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.     

GRADATION AND ASSESSMENT OF DAMAGE DEGREE OF NATURAL LANDSCAPE IN XING, AN COUNTY, GUANGXI

A new technique designed to help quantify the degree of damage to the landscape from one area to another shows a close relationship between population density and the degree of landscape damage. The technique establishes a scale of damage from 0 to 5 (zero = no damage; 5 = severe damage) using data from aerial photographs, land-use maps, and field data. The related formula allows one to compare the relative degree of damage across regions using a combination of an absolute index, a theoretical index, a relative index, and population density. Xing'an County is used to demonstrate the technique.     

利用Lageos 1 SLR资料解算1990-2001年的地球定向参数

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。     

第22太阳周活动区M级以上X射线耀斑指数的统计

本文对第２２太阳周（１９８７年１月至１９９２年１２月）中发生过Ｍ级以上的Ｘ射线耀斑（Ｈα耀斑级别≥Ｍ级，并伴有Ｘ射线的耀斑）对应的３９５个活动区资料进行了耀斑指数的统计，得到的结果：１．２２太阳周Ｍ级以上Ｘ射线耀斑级别综合指数表，２．２２太阳周Ｍ级以上Ｘ射线耀斑总指数表，３．第２２太阳周Ｍ级以上Ｘ射线耀斑总指数随时间的变化曲线，４．第２２太阳周Ｍ级以上Ｘ射线濯斑总指数直方图，该图表明第２２太阳周活动的极大年分别是１９８９和１９９１年，为第２３周太阳活动预报提供了可用参数。     

Long-chain alkenones and U37′ variability along a south–north transect in the Western Pacific Ocean

In this paper, we present 50 surface water samples collected during the IMAGES III cruise (June–July 1997) along a transect from New Zealand to the China Sea (42°S–178°E, 21°N–120°E) covering a temperature range from 13.3 to 30.4 °C. A very worthwhile aspect of this study is a coupling of both biomarker (alkenone) and coccolithophorid counting. We show that the U₃₇^k′–temperature relationship is very similar to the Prahl et al. [Geochim. Cosmochim. Acta 52 (1988) 2203] culture calibration and to the global core top calibration of Müller et al. [Geochim. Cosmochim. Acta 62 (1998) 1757]. However, in the warmest surface waters of the Western Pacific ocean (>26.4 °C) where Gephyrocapsa oceanica is likely the most widespread species, the associated U₃₇^k′ has a constant value of 1.0. The consequence is that above this temperature threshold, U₃₇^k′ cannot be used as an accurate paleothermometer.     

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     

FUZZY COMPREHENSIVE EVALUATION OF CONTAINER TRANSPORTATION MODES ALONG THE CHANGJIANG RIVER MAIN LINE AND ITS DELTA AREA

The Changjiang River (Yangtze) is one of the fastest growth areas of container transportation in Chi-na. Rail, road and water transportation have competed against each other for container transportation in the Chang-jiang River main line and its delta area. It is of significance to assess these different transportation modes scientifi-cally in order to organize container transportation efficiently in this area and make decision for integral plan and construction of transportation system in this area. This paper outlines application of fuzzy comprehensive evaluation to appraise different modes of typical direction of containers. Twelve assessment indexes were decided. Membership functions were formulated. Evaluation results indicated that road transportation was optimal mode in the Changjiang River delta area, however water transportation was the primary way in the Changjiang River main line.     

Effects of Different Diets on the Dietary Attractability and Selectivity of Chinese Shrimp, Fenneropenaeus chinensis

Attractabilities of different diets and dietary selectivity of Chinese shrimp, Fenneropenaeus chinensis were studied through behavior observation and feeding experiment, respectively. The five diets used in the experiment are: Fish Flesh (FF), Shrimp Flesh (SF), Clam Foot (CF), Polychaete Worm (PW), and Formulated Diet (FD). No significant differences of attractability exist between any two different diets when every two natural diets or all five diets are provided simultaneously. On the other hand, significant differences of attractability exist between FD and every single natural diet when they are provided simultaneously. Results of behavioral observation indicate that natural diets are more attractive than FD. In feeding experiment, Chinese shrimp has distinct selectivity on different diets. It positively selects CF and PW, negatively selects FF and SF, and excludes FD absolutely. The results of the present studies indicate that the dietary selectivity of shrimp was based not only on the attractabilities of the diets, but also on the responses such as growth and food conversion.     

Gouging abrasion test for rock abrasiveness testing

Wear parts of many mineral processing and mining equipment are often subjected to high stress loads applied at high speeds and at varying angles of incidence, where the prevalent mode of wear is high-stress gouging/sliding impact abrasion. Examples include crusher liners, wear liners in hoppers and chutes, picks on roadheaders, discs on tunnel boring machines and ground engaging tools. Abrasion under these conditions is characterised by a high material removal rate and thus has a direct bearing on wear rates and service life of the equipment concerned. However, at present there appears to be no method for rock abrasiveness assessment under these conditions. This paper describes a new Gouging Abrasion method and apparatus for testing abrasivity of rocks under high-stress gouging/sliding impact wear. A Gouging Abrasion Index (Gi) is introduced, which can be used for prediction and assessment of component life expectancy and efficiency of mineral processing and materials handling equipment. Experimental data from Gouging Abrasion testing of numerous Australian rock types are presented. It is suggested that the results of Gi testing can be used for wear rate predictions for a variety of mineral processing and materials handling equipment working under high-stress gouging/sliding impact abrasion conditions.