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.     

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。     

The possible response of life zones in China under global climate change

The response of natural vegetation to climate change is of global concern. In this research, an aggregated Holdridge Life Zone System was used to study the possible response of life zones in China under doubled atmospheric CO₂ concentration with the input climatic parameters at 0.5×0.5° resolution of longitude and latitude from NCAR regional climate model 2 (RegCM2) coupled with the CSIRO global climate model. The results indicate that the latitudinal distribution of life zones would become irregular because of the complicated climate change. In particular, new life zones, such as subtropical desert (SD), tropical desert (TDE) and tropical thorn woodland (TTW), would appear. Subtropical evergreen broadleaved forest (SEBF), tropical rainforest and monsoon forest (TRF), SD, TDE and TTW zones would appear in the northeastern China. Cool-temperate mixed coniferous and broadleaved forest (CMC) and warm-temperate deciduous broadleaved forest (WDBF) zones would appear at latitudes 25–35°N. The temperate desert (TD) in the western China would become Tibetan high-cold plateau (THP), SEBF, WDBF and temperate steppe (TS), and a large part of THP would be replaced by TRF, TDE, SEBF, TS and TTW. The relative area (distribution area/total terrestrial area) of CMC, TRF, TDE and TTW zone would increase about 3%, 21%, 3% and 6%, respectively. However, the relative area of SEBF, TS, TD and THP would decrease about 5%, 3%, 19% and 4%, respectively. In all, the relative area of forests (CCF, CMC, WDBF, SEBF, TRF) would increase about 15%, but the relative area of desert (TD, SD, TDE, and TTW) and THP would decrease about 9% and 4%, respectively. Therefore, responses of different life zones in China to climate change would be dramatic, and nationwide corridors should be considered for the conservation of migrating species under climate change.     

The characteristics of Asian dust events in Northeast Asia during the springtime from 1993 to 2004

The characteristics of Asian dust events that occurred in Northeast Asia during the springtime from 1993 to 2004 are investigated using 3-hourly SYNOP reports (World Meteorological Organization). Occurrences of blowing sand and dust storm are low in 1997 and 1999, but have increased rapidly since 2000. The maximum occurrence was recorded in 2002. Wind velocity of 6.5 m s^− 1 as a threshold wind velocity is not so exactly consistent with the occurrence of blowing sand. However, wind velocity of 14 m s^− 1 as a strong wind causing dust storm had similar tendency to those of dust storm and Dust Storm Index.Source regions of Asian dust are divided into three regions (A: dry arid, B: semi-arid, and C: cultivated), based upon the occurrence of blowing sand and dust storm. Eight meteorological stations are selected in three regions, which have frequent occurrences of blowing sand. Source regions of Asian dust that affect the Korean peninsula are gradually extending eastward. Positive anomalies of NDVI occurred in 1994, 1995, and 1998 when temperature was high and precipitation was heavy. However, the frequent occurrence of the dust phenomena is not always consistent with lots of vegetation, high temperature, and much precipitation in this study.     

Virtual Huanghe River System： Framework and Technology

1 Introduction Huanghe (Yellow) River basin is located in 32°–42°N, 96°–119°E. The area of the catchment is more than 752,000km2. The river is 5464km long with a drop in elevation of 4830m. Among the whole area, the moun- tainous and stone area accounts for 29%, loess and hills area 46%, sandy area 11% and plain area 14%, respec- tively. Different natural landscapes exist in this area. The Huanghe River flows through the Loess Plateau, where the soil is eroded seriously (Wang, 2002;…     

The plane of the Edgeworth-Kuiper belt

We examine possible locations for the primordial disk of the Edgeworth-Kuiper Belt (EKB), using several subsets of the known objects as markers of the total mass distribution. Using a secular perturbation theory, we find that the primordial plane of the EKB could have remained thin enough to escape detection only if it is clustered very closely about the invariable plane of the Solar System.     

Starburst activity in a ROSAT narrow emission-line galaxy

We present multiwaveband photometric and optical spectropolarimetric observations of the R =15.9 narrow emission-line galaxy R117_A which lies on the edge of the error circle of the ROSAT X-ray source R117. The overall spectral energy distribution of the galaxy is well modelled by a combination of a normal spiral galaxy and a moderate-strength burst of star formation. The far-infrared and radio emission is extended along the major axis of the galaxy, indicating an extended starburst.
On positional grounds, the galaxy is a good candidate for the identification of R117, and the observed X-ray flux is very close to what would be expected from a starburst of the observed far-infrared and radio fluxes. Although an obscured high-redshift QSO cannot be entirely ruled out as contributing some fraction of the X-ray flux, we find no candidates to K =20.8 within the X-ray error box, and so conclude that R117_A is responsible for a large fraction, if not all, of the X-ray emission from R117.
Searches for indicators of an obscured AGN in R117_A have so far proven negative; deep spectropolarimetric observations show no signs of broad lines to a limit of 1 per cent and, for the observed far-infrared and radio emission, we would expect 10 times greater X-ray flux if the overall emission were powered by an AGN. We therefore conclude that the X-ray emission from R117 is dominated by starburst emission from the galaxy R117_A.     

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