Decision tree classification of land cover from remotely sensed data

Decision tree classification algorithms have significant potential for land cover mapping problems and have not been tested in detail by the remote sensing community relative to more conventional pattern recognition techniques such as maximum likelihood classification. In this paper, we present several types of decision tree classification algorithms arid evaluate them on three different remote sensing data sets. The decision tree classification algorithms tested include an univariate decision tree, a multivariate decision tree, and a hybrid decision tree capable of including several different types of classification algorithms within a single decision tree structure. Classification accuracies produced by each of these decision tree algorithms are compared with both maximum likelihood and linear discriminant function classifiers. Results from this analysis show that the decision tree algorithms consistently outperform the maximum likelihood and linear discriminant function classifiers in regard to classf — cation accuracy. In particular, the hybrid tree consistently produced the highest classification accuracies for the data sets tested. More generally, the results from this work show that decision trees have several advantages for remote sensing applications by virtue of their relatively simple, explicit, and intuitive classification structure. Further, decision tree algorithms are strictly nonparametric and, therefore, make no assumptions regarding the distribution of input data, and are flexible and robust with respect to nonlinear and noisy relations among input features and class labels.

Nitrogen-15 signals of leaf-litter-soil continuum as a possible indicator of ecosystem nitrogen saturation by forest succession and N loads

National Key Research and Development Program [2010CB833502]; National Natural Science Foundation of China [30600071, 40601097, 30590381]; Chinese Academy of Sciences [KZCX2-YW-432, O7V70080SZ, LENOM07LS-01]; GUCAS [O85101PM03]

Estimation of wind erosion rates by using Cs-137 tracing technique: A case study in Tariat-Xilin Gol transect, Mongolian Plateau

Wind erosion is one of the major environmental problems in semi-arid and arid regions. Here we established the Tariat-Xilin Gol transect from northwest to southeast across the Mongolian Plateau, and selected seven sampling sites along the transect. We then estimated the soil wind erosion rates by using the Cs-137 tracing technique and examined their spatial dynamics. Our results showed that the Cs-137 inventories of sampling sites ranged from 265.63 +/- 44.91 to 1279.54 +/- 166.53 Bq.m(-2), and the wind erosion rates varied from 64.58 to 419.63 t.km(-2).a(-1) accordingly. In the Mongolia section of the transect (from Tariat to Sainshand), the wind erosion rate increased gradually with vegetation type and climatic regimes; the wind erosion process was controlled by physical factors such as annual precipitation and vegetation coverage, etc., and the impact of human activities was negligible. While in the China section of the transect (Inner Mongolia), the wind erosion rates of Xilin Hot and Zhengxiangbai Banner were thrice as much as those of Bayannur of Mongolia, although these three sites were all dominated by typical steppe. Besides the physical factors, higher population density and livestock carrying level should be responsible for the higher wind erosion rates in these two regions of Inner Mongolia.

Using the RBFN model and GIS technique to assess wind erosion hazard of inner Mongolia, China

Soil wind erosion is the primary process and the main driving force for land desertification and sand-dust storms in and and semi-arid areas of Northern China. While many researchers have studied this issue, this study quantified the various indicators of soil wind erosion, using the GIS technology to extract the spatial data and to construct a RBFN (Radial Basis Function Network) model for Inner Mongolia. By calibrating sample data of the different levels of wind erosion hazard, the model parameters were established, and then the assessment of wind erosion hazard. Results show that in the southern parts of Inner Mongolia wind erosion hazards are very severe, counties in the middle regions of Inner Mongolia vary from moderate to severe, and in eastern are slight. Comparison of the results with other research shows conformity with actual conditions, proving the reasonability and applicability of the RBFN model. Copyright (C) 2007 John Wiley & Sons, Ltd.

Distribution characteristics of (CS)-C-137 in wind-eroded soil profile and its use in estimating wind erosion modulus

Due to its inert reaction in soil system and distinctive vertical distribution in soil profile, caesium-137 (Cs-137) has been used as a tracer to assess wind erosion. In this study, 62 soil samples were collected from 4 sampling sites in Taipusi County, Inner Mongolia; Caesium-137 activities for those soil samples were measured using a gamma-ray spectrometry in Sichuan University, Chengdu. Distribution pattern of Cs-137 in vertical soil profile was different for different land use and land cover types. Caesium-137 was distributed homogeneously in plow layer of cropland, and negatively exponential in low to medium cover grassland. Distribution pattern in high covered grassland was represented by a peak at 2-4 cm soil depth followed by a negative exponential curve. Based on those findings, simplified mass balance model was chosen to estimate the rate of wind erosion for cropland, while profile distribution model was used for grassland. Estimated wind erosion rates were 7990, 4270 and 1808 Mg(.)km(-2.)a(-1) for cropland, low cover grassland and medium cover grassland, respectively. Wind erosion intensity correlated negatively with plant cover.