A Comparison between a Modified Counter Propagation Network and an Extended Self-Organizing Map in Remotely Sensed Data Classification     

Yongliang Chen  Micha I. Pazner  Wei Wu 《Mathematical Geology》2007,39(6):559-574

A modified counter propagation network model and an extended self-organizing map model have the same three-layer network architecture while employing slightly different learning rules. Their network architecture comprises an input layer, a Kohonen layer and an output layer. The neurons between two neighboring layers are fully connected and the neighboring neurons within the Kohonen layer also have neighborhood connections. The modified counter propagation network model employs the Kohonen algorithm to train the Kohonen layer while using the Widrow–Hoff rule to train the output layer. However, the extended self-organizing map model applies a modified Kohonen’s learning rule to train both the Kohonen layer and the output layer. This paper compares the performances of these two models in supervised classification of remotely sensed data. The training results show that compared to the extended self-organizing map model, the modified counter propagation model has faster learning speed but larger output errors. The classification results indicate that the extended self-organizing map model has a faster classification speed and a much higher classification precision than the modified counter propagation model.  相似文献   

Irrigated area determination: a case study in the Province of San Juan,Argentina     

Graciela Salinas de Salmuni  Inés Velasco  Mirta Fresina  Alberto L. Flores 《GeoJournal》2007,70(4):273-279

Much of the central-western region of Argentina, where San Juan Province is located, experiences arid to semi-arid climatic conditions with low average annual rainfall accompanied by substantial evapotranspiration. Consequently, a viable crop industry depends to a large extent upon irrigation from major river systems. Increasing demand for water in the lower basin of the San Juan River is emphasizing the need for more accurate estimates of water used for irrigation. Since the water demand for a particular crop is very closely related to crop area, monitoring the area of crop under irrigation is considered a proxy for the amount of water used. Landsat 5 imagery for the growing season, field data and aerial photographs were used to evaluate crop area.  相似文献   

Aftershocks series monitoring of the September 18, 2004 M = 4.6 earthquake at the western Pyrenees: A case of reservoir-triggered seismicity?     

M. Ruiz  O. Gasp  J. Gallart  J. Díaz  J.A. Pulgar  J. García-Sansegundo  C. Lpez-Fernndez  J.M. Gonzlez-Cortina 《Tectonophysics》2006,424(3-4):223

On September 18, 2004, a 4.6 mbLg earthquake was widely felt in the region around Pamplona, at the western Pyrenees. Preliminary locations reported an epicenter less than 20 km ESE of Pamplona and close to the Itoiz reservoir, which started impounding in January 2004. The area apparently lacks of significant seismic activity in recent times. After the main shock, which was preceded by series of foreshocks reaching magnitudes of 3.3 mbLg, a dense temporal network of 13 seismic stations was deployed there to monitor the aftershocks series and to constrain the hypocentral pattern. Aftershock determinations obtained with a double-difference algorithm define a narrow epicentral zone of less than 10 km², ESE–WNW oriented. The events are mainly concentrated between 3 and 9 km depth. Focal solutions were computed for the main event and 12 aftershocks including the highest secondary one of 3.8 mbLg. They show mainly normal faulting with some strike-slip component and one of the nodal planes oriented NW–SE and dipping to the NE. Cross-correlation techniques applied to detect and associate events with similar waveforms, provided up to 33 families relating the 67% of the 326 relocated aftershocks. Families show event clusters grouped by periods and migrating from NW to SE. Interestingly, the narrow epicentral zone inferred here is located less than 4 km away from the 111-m high Itoiz dam. These hypocentral results, and the correlation observed between fluctuations of the reservoir water level and the seismic activity, favour the explanation of this foreshock–aftershock series as a rapid response case of reservoir-triggered seismicity, burst by the first impoundment of the Itoiz reservoir. The region is folded and affected by shallow dipping thrusts, and the Itoiz reservoir is located on the hangingwall of a low angle southward verging thrust, which might be a case sensible to water level fluctuations. However, continued seismic monitoring in the coming years is mandatory in this area to infer more reliable seismotectonic and hazard assessments.  相似文献   

Tracer methods used to verify the hypothesis of Cvijić about the underground connection between Prespa and Ohrid Lake     

Sokrat Amataj  Todor Anovski  Ralf Benischke  Romeo Eftimi  Laurence L. Gourcy  Liliana Kola  Ioannis Leontiadis  Eftim Micevski  Alqiviadis Stamos  Jovan Zoto 《Environmental Geology》2007,51(5):749-753

Prespa Lake and Ohrid Lake constitute a hydraulic system shared between Albania, FYR of Macedonia and Greece. Karst rocks separate both lakes. The elevation of Prespa Lake is about 150 m higher than that of Ohrid Lake. Considering these facts, Cvijić formulated in 1906 the hypothesis that Prespa Lake recharges the St. Naum and Tushemisht springs at Ohrid lakeside. Environmental isotopes demonstrated that Prespa Lake recharges about 37–42 and 52–54% of water emerging in St. Naum, and Tushemisht springs, respectively. An artificial tracer experiment carried out in 2002 physically demonstrated the underground connection between both lakes. This experiment confirmed the supposed underground connection and brought important information about the groundwater velocity, transit time, and karst water conduits development.  相似文献   

Environmental impact assessment of risk associated with groundwater overdraft remediation in cone of depression,Jining, China     

B. T. I. Ong′or  Long-cang Shu  Pei-gui Liu 《Environmental Geology》2007,53(4):751-762

In this paper, a simple scenario and probabilistic approach is used to assess the potential groundwater risk due to proposed overdraft remedial actions in cone of depression, Jining City, China. Focusing on the concentrations of Chloride ions (Cl⁻) and total hardness (TH), the impact of artificial recharge and reduced pumping on groundwater quality and quantity is analysed by using the three-dimensional finite difference groundwater flow and transport model, Visual MODFLOW, to simulate groundwater flow and transport within the study area based on scenarios, and utilizes SURFER software to map risk levels. Although 5, 10 or 15% reduced pumping with artificial recharge leads to more decrease in Cl⁻ and TH concentrations than the 25%, less volume increase is achieved for the remediation of land subsidence and other environmental problems in the cone of depression. The Cl⁻ concentrations in recovered groundwater are within the desired concentration of 200 mg/l; however, TH in some cases are above the maximum permissible limit of 500 mg/l, with an exceedence probability of about 0.67 for recharge and recharge with reduced pumping at 25%. The presence of fractures and hydrogeological complexity greatly determines impacts of remediation, and the 22% reduced pumping with artificial recharge offers an optimum strategy for overdraft remediation in the Jining cone of depression.  相似文献   

基于MatLab的神经网络在江苏矿山地质环境评估中的应用     

刘洪  张宏斌 《江苏地质》2007,31(4):348-353

神经网络作为一种新的方法体系,具有分布并行处理、非线性映射、自适应学习和鲁棒容错等特性,在模式识别、控制优化和智能信息处理等方面有着广泛的应用。利用MatLab的神经网络工具箱,建立了江苏矿山地质环境质量的评估模型,评估结果经过实际验证,具有较高的可信度和实用性。  相似文献   

Degradation of Tetrachloroethene by Several Co-metabolism Substrates in Groundwater          下载免费PDF全文

SHI Jinghua LIU Fei CHEN Honghan LI Ye 《《地质学报》英文版》2007,81(5):827-832

Tetrachloroethene （PCE） is biodegraded by reductive dechlorination with co-metabolism substrates under anaerobic conditions. By inoculating sludge from an anaerobic pool, a biodegradation test of PCE is conducted in the anaerobic condition. In the test, several substrates including methanol, ethanol, formate, acetate, lactate and glucose, are conducive to the conversion from PCE to TCE and 1,1-DCE. The results show the microbe can be cultivated well under the anaerobic circumstances of mixture of sewage （sludge） and soil with the index of COD after eleven days. Degradation of PCE accords with one order reaction kinetics equation. The sequence of the reaction rate constant is Kacetate 〉Kglucose 〉 Klactate 〉 Kethanol 〉 Kformate 〉 Kmethanol, and acetate is an outstanding co-metabolism substratum whose reaction rate constant is 0.6632d^-1.  相似文献   

一种基于人工免疫的图像分割算法     

汤凌  郑肇葆  虞欣 《测绘科技情报》2006,(3)

图像二维熵分割,一直因耗时长而限制了实际应用。本文借鉴生物免疫思想,提出二维熵图像分割的人工免疫算法。在克隆选择算法中引入疫苗的免疫接种,用于优化最优分割阈值对的搜索过程。在遥感高分辨率图像上的实验显示,该算法不仅能准确搜索到最优阈值对,而且计算时间只有传统算法的1.8%。该算法也验证了人工免疫思想用于图像分割的可行性和有效性。  相似文献   

Texture classification of Mediterranean land cover     

《International Journal of Applied Earth Observation and Geoinformation》2007,9(3):322-334

Maximum likelihood (ML) and artificial neural network (ANN) classifiers were applied to three Landsat Thematic Mapper (TM) image sub-scenes (termed urban, agricultural and semi-natural) of Cukurova, Turkey. Inputs to the classifications comprised (i) spectral data and (ii) spectral data in combination with texture measures derived on a per-pixel basis. The texture measures used were: the standard deviation and variance and statistics derived from the co-occurrence matrix and the variogram. The addition of texture measures increased classification accuracy for the urban sub-scene but decreased classification accuracy for agricultural and semi-natural sub-scenes. Classification accuracy was dependent on the nature of the spatial variation in the image sub-scene and, in particular, the relation between the frequency of spatial variation and the spatial resolution of the imagery. For Mediterranean land, texture classification applied to Landsat TM imagery may be appropriate for the classification of urban areas only.  相似文献   

月降水量的神经网络混合预报模型研究   总被引：3，自引：8，他引：3  

金龙  罗莹  王业宏  李永华 《高原气象》2003,22(6):618-623

以均生函数表征预报量自身周期变化，结合500hPa月平均高度场和月平均海温场预报因子，采用神经网络方法建立了一种新的短期气候预报模型。分别以广西桂北、桂中和桂南6月降水量作为预报对象进行预报试验，结果表明，这种新的预报方法比均生函数回归预报模型及高度场、海温场预报因子的回归预报模型，具有更好的物理基础和预报能力。  相似文献