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.

Shallow gas in the muddy sediments of Eckernförde Bay, Germany

The seafloor of central Eckernförde Bay is characterised by soft muddy sediments that contain free methane gas. Bubbles of free gas cause acoustic turbidity which is observed with acoustic remote sensing systems. Repeated surveys with subbottom profiler and side scan sonar revealed an annual period both of depth of the acoustic turbidity and backscatter strength. The effects are delayed by 3–4 months relative to the atmospheric temperature cycle. In addition, prominent pockmarks, partly related to gas seepage, were detected with the acoustic systems. In a direct approach gas concentrations were measured from cores using the gas chromatography technique. From different tests it is concluded that subsampling of a core should start at its base and should be completed as soon as possible, at least within 35 min after core recovery. Comparison of methane concentrations of summer and winter cores revealed no significant seasonal variation. Thus, it is concluded that the temperature and pressure influences upon solubility control the depth variability of acoustic turbidity which is observed with acoustic remote sensing systems. The delay relative to the atmospheric temperature cycle is caused by slow heat transfer through the water column. The atmospheric temperature cycle as ‘exiting function’ for variable gas solubility offers an opportunity for modelling and predicting the depth of the acoustic turbidity. In practice, however, small-scale variations of, e.g., salinity, or gas concentration profile in the sediment impose limits to predictions. In addition, oceanographic influences as mixing in the water column, variable water inflow, etc. are further complications that reduce the reliability of predictions.

Fast monostatic GPR modeling

We propose the exploding-reflector method to simulate a monostatic survey with a single simulation. The exploding reflector, used in seismic modeling, is adapted for ground-penetrating radar (GPR) modeling by using the analogy between acoustic and electromagnetic waves. The method can be used with ray tracing to obtain the location of the interfaces and estimate the properties of the medium on the basis of the traveltimes and reflection amplitudes. In particular, these can provide a better estimation of the conductivity and geometrical details. The modeling methodology is complemented with the use of the plane-wave method. The technique is illustrated with GPR data from an excavated tomb of the nineteenth century.

新疆土壤侵蚀遥感影像判读与几个独特问题

在新疆土壤侵蚀遥感调查中，对遥感影像的判读，采用了遥感信息与地学资料相结合、综合分析与主导分析结合、室内判读与专家经验及外业调查结合、分层分类判读的方法；根据新疆水蚀、风蚀、冻融侵蚀具有垂直分布规律的特点，在土壤侵蚀分类时主要考虑降水量、海拔高度和年均温等指标；列出了新疆土壤侵蚀分类分级影像特征；指出盐碱地的侵蚀分类与戈壁的侵蚀分级是有待研究的重要问题。

区域水土流失研究综述

以区域水土流失为主题 ,分析并阐述了该领域的研究现状 ,指出了当前存在的主要问题 ,并对研究的今后发展方向进行了展望。

基于RS的黄河中游多沙粗沙区土地利用变化分析

据1975年的Landsat MSS、1986年和1997年的Landsat TM影像资料,运用遥感影像计算机自动分类方法获取土地利用信息,用GIS空间分析方法以及数理统计方法全面分析了黄河中游多沙粗沙区1975~1986年和1986~1997年两个时期内各土地利用类型的变化幅度、变化速度、数量变化的区域差异、变化方向以及变化方向的区域差异等。结果表明:后期土地利用类型间的相互转化有所增强;耕地、草地、林地和未利用地是本区土地利用变化的主导类型,耕地、草地与其它土地利用类型间的相互转化分布校广;后期耕地被居民地占用的面积和毁林开荒的面积比前期有所增加。

Impacts of the Wenchuan Earthquake on the Giant Panda Nature Reserves in China

Ministry of Science and Technology of China [2008BAK47B02, 2008BAC44B04, 2008BAK50B06, 2008BAC43B01, 2006BAC08B06]

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.