Detection of coffee berry necrosis by digital image processing of landsat 8 oli satellite imagery     

《International Journal of Applied Earth Observation and Geoinformation》2020

Coffee berry necrosis is a fungal disease that, at a high level, significantly affects coffee productivity. With the advent of surface mapping satellites, it was possible to obtain information about the spectral signature of the crop on a time scale pertinent to the monitoring and detection of plant phenological changes. The objective of this paper was to define the best machine learning algorithm that is able to classify the incidence CBN as a function of Landsat 8 OLI images in different atmospheric correction methods. Landsat 8 OLI images were acquired at the dates closest to sampling anthracnose field data at three times corresponding to grain filling period and were submitted to atmospheric corrections by DOS, ATCOR, and 6SV methods. The images classified by the algorithms of machine learning, Random Forest, Multilayer Perceptron and Naive Bayes were tested 30 times in random sampling. Given the overall accuracy of each test, the algorithms were evaluated using the Friedman and Nemenyi tests to identify the statistical difference in the treatments. The obtained results indicated that the overall accuracy and the balanced accuracy index were on an average around 0.55 and 0.45, respectively, for the Naive Bayes and Multilayer Perceptron algorithms in the ATCOR atmospheric correction. According to the Friedman and Nemenyi tests, both algorithms were defined as the best classifiers. These results demonstrate that Landsat 8 OLI images were able to identify an incidence of the coffee berry necrosis by means of machine learning techniques, a fact that cannot be observed by the Pearson correlation.  相似文献   

Regional soil organic carbon prediction model based on a discrete wavelet analysis of hyperspectral satellite data     

《International Journal of Applied Earth Observation and Geoinformation》2020

Most studies have the achieved rapid and accurate determination of soil organic carbon (SOC) using laboratory spectroscopy; however, it remains difficult to map the spatial distribution of SOC. To predict and map SOC at a regional scale, we obtained fourteen hyperspectral images from the Gaofen-5 (GF-5) satellite and decomposed and reconstructed the original reflectance (OR) and the first derivative reflectance (FDR) using discrete wavelet transform (DWT) at different scales. At these different scales, as inputs, we selected the 3 optimal bands with the highest weight coefficient using principal component analysis and chose the normalized difference index (NDI), ratio index (RI) and difference index (DI) with the strongest correlation with the SOC content using a contour map method. These inputs were then used to build regional-scale SOC prediction models using random forest (RF), support vector machine (SVM) and back-propagation neural network (BPNN) algorithms. The results indicated that: 1) at a low decomposition scale, DWT can effectively eliminate the noise in satellite hyperspectral data, and the FDR combined with DWT can improve the SOC prediction accuracy significantly; 2) the method of selecting inputs using principal component analysis and a contour map can eliminate the redundancy of hyperspectral data while retaining the physical meaning of the inputs. For the model with the highest prediction accuracy, the inputs were all derived from the wavelength range of SOC variations; 3) the differences in prediction accuracy among the different prediction models are small; and 4) the SOC prediction accuracy using hyperspectral satellite data is greatly improved compared with that of previous SOC prediction studies using multispectral satellite data. This study provides a highly robust and accurate method for predicting and mapping regional SOC contents.  相似文献   

ENSO事件对西北太平洋热带气旋影响的分级研究   总被引：2，自引：0，他引：2  

曹智露  胡邦辉  杨修群  王学忠  何雪松  谭言科 《海洋学报》2013,35(2):21-34

采用1951-2006年联合台风警报中心(JTWC)最佳路径数据集和气候预测中心(CPC) ENSO资料,分析了西北太平洋不同等级热带气旋累积能量(accumulated cyclone energy,ACE)与ENSO指数之间的关系.结果表明;ACE与ENSO指数间存在正相关关系;分级热带气旋中,ENSO事件主要通过超强台风(Super TY)的活动与ACE指数联系起来的,超强台风频数在El Ni(n)o期间多于La Ni(n)a 期间,同时持续时间也更长;ENSO指数和热带气旋活跃季超强台风ACE指数的滞后相关(ENSO指数滞后5个月内)与它们的同时相关大小相当.此外,还研究了分级热带气旋持续时间、强度和频数分别对ACE指数的贡献,结果显示超强台风频数的贡献最大.接下来,利用1951-2006年不同ENSO位相情况下NCEP再分析资料,分析了ENSO影响超强台风发生发展的物理机制.主要结论为:西北太平洋存在一些SuperTY频数与源地分布在ENSO年与平常年相比有明显差异的关键区;ENSO事件改变关键区低层相对涡度以及海表温度是其影响SuperTY源地及频数变化的重要途径.  相似文献   

连续降温对大菱鲆成鱼代谢机能的影响   总被引：2，自引：0，他引：2  

纪利芹  蒋克勇  韩龙江  袁坤山  邱楚雯  王宝杰  刘梅  王雷  温海深 《海洋科学》2014,38(5):46-53

为了探寻连续降温对大菱鲆(Scophthalmus maximus)成鱼血清、肝脏及肌肉能量代谢等指标的影响,作者将大菱鲆从正常养殖水温18℃快速、连续降温至1℃,并在18℃、13℃、8℃、5℃、3℃和1℃共计6个温度点取血采样,分别测定血清中的总蛋白(TP)、白蛋白(ALB)、高密度脂蛋白胆固醇(HDL-C)、低密度脂蛋白胆固醇(LDL-C)、甘油三酯(TG)、总胆固醇(TC)、血糖(GLU)以及肝脏中的糖原和肌肉中的乳酸等指标。结果发现,随着温度降低,大菱鲆的血清TP浓度呈先下降后升高的趋势,各实验组与对照组无显著差异(P0.05),但在13℃和3℃之间出现显著性差异(P0.05);血清ALB浓度则呈现升高趋势,在3℃时显著高于1℃(P0.05);血清TC浓度呈现升高趋势,且3℃时显著高于18℃(P0.05);GLU浓度呈先降低后升高趋势,且8℃、5℃、3℃实验组浓度显著高于其余实验组(P0.05);尿素浓度呈先降低后升高再降低趋势,且8℃时显著高于1℃(P0.05);肝糖原浓度呈先降低后升高趋势,且8、5、3℃实验组浓度显著高于其余实验组(P0.05);肌肉中乳酸含量呈先升高后降低趋势,且5℃时显著高于18℃(P0.05);其余指标则无显著性差异(P0.05)。结果表明:当温度在18~8℃时,降温对大菱鲆体内代谢影响不大;当温度降到8~3℃时,大菱鲆体内开始出现应激反应;当温度继续降低至1℃时,大菱鲆体内的各种代谢基本处于停滞状态。综合分析各温度下的代谢指标得出结论,3~1℃温度区间与大菱鲆的生态冰温点比较接近,可以在此温度区间附近进一步进行无水保活的探索,在保证大菱鲆无水运输可行性的基础上优化经济成本。  相似文献   

深海沉积物分类与命名的参数指标和主成分分析   总被引：1，自引：0，他引：1  

张富元  章伟艳  张霄宇  陈奎英  孟翊  姚旭莹  赵宏樵 《海洋学报》2010,32(6):118-129

对于南海中部(118个表层沉积物样,水深82~4 420 m)、东部(106个表层沉积物样,水深700~4 508 m)海域的表层沉积物的粒度资料按小于200 m,200~2 000 m,大于2 000 m水深段对水深、平均粒径、黏土含量进行统计分析,结果表明从陆架到陆坡再到深海,平均粒径和黏土含量随水深增加呈非常有规律的变化;把大于2 000 m水深区域再细分为大于2 500 m,大于3 000 m,大于3 500 m,结果表明平均粒径和黏土含量随水深增加几乎无变化,在南海中部水深大于2 000 m海域平均粒径为3.39~3.54μm,黏土平均含量为54.91%~55.47%;在南海东部水深大于2 000 m海域平均粒径为3.25~3.37μm,黏土平均含量为53.91%~54.56%。研究表明2 000 m水深具有划分深海沉积物的指示意义。南海中部水深大于2 000 m海域黏土平均含量为55.19%,平均粒径为3.39μm;在南海东部水深大于2 000 m海域黏土平均含量为53.91%,平均粒径为3.37μm;在南海中部、东部水深大于2 000 m海域平均粒径均小于4μm,黏土平均含量均大于50%,表明深海沉积物粒度特征是平均粒径小于4μm和黏土平均含量大于50%。黏土含量是非生物组分的代表和划分深海沉积物类型的一个独立参数,钙质生物和硅质生物组分是另外两个独立参数。南海东部海域表层沉积物中55种元素总含量为47.50%,硅、铝、钛、钠、钾、磷、钙、镁、铁、锰十种主元素含量为47.03%,其他45种元素含量为0.47%,虽然沉积物来源复杂、成因不同,但沉积物化学主成分并不复杂,主要由前10种主元素和氧元素组成。沉积物主元素铝、钙、硅分别富集于黏土、钙质沉积、硅质沉积中。通过建立沉积物生源组分与碳酸钙、三氧化二铝、二氧化硅的量化关系,可把碳酸钙、生物二氧化硅作为钙质生物和硅质生物的两个替代参数。  相似文献   

Response of BITS (a benthic index based on taxonomic sufficiency) to water and sedimentary variables and comparison with other indices in three Adriatic lagoons     

Cristina Munari  Elena Manini  Antonio Pusceddu  Roberto Danovaro  & Michele Mistri 《Marine Ecology》2009,30(2):255-268

The European Water Framework Directive (WFD, 2000/60/EC) recommends the development of biotic indices for assessing the ecological quality status of water bodies. The Benthic Index based on Taxonomic Sufficiency (BITS) was specifically developed for lagoonal systems, according to the tolerant/opportunistic approach. Macrobenthic data, variables indicative of eutrophication and variables indicative of sedimentary organic matter quality were collected during 18 surveys carried out between 2004 and 2005 in three Adriatic coastal lagoons (Venice Lagoon, Sacca di Goro, Lesina Lagoon). The relationship between environmental variables and biotic indices (AMBI, BENTIX, BITS, BOPA and FINE) was tested using multivariate analyses. Indices based on species classification level appeared to relate better with the variables describing organic matter quality, whereas BITS, which is based on family classification level, seemed related to eutrophication indicative variables, such as sulphide, ammonium, dissolved oxygen and orthophosphate concentrations. The BITS approach reduces the costs associated with sorting and identification of organisms. Providing a rapid assessment of ecological quality, and producing an ecologically relevant classification, BITS seems a promising tool for monitoring programs of Adriatic lagoonal ecosystems. Its sensitivity in reflecting the field conditions elsewhere, however, remains to be assessed.  相似文献   

Biometric,microstructural, and high-resolution trace element studies in Crassostrea gigas of Cantabria (Bay of Biscay,Spain): Anthropogenic and seasonal influences     

R. Higuera-Ruiz  J. Elorza 《Estuarine, Coastal and Shelf Science》2009

Living Crassostrea gigas oysters of different ages and sizes were collected in three estuaries of Cantabria (Bay of Biscay, Spain): San Vicente de la Barquera Estuary, Santander Bay, and Marismas de Santoña Estuary. The main objective was to determine different shell responses to variable environmental parameters. A shell morphological study, based on three biometric indices, indicates that oysters of Santander Bay have two significant shell anomalies: abnormal thickening of the right valve and loss of vital cavity volume. These shell abnormalities are related with the presence in these waters of the chemical tributyltin. In the other two estuaries, the oysters show no detectable anomalies. Four shell microstructures have been distinguished: Regular Simple Prismatic, Regular Foliated, cone-Complex Cross Foliated, and Chalk. In Santander Bay oysters, the Chalk forms a “root-type” framework, whereas in the other two estuaries it forms a more compact microstructure. It is proposed that exposure to tributyltin has produced this modification. High-spatial-resolution geochemical transects have been carried out on the Regular Foliated microstructure in the umbo region in order to evaluate the distribution of Mg, Sr, and Na. The elements analysed exhibit clear cyclic variations in San Vicente de la Barquera Estuary and Marismas de Santoña Estuary oysters, related with seasonal periods, and characterised by broad maxima during months in which the waters are warmer and have higher salinity. These patterns are buffered in Santander Bay oysters. Our results demonstrate that biometric, microstructural, and high-resolution trace element studies in oyster shells can provide information about contaminants and seasonal variations in the estuarine environment.  相似文献   

海洋生态系统健康评价的底栖生物指数法研究进展   总被引：2，自引：0，他引：2  

罗先香  杨建强 《海洋通报》2009,28(3)

海洋大型底栖无脊椎动物能对自然和人为活动导致的水和沉积物质量变化做出可预测的响应,因此利用底栖生物作为海洋生态环境监测的生物指标和进行系统健康度量的生物指数已经得到了广泛的认可.本文比较分析了几种常用的和正在发展的海洋生态系统健康和生态环境质量状况评估的底栖生物指数,包括指示生物法、Shannon-Wiener多样性指数、BI指数、AMBI指数和Bentix指数,总结了这几种生物指数的应用和特性,探讨了底栖生物指数在实际应用中可能存在的问题和解决的办法,以期为我国海洋生态系统健康评估工作提供参考.  相似文献   

�ռ�����ؾֲ�ָ��Moranָ����Gϵ���о�   总被引：15，自引：0，他引：15  

张松林  张昆 《大地测量与地球动力学》2007,27(3):31-34

?о????????????????????????????Moran?????G???????????????????????Щ?д?????????????????м??????????????????????ó????G?????????Moran?????????  相似文献   

海陆气候事件关联规则挖掘方法     

石岩  邓敏  刘启亮  杨文涛 《地球信息科学学报》2014,16(2):182-190

近年来,异常气候事件的频发对人类的生活环境和经济发展带来严重负影响。气象学家研究表明：海洋气候异常对陆地气候异常事件的发生具有重要的诱发作用,因此,对海陆气候间的内在关联机制进行深入挖掘具有重要研究价值。本文提出了一种关联规则挖掘方法,以探索单一海洋气候指数与陆地异常气候事件间存在的关联。首先,针对陆地气候要素,采用顾及空间邻近关系的层次聚类方法进行有效气候分区,通过对各层分区结果进行相关统计分析得到有效的各区域气候序列;然后,进行顾及多重约束进行时序关联规则挖掘,以探索海陆气候要素间的关联机制;最后,通过实际算例分析得到的各气候指数与我国陆地区域异常降水事件间的关联机制结果,与实际情况高度吻合。  相似文献