An evaluation of Guided Regularized Random Forest for classification and regression tasks in remote sensing     

《International Journal of Applied Earth Observation and Geoinformation》2020

New Earth observation missions and technologies are delivering large amounts of data. Processing this data requires developing and evaluating novel dimensionality reduction approaches to identify the most informative features for classification and regression tasks. Here we present an exhaustive evaluation of Guided Regularized Random Forest (GRRF), a feature selection method based on Random Forest. GRRF does not require fixing a priori the number of features to be selected or setting a threshold of the feature importance. Moreover, the use of regularization ensures that features selected by GRRF are non-redundant and representative. Our experiments based on various kinds of remote sensing images, show that GRRF selected features provides similar results to those obtained when using all the available features. However, the comparison between GRRF and standard random forest features shows substantial differences: in classification, the mean overall accuracy increases by almost 6% and, in regression, the decrease in RMSE almost reaches 2%. These results demonstrate the potential of GRRF for remote sensing image classification and regression. Especially in the context of increasingly large geodatabases that challenge the application of traditional methods.  相似文献   

Regionalization for large area crop estimates by remote sensing     

Qian Huaisui 《中国地理科学(英文版)》1997,8(3):204-211

The crop estimates by remote sensing, developing quickly in recent decades, is a up-to-date technique. Regionalization for large area crop estimates by remote sensing, a special applied regionalization, is the foundation of crop estimates in a large area by remote sensing. According to the actual demands of wheat yield estimation by remote sensing and wheat agroclimatic demarcation of China, this paper first puts forward some principles upheld in this regionalization and analyses its main bases. Secondly, it works out the classificatory schemes about the optimum temporal for estimating wheat yield by remote sensing, information sources of space remote sensing and landuse structure in China. Finally, According to the regionalization indices, this study divides the wheat plantable region of China into 14 regions of crop yield estimates and 31 subregions of crop yield estimates.  相似文献   

冰碛扇型砂金矿床特征及其成矿初探     

杨文智 《河南国土资源》1997,(2)

成生于冰碛扇内，经一定的生物、物理、化学成矿作用，以砂金形态分布而富集成矿的金矿称为冰碛扇型砂金矿床。它具有沿造山带一定标高范围成群、成带分布，沉积物为近源且半胶结，砂金呈面状分布，并以粒金、块金为主，具胶状、浑圆状、包块状构造形态，分布极不均匀等特征。冰碛扇型砂金矿床的成矿作用与河成砂金矿床有本质的区别。它的成矿作用模式是：造山带下地壳富含的活化金通过新构造运动活化的断裂运移地表，经地下流体和地表流体的迁移聚集到冰碛扇这一封闭稳定的生物、物理、化学障环境中，主要经高效聚金微生物有机胶体成矿作用沉淀、再生加大形成砂金，逐步富集成矿床。而红色磨拉石建造中风化离解的Ｆｅ，Ｍｎ物质对沉淀环境ｐＨ值起着一定的调节作用。冰碛扇型砂金矿床在我国西部造山带内广泛分布，具有一定的工业价值，是砂金矿床中一重要类型，应予以重视  相似文献   

上扬子地台震旦系铅锌矿床类型及找矿方向   总被引：13，自引：0，他引：13  

齐文  侯满堂  王根宝 《地球科学与环境学报》2006,28(2):30-36

上扬子地台含铅锌矿地层主要为震旦系。震旦系在上扬子地台主要发育上统灯影组,次有下统陡山沱组。将上扬子地台震旦系铅锌矿床成因划分为一级为叠生矿床,二级为层控矿床,三级为热水沉积改造矿床和热水沉积再造矿床四级类型,该类型按铅锌比例进一步划分为富铅型、富锌型、铅锌共生型。研究区内最重要的铅锌矿床成因类型为南郑马元、会东大梁子铅锌矿为代表的富锌型。陕西南郑、紫阳—镇坪地区,湖北武当、神农架、黄陵地区,以及地台西缘的安宁河、甘洛—小江、峨边—寻甸等地区的震旦系是寻找铅锌矿的最有利地段。  相似文献   

STUDY ON THE INTERACTION BETWEEN NDVI PROFILE AND THE GROWING STATUS OF CROPS   总被引：5，自引：1，他引：4  

JIANGDong WANGNai-bin YANGXIao-huan WANGJi-hua 《中国地理科学(英文版)》2003,13(1):62-65

Daily and ten-day Normalized Difference Vegetation Index(NDVI) of crops were retrieved from meteorological statellite NOAA AVHRR images ,The temporal variations of the NDVI were analyzed during the whole growing season,and thus the principle of the interaction between NDIV profile and the growing status of crops was discussed,As a case in point,the relationship between integral NDVI and winter wheat yield of Henan Province in 1999 had been analyzed.By putting integral NDVI values of 60 sample counties into the winter wheat yield-integral NDVI coordination,scattering map was plotted. It demonstrated that integral NDVI had a close relation with winter wheat yield.These relation could be described with linear,cubic polynomial ,and exponential regression,and the cubic polynomial regression was the best way,In general ,NDVI reflects growing status of green vegetation ,so crop monitoring and crop yield estimation could be realized by using remote sensing technique on the basis of time serial NDVI data together with agriculture calendars.  相似文献   

The O4f + O6V eclipsing binary system Sk−67°105 in the Large Magellanic Cloud     

Pablo G. Ostrov  Emilio Lapasset 《Monthly notices of the Royal Astronomical Society》2003,338(1):141-146

  相似文献   

TEMPORAL TRENDS IN SOIL PRODUCTIVITY EVALUATIONS*     

Bryan D. Baker  Philip J. Gersmehl 《The Professional geographer》1991,43(3):304-318

Studies of soil productivity must compensate for the effects of temporal trends in order to examine the pattern of crop yields along spatial gradients. An analysis of the published yield estimates for 30 soils in 233 counties, however, did not find consistent yield increases over the past three decades. On the contrary, the yield estimates for many soils were markedly uniform since 1972. The uniformity appears to have two causes: the acknowledged difficulty of making yield estimates in a time of increasing variability in soil and crop management, both within and between regions, and surveyors' awareness of data stored in a national soils data base. The effect is to cast doubt on soil productivity data reported in county soil surveys published between 1973 and 1988.  相似文献   

Properties of Galaxies in the Second Byurakan Survey. II. Characteristic Features of a Separate Sample of Galaxies     

L. K. Erastova 《Astrophysics》2004,47(4):547-554

Some features of a sample of galaxies from the Second Byurakan Survey are discussed. Most of them are small galaxies with star formation. It is shown that different types of galaxies are in the Survey, with high, medium, and low levels of excitation and continua ranging from blue to relatively red. Many of the galaxies have absorption lines in their spectra; their continua are formed by stars in later spectral classes.  相似文献   

矿物的导电类型与矿物形成温度的关系     

赵亨达 《国土资源》1992,(3)

通过杂质对导电类型的影响的研究,得出了同种矿物的不同导电类型与矿物形成温度的规律:电子型(n型)导电矿物的形成温度大于电子与空穴混合型导电矿物的形成温度,又大于空穴型(p型)导电矿物的形成温度,绝缘体矿物的形成温度低于上述三种导电类型矿物。应用矿物热电图谱仪,天然金刚石半导体测试仪对闪锌矿、黄铁矿、金刚石等矿物的导电类型进行了测试,并探讨了导电类型成因,证实了上述规律的正确性。  相似文献   

AN INTEGRATED APPROACH TO AIR MASS CLASSIFICATION IN THE NORTH CENTRAL UNITED STATES     

Mark D. Schwartz 《The Professional geographer》1991,43(1):77-91

Both subjective and objective schemes for air mass classification offer advantages to climatological studies. An integrated approach is developed and applied to 850 mb level data in the north central United States. Each air mass type was initially delimited by a subjective analysis. Final limits were then determined with an objective technique that separates temperature curves into normal components based on interpretation from the subjective method. Continental air was most frequent in all seasons except summer. The methodology also allows estimation of classification error.  相似文献