A new supervised classifier exploiting spectral-spatial information in the Bayesian framework     

《International Journal of Applied Earth Observation and Geoinformation》2020

Conventional machine learning methods are often unable to achieve high degrees of accuracy when only spectral data are involved in the classification process. The main reason of that inaccuracy can be brought back to the omission of the spatial information in the classification. The present paper suggests a way to combine effectively the spectral and the spatial information and improve the classification’s accuracy. In practice, a Bayesian two-stage methodology is proposed embodying two enhancements: i) a geostatistical non-parametric classification approach, the universal indicator kriging and ii) the smooth multivariate kernel method. The former provides an informative prior, while the latter overcomes the assumption (often not true) of independence of the spectral data. The case study reports an application to land-cover classification in a study area located in the Apulia region (Southern Italy). The methodology performance in terms of overall accuracy was compared with five state-of-the-art methods, i.e. naïve Bayes, Random Forest, artificial neural networks, support vector machines and decision trees. It is shown that the proposed methodology outperforms all the compared methods and that even a severe reduction of the training set does not affect seriously the average accuracy of the presented method.  相似文献   

基于贝叶斯分类器的南海黄鳍金枪鱼渔场预报模型   总被引：1，自引：0，他引：1  

周为峰  黎安舟  纪世建  邱永松  郑汉丰 《海洋湖沼通报》2018,(1):116-122

本文利用来自中西太平洋渔业委员会(WCPFC)黄鳍金枪鱼延绳钓2000-2011年的历史渔获数据和美国国家海洋和大气管理局(NOAA)气候预报中心提供的海表温度最优插值数据和法国空间局(CNES)卫星海洋数据中心提供的多卫星融合高度计月合成海面高度资料,基于贝叶斯分类器,根据模型中环境因子的选取以及渔区分类策略的不同预拟了8种构建方案对2011年南海外海黄鳍金枪鱼的渔场进行分类预报,并将预报结果与实际渔场进行对比检验,比较分析不同方案对最终分类结果和精度的影响。检验结果表明,方案1-8总体精度分别为71.4%、75%、70.8%、74.4%、66.7%、68.5%、57.7%和63.7%。方案1-6在65%以上,均能够满足实际渔场预报业务化需求。采用SST和SSH双环境因子的方案均比采用单SST环境因子的方案总体精度稍高,一定程度上提高了预报精度,其中采用去除SST和SSH相关性的第一主分量作为预报因子的方案2达到了75%最高精度。采用CPUE平均值正负标准差作为节点比以33.3%与66.7%作为节点来区分高、中、低CPUE渔区的预报结果要更加准确。因此在模型筛选的基础上,选用模型方案2完成南海金枪鱼渔场渔情预报服务系统的系统实现。  相似文献   

基于推广Bayes方法参数优化的滑坡稳定性评价   总被引：1，自引：0，他引：1  

汤罗圣  殷坤龙  李德营 《地质灾害与环境保护》2010,21(4):33-37

传统的极限平衡法在确定的计算工况下要求抗剪强度参数为常数,但由于各种参数的随机性、测试的误差、地质体的不均匀性、外界因素变化的随机性等特点,对滑坡稳定性评价起主要作用的抗剪强度参数从严格意义上来说均是随时间变化的随机变量,这就需要用破坏概率模型等非传统方法对滑坡进行稳定性评价。破坏概率模型的关键是滑坡抗剪强度参数的概率分布函数,但是在实际工程中,由于试验数据太少无法准确确定抗剪强度参数概率分布函数。本文提出了以区域统计规律得出的概率分布函数为先验分布函数,然后用推广Bayes方法确定该滑坡的概率分布函数,并以里沱河滑坡为例用破坏概率模型对其进行稳定性评价。  相似文献   

基于朴素贝叶斯的西北太平洋柔鱼渔场预报模型的建立   总被引：2，自引：0，他引：2  

崔雪森  唐峰华  张衡  伍玉梅  樊伟 《中国海洋大学学报(自然科学版)》2015,45(2):37-43

西北太平洋是中国进行柔鱼(Ommastrephes bartramii)捕捞生产的重要海区,准确预报渔场出现的位置对提高渔业捕捞产量、节省燃油有重要的意义。本研究利用2002—2011年中国在该海域的历史产量数据、渔场时空数据以及包括海表温度、叶绿素浓度a、表温梯度强度和叶绿素梯度强度在内的海洋环境数据,基于朴素贝叶斯方法,建立了西北太平洋柔鱼渔场的预报模型。为满足朴素贝叶斯方法对条件独立性的假设,利用独立成份分析,重新获得相互独立的属性变量。通过求Cohen′s Kappa系数最大值的方法,确定3种CPUE类型的先验概率,建立可用于渔场预报的朴素贝叶斯预报模型。作为实际验证,将2012年7~11月我国柔鱼渔船在西北太平洋实际生产数据与预报的高CPUE渔场位置进行叠加,平均综合预报精度达到69.9%,表明该模型对西北太平洋渔场的预报具有较好效果和可行性。  相似文献   

贝叶斯估计在水深格网节点信息估算中的应用     

田勋  肖付民  孙文川  李玲玲  钱多 《海洋测绘》2013,33(3):26-28

离散数据格网化是目前表达高程和地形方法的前期工作和基础,而格网化的关键是如何利用节点周围的水深值序列推估格网节点水深值及其不确定度值。为解决这一问题,提出了基于贝叶斯估计理论的估计格网节点水深值及水深不确定度的方法,该方法具有独特的估计优势,可以很好的运用测量值和专家经验,得到可靠性较高的节点水深值和水深不确定度,对海底地形显示及数据质量估计具有一定的参考意义。  相似文献   

Integrating a fuzzy <Emphasis Type="Italic">k</Emphasis>-means classification and a Bayesian approach for spatial prediction of landslide hazard     

Pece V.?GorsevskiEmail author  Paul E.?Gessler  Piotr?Jankowski 《Journal of Geographical Systems》2003,5(3):223-251

A robust method for spatial prediction of landslide hazard in roaded and roadless areas of forest is described. The method is based on assigning digital terrain attributes into continuous landform classes. The continuous landform classification is achieved by applying a fuzzy k-means approach to a watershed scale area before the classification is extrapolated to a broader region. The extrapolated fuzzy landform classes and datasets of road-related and non road-related landslides are then combined in a geographic information system (GIS) for the exploration of predictive correlations and model development. In particular, a Bayesian probabilistic modeling approach is illustrated using a case study of the Clearwater National Forest (CNF) in central Idaho, which experienced significant and widespread landslide events in recent years. The computed landslide hazard potential is presented on probabilistic maps for roaded and roadless areas. The maps can be used as a decision support tool in forest planning involving the maintenance, obliteration or development of new forest roads in steep mountainous terrain.  相似文献   

Using Bayesian belief networks to analyse the stochastic dependence between interevent time and size of earthquakes     

C. Agostinelli  R. Rotondi 《Journal of Seismology》2003,7(3):281-299

The purpose of this article is to show how Bayesian belief networks can beused in analysis of the sequence of the earthquakes which have occurred in a region, to study the interaction among the variables characterizing eachevent. These relationships can be represented by means of graphs consistingof vertices and edges; the vertices correspond to random variables, whilethe edges express properties of conditional independence. We have examinedItalian seismicity as reported in two data bases, the NT4.1.1 catalogue and the ZS.4 zonation, and taken into account three variables: the size of thequake, the time elapsed since the previous event, and the time before the subsequent one. Assigning different independence relationships among these variables, first two couples of bivariate models, and then eight trivariatemodels have been defined. After presenting the main elements constituting a Bayesian belief network, we introduce the principal methodological aspects concerning estimation and model comparison. Following a fully Bayesian approach, prior distributions are assigned on both parameters and structuresby combining domain knowledge and available information on homogeneous seismogenic zones. Two case studies are used to illustrate in detail the procedure followed to evaluate the fitting of each model to the data sets andcompare the performance of alternative models. All eighty Italian seismogenic zones have been analysed in the same way; the results obtained are reportedbriefly. We also show how to account for model uncertainty in predicting a quantity of interest, such as the time of the next event.  相似文献   

Probabilistic mapping of flood-induced backscatter changes in SAR time series     

《International Journal of Applied Earth Observation and Geoinformation》2017

The information content of flood extent maps can be increased considerably by including information on the uncertainty of the flood area delineation. This additional information can be of benefit in flood forecasting and monitoring. Furthermore, flood probability maps can be converted to binary maps showing flooded and non-flooded areas by applying a threshold probability value p_F = 0.5. In this study, a probabilistic change detection approach for flood mapping based on synthetic aperture radar (SAR) time series is proposed. For this purpose, conditional probability density functions (PDFs) for land and open water surfaces were estimated from ENVISAT ASAR Wide Swath (WS) time series containing >600 images using a reference mask of permanent water bodies. A pixel-wise harmonic model was used to account for seasonality in backscatter from land areas caused by soil moisture and vegetation dynamics. The approach was evaluated for a large-scale flood event along the River Severn, United Kingdom. The retrieved flood probability maps were compared to a reference flood mask derived from high-resolution aerial imagery by means of reliability diagrams. The obtained performance measures indicate both high reliability and confidence although there was a slight under-estimation of the flood extent, which may in part be attributed to topographically induced radar shadows along the edges of the floodplain. Furthermore, the results highlight the importance of local incidence angle for the separability between flooded and non-flooded areas as specular reflection properties of open water surfaces increase with a more oblique viewing geometry.  相似文献   

基于贝叶斯分类器的多普勒天气雷达海浪回波识别和效果检验     

沈妍琰  黄兴友  黄书荣  沈艳秋  陈晓颖 《海洋科学》2020,44(6):83-90

为了提升雷达数据质量，减少海浪回波对临近预报和数值天气预报模式的雷达数据同化的不利影响，因此需要对海浪回波进行识别和去除。识别算法主要为统计获得先验概率，分析海浪和降水回波特征分布得到似然函数，再经过贝叶斯分类器来达到识别的目的。在本次算法识别过程中65个样本数据试验的临界成功指数I_CS达到了0.692，结果表明利用贝叶斯分类器对海浪回波的识别，具有较好的识别效果，能一定程度降低海浪回波误判为降水回波的错误，提高雷达数据质量。  相似文献   

The optimum Bayesian probability procedure and the prediction of strong earthquakes felt in Mexico city     

Sergio G. Ferraes 《Pure and Applied Geophysics》1988,127(4):561-571

Bayes' theorem has possible application to earthquake prediction because it can be used to represent the dependence of the inter-arrival time (T) of thenext event on magnitude (M) of thepreceding earthquake (Ferraes, 1975;Bufe et al., 1977;Shimazaki andNakata, 1980;Sykes andQuittmeyer, 1981). First, we derive the basic formulas, assuming that the earthquake process behaves as a Poisson process. Under this assumption the likelihood probabilities are determined by the Poisson distribution (Ferraes, 1985) after which we introduce the conjugate family of Gamma prior distributions. Finally, to maximize the posterior Bayesian probabilityP(/M) we use calculus and introduce the analytical condition .Subsequently we estimate the occurrence of the next future large earthquake to be felt in Mexico City. Given the probabilistic model, the prediction is obtained from the data set that include all events withM7.5 felt in Mexico City from 1900 to 1985. These earthquakes occur in the Middle-America trench, along Mexico, but are felt in Mexico City. To see the full significance of the analysis, we give the result using two models: (1) The Poisson-Gamma, and (2) The Poisson-Exponential (a special case of the Gamma).Using the Poisson-Gamma model, the next expected event will occur in the next time interval =2.564 years from the last event (occurred on September 19, 1985) or equivalently, the expected event will occur approximately in April, 1988.Using the Poisson-Exponential model, the next expected damaging earthquake will occur in the next time interval =2.381 years from the last event, or equivalently in January, 1988.It should be noted that very strong agreement exists between the two predicted occurrence times, using both models.  相似文献