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   

Isotope hydrological study of mean transit time in the granitic Strengbach catchment (Vosges massif,France): application of the FlowPC model with modified input function     

D. Viville  B. Ladouche  T. Bariac 《水文研究》2006,20(8):1737-1751

Measurements of ¹⁸O concentrations in precipitation, soil solution, spring and runoff are used to determine water transit time in the small granitic Strengbach catchment (0·8 km²; 883–1146 m above sea level) located in the Vosges Mountains of northeastern France. Water transit times were calculated by applying the exponential, exponential piston and dispersion models of the FlowPC program to isotopic input (rainfall) and output (spring and stream water) data sets during the period 1989–95. The input function of the model was modified compared with the former version of the model and estimated by a deterministic approach based on a simplified hydrological balance. The fit between observed and calculated output data showed marked improvements compared with results obtained using the initial version of the model. An exponential piston version of the model applied to spring water indicates a 38·5 month mean transit time, which suggests that the volume in the aquifer, expressed in water depth, is 2·4 m. A considerable thickness (>45 m) of fractured bedrock may be involved for such a volume of water to be stored in the aquifer. Copyright © 2005 John Wiley & Sons, Ltd.  相似文献   

利用Lageos 1 SLR资料解算1990-2001年的地球定向参数     

ZHU Yuanlan FENG Chugang ZHOU Yonghong 《中国科学院上海天文台年刊》2003,(1)

利用 12年的Lageos 1卫星激光测距资料 (1990 - 2 0 0 1)解算得到了地球定向参数 (EOP) ,将该序列的结果与同期的EOP(IERS)C0 4进行比较 ,其外符精度为 :极移XP— 0 .4 0mas,YP— 0 .4 2mas ,日长变化Dr— 0 .0 35ms。  相似文献   

APPLICATION OF GEOGRAPHICAL PARAMETER DATABASE TO ESTABLISHMENT OF UNIT POPULATION DATABASE   总被引：1，自引：1，他引：0  

DONG Chun  ZHAO Rong  LIU Ji-ping  WANG Gui-xin  WU Xi-zhi 《中国地理科学(英文版)》2003,13(1):34-38

Now GIS is turning into a good tool in handling geographical, economical, and population data, so we can obtain more and more information from these data. On the other hand, in some cases, for a calamity, such as hurricane, earthquake, flood, drought etc., or a decision-making, such as setting up a broadcasting transmitter, building a chemical plant etc., we have to evaluate the total population in the region influenced by a calamity or a project. In this paper, a method is put forward to evaluate the population in such special region. Through exploring the correlation of geographical parameters and the distribution of people in the same region by means of quantitative analysis and qualitative analysis, unit population database (1km× 1km) is established. In this way, estimating the number of people in a special region is capable by adding up the population in every grid involved in this region boundary. The geographical parameters are obtained from topographic database and DEM database on the scale of  相似文献   

Properties of star formation in the spiral arms of barred galaxies     

S. Baes-Fischlmair  W.W. Zeilinger  J.-C. Vega-Beltran  J.E. Beckman 《Astrophysics and Space Science》2003,284(2):735-738

It is assumed that the two-fold disc-wide symmetry of spirals is caused by density waves, but also the potential of a bar component may have a significant influence on structural properties. The strength of the bar component appears to be anti-correlated with the degree of symmetry of star-forming regions in the spiral arms (Rozas et al., 1998). We present new results of R and Hα surface photometry of a sample of bright barred spirals. A photometric decompositon of the galaxy components is carried out in order to make a more accurate measurement of the strength of the bar and its interrelation to gas and stars in the disc. This revised version was published online in August 2006 with corrections to the Cover Date.  相似文献   

Microphysical modeling of ethane ice clouds in titan’s atmosphere     

Erika L. Barth  Owen B. Toon 《Icarus》2003,162(1):94-113

A time-dependent microphysical model is used to study the evolution of ethane ice clouds in Titan’s atmosphere. The model simulates nucleation, condensational growth, evaporation, coagulation, and transport of particles. For a critical saturation of 1.15 (a lower limit, determined by laboratory experiments), we find that ethane clouds can be sustained between altitudes of 8 and 50 km. Growth due to coalescence is inefficient, limiting the peak in the size distribution (by number) to 10 μm. These clouds vary with a period of about 20 days. This periodicity disappears for higher critical saturation values where clouds remain subvisible. Rainout of ethane due to methane cloud formation raises the altitude of the ethane cloud bottom to near the tropopause and may eliminate ethane clouds entirely if methane cloud formation occurs up to 30 km. However, clouds formed above the troposphere from other gases in Titan’s atmosphere could be sustained even with rainout up to 30 km. Although the optical depth of ethane clouds above 20 km is typically low, short-lived clouds with optical depths of order 0.1-1 can be created sporadically by dynamically driven atmospheric cooling. Ethane cloud particles larger than 25 μm can fall to the surface before total evaporation. However, ethane clouds remain only a small sink for tholin particles. At the peak of their cycle, the optical depth of ethane clouds could be comparable to that of tholin in the near-infrared, resulting in a 5% increase in Titan’s albedo for wavelengths between 1 and 2 μm. A number of factors limit our ablility to predict the ethane cloud properties. These factors include the mixing time in the troposphere, the critical saturation ratio for ethane ice, the existence of a surface reservoir of ethane, the magnitude and timing of dynamically driven temperature perturbations, and the abundance and life cycle of methane clouds.  相似文献   

Extensional Late Paleozoic deformation on the western margin of Pangea, Patlanoaya area, Acatlán Complex, southern Mexico     

M.A. Ramos-Arias  J.D. Keppie  A. Ortega-Rivera  J.W.K. Lee 《Tectonophysics》2008,448(1-4):60-76

New mapping in the northern part of the Paleozoic Acatlán Complex (Patlanoaya area) records several ductile shear zones and brittle faults with normal kinematics (previously thought to be thrusts). These movement zones separate a variety of units that pass structurally upwards from: (i) blueschist-eclogitic metamorphic rocks (Piaxtla Suite) and mylonitic megacrystic granites (Columpio del Diablo granite ≡ Ordovician granites elsewhere in the complex); (ii) a gently E-dipping, listric, normal shear zone with top to the east kinematic indicators that formed under upper greenschist to lower amphibolite conditions; (iii) the Middle–Late Ordovician Las Minas quartzite (upper greenschist facies psammites with minor interbedded pelites intruded by mafic dikes and a leucogranite dike from the Columpio del Diablo granite) unconformably overlain by the Otate meta-arenite (lower greenschist facies psammites and pelites): roughly temporal equivalents are the Middle–Late Ordovician Mal Paso and Ojo de Agua units (interbedded metasandstone and slate, and metapelite and mafic minor intrusions, respectively) — some of these units are intruded by the massive, 461 ± 2 Ma, Palo Liso megacrystic granite: decussate, contact metamorphic muscovite yielded a ⁴⁰Ar/³⁹Ar plateau age of 440 ± 4 Ma; (iv) a steeply-moderately, E-dipping normal fault; (v) latest Devonian–Middle Permian sedimentary rocks (Patlanoaya Group: here elevated from formation status). The upward decrease in metamorphic grade is paralleled by a decrease in the number of penetrative fabrics, which varies from (i) three in the Piaxtla Suite, through (ii) two in the Las Minas unit (E-trending sheath folds deformed by NE-trending, subhorizontal folds with top to the southeast asymmetry, both associated with a solution cleavage), (iii) one in the Otate, Mal Paso, and Ojo de Agua units (steeply SE-dipping, NE–SW plunging, open-close folds), to (iv) none in the Patlanoaya Group. ⁴⁰Ar/³⁹Ar analyses of muscovite from the earliest cleavage in the Las Minas unit yielded a plateau age of 347 ± 3 Ma and show low temperature ages of  260 Ma. Post-dating all of these structures and the Patlanoaya Group are NE-plunging, subvertical folds and kink bands. An E–W, vertical normal fault juxtaposes the low-grade rocks against the Anacahuite amphibolite that is cut by megacrystic granite sheets, both of which were deformed by two penetrative fabrics. Amphibole from this unit has yielded a ⁴⁰Ar/³⁹Ar plateau age of 299 ± 6 Ma, which records cooling through  490 °C and is probably related to a Permo-Carboniferous reheating event during exhumation. The extensional deformation is inferred to have started in the latest Devonian ( 360 Ma) during deposition of the basal Patlanoaya Group, lasting through the rapid exhumation of the Piaxtla Suite at  350–340 Ma synchronous with cleavage development in the Las Minas unit, deposition of the Patlanoaya Group with active fault-related exhumation suggested by Mississippian and Early Permian conglomerates ( 340 and 300 Ma, respectively), and continuing at least into the Middle Permian (≡ 260 Ma muscovite ages). The continuity of Mid-Continent Mississippian fauna from the USA to southern Mexico suggests that this extensional deformation occurred on the western margin of Pangea after closure of the Rheic Ocean.  相似文献   

Models in geography revisited     

N.J. Clifford 《Geoforum》2008,39(2):675-686

Agent based models (ABMs) have many applications, and illustrate a rapidly developing field of enquiry, spanning both the physical-mathematical and human-social sciences. ABMs are seen as most appropriate in situations where decisions or actions are distributed around particular locations, and in which structure is viewed as emergent from the interaction between individuals. ABMs may be used either as representational devices, to reproduce the patterns observed or desired in the system of interest, or as foundational tools contributing to the development of social or economic theory. The role and status of models and modelling is itself an instantiation of a wider debate concerning representation and explanation. Today, a case can be made that the nature of explanation and the use of scientific interpretation reflect much less definite and exclusive positions and permit more diverse approaches than hitherto. The underlying proposition of this commentary is, therefore, that the time is right for a positive application of ABMs within the discipline of geography, and for a rediscovery and reappraisal of the richness and depth of insight in the model-building enterprise more generally. First, the context for ABM development and application is set with reference to the agency-structure debate. Second, some aspects of the heritage of models in geography is presented, based upon reviews of two benchmark publications bearing that title. Next, some of the most significant characteristics, uses, potentials and limitations of ABMs, are reviewed. Finally, some constructive ways forward are suggested, as informed by theory and method from the interpretative social sciences.  相似文献   

Influence of Structural Non-Stationarity of Surface Roughness on Morphological Characterization and Mechanical Deformation of Rock Joints   总被引：2，自引：2，他引：0  

N. Fardin 《Rock Mechanics and Rock Engineering》2008,41(2):267-297

Summary Structural non-stationarity of surface roughness affects accurate morphological characterization as well as mechanical behaviour of rock joints at the laboratory scale using samples with a size below the stationarity threshold. In this paper, the effect of structural non-stationarity of surface roughness is investigated by studying the scale dependence of surface roughness and mechanical behaviour of rock joints. The results show that the structural non-stationarity mainly affects the accurate characterization of the surface roughness of the fracture samples. It also controls the amount and location of the contact areas during shear tests, which in turn affects the mechanical properties and asperity degradation of the samples. It is concluded that for accurate determination of the morphological and mechanical properties of rock joints at laboratory and field scales, samples with size equal to or larger than the stationarity threshold are required. Author’s address: Nader Fardin, Rock Mechanics Group, Department of Mining Engineering, Faculty of Engineering, University of Tehran, P.O. Box: 11365/4563, Tehran, Iran  相似文献   

流域水文模型参数识别的现代优化方法研究进展   总被引：1，自引：1，他引：0  

武震  张世强  张小文 《冰川冻土》2008,30(1):64-71

水文参数优化是水文模型发展中的一个重要部分,针对水循环过程模拟中的流域水文模型参数识别的复杂优化问题,回顾了水文模型优化算法的发展历程,对国内外水文模型参数识别算法的最新进展进行了阐述.介绍了模拟退火算法、遗传算法、SCE-UA、粒子群算法等常用算法的参数设定及一般流程,并对编码遗传算法、单纯形混合加速遗传算法和运用融合技术的几种遗传算法以及其它几种常用算法在新安江模型中的优化结果进行了比较,认为混合加速遗传算法是一种较好的方法.在系统研究现代优化算法与传统优化算法的基础上,建立各种优化算法的融合技术和法则可能是进一步提高参数优化算法性能的方向.  相似文献