SAR and optical data. The area of mangrove forest in the reserve was found to be 1981.7 ha, as determined from the group with the highest classification accuracy. Combining optical data with SAR data could improve the classification accuracy and be significant for mangrove forest conservation.
关键词： Landsat 8,mapping,Radasat-2,classification,SVM,mangrove forest
更新于2025-09-19 17:15:36
-
Remote sensing analysis of mangrove distribution and dynamics in Zhanjiang from 1991 to 2011
摘要： Mangrove forests provide valuable societal and ecological services and goods. However, they have been experiencing high annual rates of loss in many parts of the world. In order to evaluate a long-term wetland conservation strategy that compromises urban development with comprehensive wetland ecosystem management, remote sensing techniques were used to analyze the changing mangrove distribution in the Zhanjiang Mangrove Forest National Nature Reserve. Between 1991 and 2000, the mangrove area within the study region declined from 2 264.9 to 2 085.9 ha consistent with an annual decrease of 0.79%. However, there was an overall 34.3% increase in mangrove coverage from 2 085.9 to 2 801.8 ha between 2000 and 2011. Major causes of forest loss include local human pressures in the form of deforestation, conversion to agriculture, and natural forces such as erosion. The recent gain in mangrove forest cover is attributed to effective conservation management in the nature reserve area, including intensive mangrove plantation efforts and increased local awareness of wetland conservation.
关键词： HJ-1A,landsat TM/ETM+,conservation,mangrove,remote sensing
更新于2025-09-19 17:15:36
-
P‐9.9: Research on The New Display Technology ‐ Inkjet‐Printed Quantum Dot Display with Blue OLEDs
摘要： Direct discharge of aquaculture wastewater in coastal areas could increase concentrations of antibiotics in coastal mangrove forests. This study focused on the Gaoqiao Mangrove Nature Reserve in Zhanjiang City, Guangdong Province. Norfloxacin (NOR) residues in rhizosphere sediments, plant roots, branches, and leaves of two dominant mangrove communities, Rhizophora stylosa and Avicennia marina, the correlation between physical properties of rhizosphere deposition and residual NOR in sediments, and NOR accumulation in the root system were analyzed. Significant differences were noted in NOR residues in rhizosphere sediments of R. stylosa and A. marina, with higher NOR concentrations than those in other wetland sediments locally and abroad. NOR accumulation in R. stylosa was higher in the branches than in the roots and was also significantly higher than that in A. marina. Thus, both species could accumulate NOR from the environment with R. stylosa showing a stronger potential to purify the environment. Cation exchange capacity and total organic carbon could affect NOR distribution in the rhizosphere sediment, and total organic carbon content could reduce NOR uptake by mangrove roots. This study contributes to research on the migration and adsorption characteristics of antibiotics in mangrove wetlands.
关键词： mangrove ecosystems,migration characteristics,aquaculture wastewater,norfloxacin,residual characteristics
更新于2025-09-19 17:13:59
-
PEMANFAATAN CITRA SATELIT UNTUK PENENTUAN LAHAN KRITIS MANGROVE DI KECAMATAN TUGU, KOTA SEMARANG
摘要： This study aims to mapping the level of degraded land of mangrove forest area In TUGU Sub-district, Semarang, by comparing the results between the Landsat 7 ETM + images of 2009 and ALOS AVNIR-2 in 2009. In determining the degradation of mangrove forest area, we used geographic information systems and remote sensing as a tool of analysis that is based on three (3) criteria; land use type, canopy density, and soil resilience from abrasion. From 2 satellite image data used, it will be supervised image classification using ER Mapper software to get the criteria type of land use and density of the canopy. For soil resilience from abrasion, we used soil types reclassification techniques, using ArcGIS software. Based on Landsat imagery, obtained results 92.22 % of mangrove forest area included in severely damaged condition and 7.78% is included in the category of moderate damage. Meanwhile, based on the results of ALOS image, 77.73 % of mangrove areas in severely damaged condition and 22.27 % are included in the category of moderate damage. From this study, it can be concluded that ALOS and Landsat Imagery is good for the determination and identifying critical mangrove area and distribution of mangrove forests, but the degraded land of mangrove maps generated by Landsat, less detailed than ALOS in classification and representation the conditions of critical mangrove area in Tugu sub-district.
关键词： Satellite Imagery,GIS,Mangrove,Critical Land,Remote Sensing
更新于2025-09-04 15:30:14
-
Mapping of mangrove coverage and canopy height using LiDAR data at Sangkulirang District, East Kutai, East Borneo
摘要： Light Detection and Ranging (LiDAR) is remote sensing technology using transmitted properties of scattered light to detect the intended target. This technology potentially used for spatial planning and management, including mangrove monitoring. The purpose of this research was to map the mangrove coverage and canopy height using airborne LiDAR data at mangrove areas of Sangkulirang district, East Kutai, East Borneo. The corrected point cloud LiDAR data inputed into 10 blocks boundary. This data is classified into 7 classes (ground, mangroves, non mangroves, water, vehicle, low point and isolated point). Ground class used as the data source for digital terrain model (DTM) while mangrove class used as the data source for digital surface model (DSM). The substraction from overlaying DTM - DSM will produce canopy height model (CHM) that represent the height of mangroves canopy from land. The result of this research showed that mangrove distribution had an area of 64.07 km2. The height of mangrove canopy was dominated by 10-30 meters height while the maximum height reached 54.04 meters.
关键词： canopy height,mangrove,digital terrain model,digital surface model,LiDAR
更新于2025-09-04 15:30:14