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

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.     

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

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.     

抗差估计的初值选择

对L1 范估计的平差值和LS估计的平差值作为抗差估计的初值进行了比较 ,指出在 ρ函数是严凸函数时 ,二者无明显的区别。因为LS估计简单且易于计算 ,因此建议用LS估计的平差值作为抗差估计的初值。     

REMOTE SENSING FOREST BIOMASS: AN EVALUATION USING HIGH RESOLUTION REMOTE SENSOR DATA AND LOBLOLLY PINE PLOTS

Eight-year-old Loblolly pine (Pinus taeda) plots located in South Carolina were evaluated using high resolution aircraft multispectral scanner data to determine if biomass could be accurately measured. Sixteen pine plots located on both sandy and clay soils were treated with 0, 180, or 360 kg. (approximately 0, 400, or 800 lb.) of nitrogen per plot. Indices of biomass from remote sensing data were significantly correlated with in situ biomass measurements made in each plot. A ratio of infrared (.9–1.1 μm) and red (.65–.70 μm) channels yielded the best correlation. The indices were not sensitive to differences in soil type (sandy or clay).     

On least squares estimation of generalized covariance functions

Least squares estimation (LSE) is theoretically related to quadratic unbiased estimation of variance components. It is argued that these methods of estimation of variance components essentially generalize LSE though they are not formally equivalent.     

APPLICATION OF GEOGRAPHICAL PARAMETER DATABASE TO ESTABLISHMENT OF UNIT POPULATION DATABASE

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     

Combined mine tremors source location and error evaluation in the Lubin Copper Mine (Poland)

A modified method of mine tremors location used in Lubin Copper Mine is presented in the paper. In mines where an intensive exploration is carried out a high accuracy source location technique is usually required. The effect of the flatness of the geophones array, complex geological structure of the rock mass and intense exploitation make the location results ambiguous in such mines. In the present paper an effective method of source location and location's error evaluations are presented, combining data from two different arrays of geophones. The first consists of uniaxial geophones spaced in the whole mine area. The second is installed in one of the mining panels and consists of triaxial geophones. The usage of the data obtained from triaxial geophones allows to increase the hypocenter vertical coordinate precision. The presented two-step location procedure combines standard location methods: P-waves directions and P-waves arrival times. Using computer simulations the efficiency of the created algorithm was tested. The designed algorithm is fully non-linear and was tested on the multilayered rock mass model of the Lubin Copper Mine, showing a computational better efficiency than the traditional P-wave arrival times location algorithm. In this paper we present the complete procedure that effectively solves the non-linear location problems, i.e. the mine tremor location and measurement of the error propagation.     

饱和粉砂不稳定性的试验研究

通过对净砂和级配良好粉砂(含10 %粉土)进行一系列三轴固结不排水试验（CU）,研究了粉土、孔隙比和围压对饱和粉砂不稳定性的影响。试验结果表明,净砂与粉砂在不排水剪切条件下均会出现应变软化现象（即不稳定性）。同一围压下脆性指数(IB)随孔隙比增加,但不稳定线的应力比随孔隙比增加而减小。引用等效粒间孔隙比(ege)后,净砂和粉砂在ege-ln p?平面上拥有基本相同的临界状态线。在临界状态理论及等效粒间孔隙比的基础上,提出在同一修正状态参数(?ge)下净砂和级配良好粉砂有相似的不稳定性。     

Wave run-up and overtopping on smooth and rough slopes of coastal structures

A series of hydraulic model tests has been carried out in a glass wave flume to investigate the influences of wave height, wave period, wave steepness, surf similarity parameter, roughness, layer thickness and porosity on wave run-up and overtopping of 1:2 sloped impermeable and permeable breakwaters fronted by a 1:10 gentle, smooth beach slope. The analysis of results involves the correlation between the overtopping energy transfer with the relative wall height and the relationship between wave run-up and overtopping rate. Further, measured wave run-up and overtopping rates are compared with the results given in the Shore Protection Manual (1984), Automated Coastal Engineering System (1992)and results of other investigators.     

A note on estimation of the Jacobian elliptic parameter in cnoidal wave theory

A new and simple calculating technique for the Jacobian elliptic parameter is presented in this study. The technique is very useful in generating a train of cnoidal waves in both laboratory and numerical wave tanks. Upon specification of water depth, the wave height and either the wave period or the wavelength, the proposed technique uses the Newton–Raphson method to estimate the Jacobian elliptic parameter directly, without trial and error procedures or look-up in tables. It is shown that the technique provides equally accurate results as the ad hoc methods previously used.