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.     

Overview of In - Situ Biodegradation and Enhancement

Microbial degradation technologies have been developed to restore ground water quality in aquifers polluted by organic contaminants effectively in recent years. However, in course of the degradation, the formation of biofilms in ground water remediation technology can be detrimental to the effectiveness of a ground water remediation project. Several alternatives are available to a remedial design engineer, such as Permeable Reactive Barriers (PRBs) and in -situ bioremediation, Hydrogen Releasing Compounds (HRCs) barrier, Oxygen Releasing Compounds (ORCs) barrier etc. which are efficient and cost- effective technologies. Excessive biomass formation renders a barrier ineffective in degrading the contaminants, Efforts are made to develop kinetics models which accurately determine bio - fouling and bio - filn formation and to control excessive biomass formation.     

ECOLOGICAL SERIES OF SOIL ANIMALS IN DARLIDAI MOUNTAIN

The ecological series of soil animals under the broad-leaved and pine mixed forest in Darlidai Mountainwas studied. Seven sample plots were selected according to different altitude gradients, which belong to different vegeta-tion types. By investigating and analyzing soil animals in every sample plot it is found that there are 45 groups and 1956individuals, which axe involved in 3 phylums, 7 classes, 16 orders, respectively. The altitude is a key factor which af-fects ecological series of soil animals. Both the groups and individuals of soil animals increase with altitude increasingunder certain conditions, which contrastes with ordinary cases, resulting from special micro-climate in studied area. Thegroups and individuls of soil animals are the most under the broad-leaved and pine forest on the top of the mountain, andthe least under Picea-Abies forest in the foot of the mountain.     

Discovery of 13 New Variable Stars in the Field of the Open Cluster NGC 2168 （M35）

A wide-field time-series CCD photometric survey of variable stars in the field of the open cluster NGC 2168 was carried out using the BATC Schmidt telescope. In total 13 new variable stars are discovered with three W UMa systems, one EA type and two EB type eclipsing binaries (one of them could be a W UMa system), and seven pulsating stars including three candidates of δScuti stars.     

Multi-wavelength Diagnostics of Bombardment by Non-thermal Particles in Solar Flares

Chromospheric lines, including Ha, Lyα, Lyβand CaⅡK, CaⅡ8542, are systemically and quantitatively investigated with respect to the non-thermal excitation and ionization due to particle beam bombardment for a series of solar semi-empirical atmospheric models. As a result we propose to use the contrast in the integrated intensity of hydrogen lines to estimate the total energy flux of the bombarding beam during the solar flare impulsive phase. Partial frequency redistribution is considered in the Lyαline calculation and a smaller intensity enhancement in the Ha line-centers is found than in the previous results of Fang et al.     

Influence of the Choice of Core-Envelope Transition Point on the Binary Merger of Two Main-sequence Components

We have studied the influence of different choices of core-envelope transition point on the final merger of contact binaries with two main-sequence components. A binary of 1.00 + 0.90M⊙ with an initial orbital period of 0.35d is examined. The mass fraction of the primary mixed with the matter of the secondary, qmix, determined by the chosen core-envelope transition point, ranges from 0.04 to 1.00 in our analysis. If as qmix< 0.8, none of the     

The Difference between the α-disks of Seyfert 1 Galaxiesand Quasars

In a previous paper, it was suggested that contamination of the nuclear luminosity by the host galaxy plays an important role in determining the parameters of the standard a disk of AGNs. Using the nuclear absolute B band magnitude instead of the total absolute B band magnitude, we have recalculated the central black hole masses, accretion rates and disk inclinations for 20 Seyfert 1 galaxies and 17 Palomar-Green (PG) quasars. It is found that a small value of a is needed for the Seyfert 1 galaxies than for the PG quasars. This difference in a possibly leads to the different properties of Seyfert 1 galaxies and quasars. Furthermore, we find most of the objects in this sample are not accreting at super-Eddington rates if we adopt the nuclear optical luminosity in our calculation.     

Cygnus A

Cygnus A was the first hyper-active galaxy discovered, and it remains by far the closest of the ultra-luminous radio galaxies. As such, Cygnus A has played a fundamental role in the study of virtually all aspects of extreme activity in galaxies. We present a review of jet theory for powering the double-lobed radio emitting structures in powerful radio galaxies, followed by a review of observations of Cygnus A in the radio, optical, and X-ray relevant to testing various aspects of jet theory. Issues addressed include: jet structure from pc- to kpc-scales, jet stability, confinement, composition, and velocity, the double shock structure for the jet terminus and the origin of multiple radio hotspots, the nature of the filamentary structure in the radio lobes, and the hydrodynamic evolution of the radio lobes within a dense cluster atmosphere, including an analysis of pressure balance between the various gaseous components. Also discussed are relativistic particle acceleration and loss mechanisms in Cygnus A, as well as magnetic field strengths and geometries both within the radio source, and in the intracluster medium. We subsequently review the classification, cluster membership, and the emission components of the Cygnus A galaxy. The origin of the activity is discussed. Concentrating on the nuclear regions of the galaxy, we review the evidence for an obscured QSO, also given the constraints on the orientation of the radio source axis with respect to the sky plane. We present an overview of models of central engines in AGN and observations of Cygnus A which may be relevant to testing such models. We conclude with a brief section concerning the question of whether Cygnus A is representative of powerful high redshift radio galaxies. Received October 10, 1995     

The Relation between the Amplitude and the Period of Solar Cycles

The maximum amplitudes of solar activity cycles are found to be well anti-correlated (r = -0.72) with the newly defined solar cycle lengths three cycles before (at lag -3) in 13-month running mean sunspot numbers during the past 190 years. This result could be used for predicting the maximum sunspot numbers. The amplitudes of Cycles 24 and 25 are estimated to be 149.5±27.6 and 144.3±27.6, respectively.