高光谱遥感影像具有光谱分辨率极高的特点,承载了大量可区分不同类型地物的诊断性光谱信息以及区分亚类相似地物之间细微差别的光谱信息,在目标探测领域具有独特的优势。与此同时,高光谱遥感影像也带来了数据维数高、邻近波段之间存在大量冗余信息的问题,高维度的数据结构往往使得高光谱影像异常目标类和背景类之间的可分性降低。为了缓解上述问题,本文提出了一种基于波段选择的协同表达高光谱异常探测算法。首先,使用最优聚类框架对高光谱波段进行选择,获得一组波段子集来表示原有的全部波段,使得高光谱影像异常目标类与背景类之间的可分性增强。然后使用协同表达对影像上的像元进行重建,由于异常目标类和背景类之间的可分性增强,对异常目标像元进行协同表达时将会得到更大的残差,异常目标像元的输出值增大,可以更好地实现异常目标和背景类的分离。本文使用了3组高光谱影像数据进行异常目标探测实验,实验结果表明,该方法与其他现有高光谱异常目标探测算法对比,曲线下面积AUC(Area Under Curve)值更高,可以更好地实现异常目标与背景分离,能够更有效地对高光谱影像进行异常目标探测。 相似文献
The transfer and evolution of stress among rock blocks directly change the void ratios of crushed rock masses and affect the flow of methane in coal mine gobs. In this study, a Lagrange framework and a discrete element method, along with the soft-sphere model and EDEM numerical software, were used. The compaction processes of rock blocks with diameters of 0.6, 0.8, and 1.0 m were simulated with the degrees of compression set at 0%, 5%, 10%, 15%, 20%, and 25%. This study examines the influence of stress on void ratios of compacted crushed rock masses in coal mine gobs. The results showed that stress was mainly transmitted downward through strong force chains. As the degree of compression increased, the strong force chains extended downward, which resulted in the stress at the upper rock mass to become significantly higher than that at the lower rock mass. It was determined that under different degrees of compression, the rock mass of coal mine gobs could be divided, from the bottom to the top, into a lower insufficient compression zone (ICZ) and an upper sufficient compression zone (SCZ). From bottom to top, the void ratios in the ICZ sharply decreased and those in the SCZ slowly decreased. Void ratios in the ICZ were 1.2–1.7 times higher than those in the SCZ.
ABSTRACT High performance computing is required for fast geoprocessing of geospatial big data. Using spatial domains to represent computational intensity (CIT) and domain decomposition for parallelism are prominent strategies when designing parallel geoprocessing applications. Traditional domain decomposition is limited in evaluating the computational intensity, which often results in load imbalance and poor parallel performance. From the data science perspective, machine learning from Artificial Intelligence (AI) shows promise for better CIT evaluation. This paper proposes a machine learning approach for predicting computational intensity, followed by an optimized domain decomposition, which divides the spatial domain into balanced subdivisions based on the predicted CIT to achieve better parallel performance. The approach provides a reference framework on how various machine learning methods including feature selection and model training can be used in predicting computational intensity and optimizing parallel geoprocessing against different cases. Some comparative experiments between the approach and traditional methods were performed using the two cases, DEM generation from point clouds and spatial intersection on vector data. The results not only demonstrate the advantage of the approach, but also provide hints on how traditional GIS computation can be improved by the AI machine learning. 相似文献
With the rapid development of space technology, earth observation technology and sky observatory technolo-gy, they have played a more and more important part in monitoring and predicting of earthquakes and volcanoes in the terres-trial land. In recent years, the related agencies have done the experiments and researches on monitoring and predicting ofearthquakes and volcanoes in the forewarning period by means of many approaches, such as satellite thermal infrared re-mote sensing (TIRS), Global Positioning System (GPS), differential interferometric synthesis aperture radar (D-INSAR),astronomical time-latitude residual anomaly, and Geographic Information Systems (GIS), etc. A quite large number of re-search foundation has been built in the fundamental theories and application methods. The experiments and researcheshave shown that these technology is efficient methods for high frequency crust movement. If the existed separate scientificforces and results are possibly assembled together to form a more complete integration monitoring system with the combina-tion of space, sky observation, ground, deep geology and macro anomaly, it will come into a new stage of monitoring andpredicting of earthquakes and volcanic eruptions. 相似文献
Tibet is located at the southwest boundary of China. It is the main body of the Qinghai-Tibet Plateau, the highest and the youngest plateau in the world. Owing to complicated geology, Neo-tectonic movements, geomorphology, climate and plateau environment, various mountain hazards, such as debris flow, flash flood, landslide, collapse, snow avalanche and snow drifts, are widely distributed along the Jinsha River (the upper reaches of the Yangtze River), the Nu River and the Lancang River in the east, and the Yarlungzangbo River, the Pumqu River and the Poiqu River in the south and southeast of Tibet. The distribution area of mountain hazards in Tibet is about 589,000 km^2, 49.3% of its total territory. In comparison to other mountain regions in China, mountain hazards in Tibet break out unexpectedly with tremendously large scale and endanger the traffic lines, cities and towns, farmland, grassland, mountain environment, and make more dangers to the neighboring countries, such as Nepal, India, Myanmar and Bhutan. To mitigate mountain hazards, some suggestions are proposed in this paper, such as strengthening scientific research, enhancing joint studies, hazards mitigation planning, hazards warning and forecasting, controlling the most disastrous hazards and forbidding unreasonable human exploring activities in mountain areas. 相似文献