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.

A methodology of characterizing status and trend of land changes in oases: A case study of Sangong River watershed, Xinjiang, China

National Natural Science Foundation of China [40471134]; program of Lights of the West China by the Chinese Academy of Science

Assessing the consequence of land use change on agricultural productivity in China

China's cultivated land has been undergoing dramatic changes along with its rapidly growing economy and population. The impacts of land use transformation on food production at the national scale, however, have been poorly understood due to the lack of detailed spatially explicit agricultural productivity information on cropland change and crop productivity. This study evaluates the effect of the cropland transformation on agricultural productivity by combining the land use data of China for the period of 1990-2000 from TM images and a satellite-based NPP (net primary production) model driven with NOAH/AVHRR data. The cropland area of China has a net increase of 2.79 Mha in the study period, which causes a slightly increased agricultural productivity (6.96 Mt C) at the national level. Although the newly cultivated lands compensated for the loss from urban expansion, but the contribution to production is insignificant because of the low productivity. The decrease in crop production resulting from urban expansion is about twice of that from abandonment of arable lands to forests and grasslands. The productivity of arable lands occupied by urban expansion was 80% higher than that of the newly cultivated lands in the regions with unfavorable natural conditions. Significance of cropland transformation impacts is spatially diverse with the differences in land use change intensity and land productivity across China. The increase in arable land area and yet decline in land quality may reduce the production potential and sustainability of China's agro-ecosystems. (C) 2008 Elsevier B.V. All rights reserved.

Application of rough set-based analysis to extract spatial relationship indicator rules: An example of land use in Pearl River Delta

Spatial relations, reflecting the complex association between geographical phenomena and environments, are very important in the solution of geographical issues. Different spatial relations can be expressed by indicators which are useful for the analysis of geographical issues. Urbanization, an important geographical issue, is considered in this paper. The spatial relationship indicators concerning urbanization are expressed with a decision table. Thereafter, the spatial relationship indicator rules are extracted based on the application of rough set theory. The extraction process of spatial relationship indicator rules is illustrated with data from the urban and rural areas of Shenzhen and Hong Kong, located in the Pearl River Delta. Land use vector data of 1995 and 2000 are used. The extracted spatial relationship indicator rules of 1995 are used to identify the urban and rural areas in Zhongshan, Zhuhai and Macao. The identification accuracy is approximately 96.3%. Similar procedures are used to extract the spatial relationship indicator rules of 2000 for the urban and rural areas in Zhongshan, Zhuhai and Macao. An identification accuracy of about 83.6% is obtained.

The characteristics of land cover and macroscopical ecology changes in the source region of three rivers in Qinghai-Tibet plateau during last 30 years

We obtained four phases of land cover spatial data sets by interpreting MSS images of middle and late 1970s and three phases of TM images of late 1980s, 2004 and 2008 based on field investigation in Three Rivers' Source Region. We analyzed the temporal and spatial characteristics of land cover and macro ecological changes in Three Rivers' Source Region in Qinghai-Tibet plateau since middle and late 1970s. Indicated by land cover condition index change rate and land cover change index, land cover and macroscopical ecological condition degenerated (7090 period Zc -0.63, LCCI -0.58)-obviously degenerated (9004 period, Zc -0.94, LCCI -1.76)-slightly meliorated (0408 period, Zc 0.06, LCCI 0.33). This course was jointly driven by climate change, grassland stocking pressure and implement of ecological construction project.

The effect of land management on plant community composition, species diversity, and productivity of alpine Kobersia steppe meadow

Grassland degradation is widespread and severe on the Tibet Plateau. To explore management approaches for sustainable development of degraded and restored ecosystems, we studied the effect of land degradation on species composition, species diversity, and vegetation productivity, and examined the relative influence of various rehabilitation practices (two seeding treatments and a non-seeded natural recovery treatment) on community structure and vegetation productivity in early secondary succession. The results showed: (1) All sedge and grass species of the natural steppe meadow had disappeared from the severely degraded land. The above-ground and root biomass of severely degraded land were only 38 and 14.7%, respectively, of those of the control. So, the original ecosystem has been dramatically altered by land degradation on alpine steppe meadow. (2) Seeding measures may promote above-ground biomass, particularly grass biomass, and ground cover. Except for the grasses seeded, however, other grass and sedge species did not occur after seeding treatments in the sixth year of seeding. Establishment of grasses during natural recovery treatment progressed slowly compared with during seeding treatments. Many annual forbs invaded and established during the 6 years of natural recovery. In addition, there was greater diversity after natural recovery treatment than after seeding treatments. (3) The above-ground biomass after seeding treatment and natural recovery treatment were 114 and 55%, respectively, of that of the control. No significant differences in root biomass occurred among the natural recovery and seeded treatments. Root biomass after rehabilitation treatment was 23-31% that of the control.

The effect of land management on carbon and nitrogen status in plants and soils of alpine meadows on the Tibetan plateau

Large-scale grassland rehabilitation has been carried out on the severely degraded lands of the Tibetan plateau. The grasslands created provide a useful model for evaluating the recovery of ecosystem properties. The purposes of this research were: (1) to examine the relative influence of various rehabilitation practices on carbon and nitrogen in plants and soils in early secondary succession; and (2) to evaluate the degree to which severely degraded grassland altered plant and soil properties relative to the non-disturbed native community. The results showed: (1) The aboveground tissue C and N content in the control were 105-97 g m(-2) and 3.356gm(-2), respectively. The aboveground tissue C content in the mixed seed treatment, the single seed treatment, the natural recovery treatment and the severely degraded treatment was 137 per cent, 98 per cent, 49 per cent and 38 per cent, respectively, of that in the control. The corresponding aboveground tissue N content was 109 per cent, 84 per cent, 60 per cent and 47 per cent, respectively, of that in the control. (2) Root C and N content in 0-20 cm depths of the control had an 2 2 average 1606 gm(-2) and 30-36 gm(-2) respectively. Root C and N content in the rehabilitation treatments were in the range of 26-36 per cent and 35-53 per cent, while those in the severely degraded treatment were only 17 per cent and 26 per cent of that in the control. (3) In the control the average soil C and N content at 0-20 cm was 11307 gm(-2) and 846 gm(-2), respectively. Soil C content in the uppermost 20 cm in the seeded treatments, the natural recovery treatment and the severely degraded treatment was 67 per cent, 73 per cent and 57 per cent, respectively, while soil N content in the uppermost 20cm was 72 per cent, 82 per cent and 79 per cent, respectively, of that in the control. The severely degraded land was a major C source. Restoring the severely degraded lands to perennial vegetation was an alternative approach to sequestering C in former degraded systems. N was a limiting factor in seeding grassland. It is necessary for sustainable utilization of seeding grassland to supply extra N fertilizer to the soil or to add legume species into the seed mix. Copyright (c) 2005 John Wiley & Sons, Ltd.