概率神经网络与BP网络模型在遥感图像分类中的对比研究

通过分析概率神经网络(以下称PNN)的基本结构及其训练算法,建立了卫星图像分类的概率神经网络模型,并通过实例对比分析了概率神经网络与BP网络分类模型的分类效果。实验表明,PNN图像分类方法在分类精度上优于误差反向传播神经网络模型,且分类时间相当,是一种有效的图像分类方法。     

复种指数遥感监测方法

复种指数是反映水土光与自然资源利用程度的指标 ,其实质是沿时间序列 ,反映某一种植制度对耕地的利用程度。联系复种指数与时间序列NDVI曲线的纽带是农作物年内的循环规律。时间序列的NDVI值蕴涵着植被的生长和枯萎的年循环节律 ,经时间序列谐函数分析法 (HarmonicAnalysisofTimeSeries ,HANTS)重构的NDVI曲线 ,可以准确地反映农作物的出苗、拔节、抽穗、收获等物理过程。因此 ,根据时间序列的NDVI曲线的周期性 ,可以反向捕捉到耕地农作物动态的信息 ,进而得到耕地的复种指数。本文依据上述原理 ,提出复种指数遥感监测的方法 ,然后用 1999年至 2 0 0 2年 4年的VGT(SPOT4卫星vegetation数据 )旬合成NDVI时间序列数据集提取了复种指数 ,并利用地面样区观测结果和统计数据进行检验 ,取得很高的精度。     

The analysis of SPOT-5 characteristics on land cover Classification

<正>KnowledgeaboutlandcoverandlandusehasbecomeincreasinglyimportantastheNationplanstoovercometheproblemsofuncontrolleddevelopment,deterioratingenvironmentalquality,lossofprimeagriculturallandsetc.Landuseandlandcoverdataareneededintheanalysisofenvironmentalprocessesandproblemstoknowiflivingconditionsandstandardsaretobeimprovedormaintainedatcurrentlevels.     

利用SPOT和ETM+影像进行县级土地利用调查--以河北省万全县为例

本文以SPOT和ETM 影像作为主要信息源，经过对图像进行几何纠正、配准、增强和融合等一系列处理后，在ARCVIEW GIS基础上，成功完成了对河北省万全县土地资源利用情况的调查分析。同时还对应用遥感技术成功获取土地资源利用信息的方法和技术进行了探讨。     

Seasonal and inter-annual relationships between vegetation and climate in central New Mexico, USA

Linear correlations between seasonal and inter-annual measures of meteorological variables and normalized difference vegetation index (NDVI) are calculated at six nearby yet distinct vegetation communities in semi-arid New Mexico, USA Monsoon season (June–September) precipitation shows considerable positive correlation with NDVI values from the contemporaneous summer, following spring, and following summer. Non-monsoon precipitation (October–May), temperature, and wind display both positive and negative correlations with NDVI values. These meteorological variables influence NDVI variability at different seasons and time lags. Thus vegetation responds to short-term climate variability in complex ways and serves as a source of memory for the climate system.     

Sequence of faulting and deformation during the 2000 eruptions of the Usu Volcano, Hokkaido, Japan—interpretation and image analyses of aerial photographs

Significant faulting and deformation of the ground surface has been rarely known during volcanic eruptions. Usu Volcano, Hokkaido, Japan, is a unique example of deformation due to felsic magma intrusion. Usu Volcano has a history of such types of eruptions as phreatic, pumice eruption (Plinian type), pyroclastic flowing and lava doming since 1663. On March 31, 2000, phreatomagmatic to phreatic eruptions took place after 23 years of dormancy in the western piedmont, followed by explosions on the western flank of Usu Volcano. They were associated with significant deformation including faulting and uplift. The eruptions and deformation were continuing up to the end of May 2000.We identified the faulting using total nine sets of aerial photographs taken from before the eruption (March 31, 2000) to more than 1 year (April 27, 2001) after the end of the activity, and traced deformation processes through image processing using aerial photographs. We found that some of the new faults and the associated phreatic eruptions were related to old faults formed during the 1977–1981 eruptive episode.The image processing has revealed that the surface deformation is coincident with the area of faulting forming small grabens and the phreatic explosion vents. However, the faulting and main explosive eruptions did not take place in the highest uplift area, but along the margin. This suggests that the faulting and explosive activities were affected by small feeder channels diverging from the main magma body which caused the highest uplift.     

Image processing of 2D resistivity data for imaging faults

A methodology to locate automatically limits or boundaries between different geological bodies in 2D electrical tomography is proposed, using a crest line extraction process in gradient images. This method is applied on several synthetic models and on field data set acquired on three experimental sites during the European project PALEOSIS where trenches were dug. The results presented in this work are valid for electrical tomographies data collected with a Wenner-alpha array and computed with an l₁ norm (blocky inversion) as optimization method. For the synthetic cases, three geometric contexts are modelled: a vertical and a dipping fault juxtaposing two different geological formations and a step-like structure. A superficial layer can cover each geological structure. In these three situations, the method locates the synthetic faults and layer boundaries, and determines fault displacement but with several limitations. The estimated fault positions correlate exactly with the synthetic ones if a conductive (or no superficial) layer overlies the studied structure. When a resistive layer with a thickness of 6 m covers the model, faults are positioned with a maximum error of 1 m. Moreover, when a resistive and/or a thick top layer is present, the resolution significantly decreases for the fault displacement estimation (error up to 150%). The tests with the synthetic models for surveys using the Wenner-alpha array indicate that the proposed methodology is best suited to vertical and horizontal contacts. Application of the methodology to real data sets shows that a lateral resistivity contrast of 1:5–1:10 leads to exact faults location. A fault contact with a resistivity contrast of 1:0.75 and overlaid by a resistive layer with a thickness of 1 m gives an error location ranging from 1 to 3 m. Moreover, no result is obtained for a contact with very low contrasts (1:0.85) overlaid by a resistive soil. The method shows poor results when vertical gradients are greater than horizontal ones. This kind of image processing technique should be systematically used for improving the objectiveness of tomography interpretation when looking for limits between geological objects.     

Groundwater vulnerability mapping: A GIS and fuzzy rule based integrated tool

Contamination of groundwater has become a major concern in recent years. Since testing of water quality of all domestic and irrigation wells within large watersheds is not economically feasible, one frequently used monitoring strategy is to develop contamination potential maps of groundwater, and then prioritize those wells located in the potentially highly contaminated areas for testing of contaminants. However, generation of contamination potential maps based on groundwater sensitivity and vulnerability is not an easy task due inherent uncertainty. Therefore, the overall goal of this research is to improve the methodology for the generation of contamination potential maps by using detailed landuse/pesticide and soil structure information in conjunction with selected parameters from the DRASTIC model. The specific objectives of this study are (i) to incorporate GIS, GPS, remote sensing and the fuzzy rule-based model to generate groundwater sensitivity maps, and (ii) compare the results of our new methodologies with the modified DRASTIC Index (DI) and field water quality data. In this study, three different models were developed (viz. DI_fuzz, VI_fuzz and VI_{fuzz_ped}) and were compared to the DI. Once the preliminary fuzzy logic-based (DI_fuzz) was generated using selected parameters from DI, the methodology was further refined through VI_fuzz and VI_{fuzz_ped} models that incorporated landuse/pesticide application and soil structure information, respectively. This study was conducted in Woodruff County of the Mississippi Delta region of Arkansas. Water quality data for 55 wells were used to evaluate the contamination potential maps. The sensitivity map generated by VI_{fuzz_ped} with soil structure showed significantly better coincidence results when compared with the field data.     

Urban development and flooding in Houston Texas, inferences from remote sensing data using neural network technique

The effects of urban development on the natural ecosystem and its link to the increased flooding in Houston, Texas were evaluated. Houston is suitable for this type of analysis due to its 1.95 million population, large geographic area and fast growth rate. Using neural network techniques, four Landsat Thematic Mapper images were grouped into five land use classes for the period 1984 to 2003: vegetation, bare ground, water, concrete and asphalt. Results show that asphalt and concrete increased 21% in the time period 1984–1994, 39% in 1994–2000 and 114%, from 2000 to 2003, while vegetation suffered an overall decrease. When change detection data are compared with runoff ratio data, a relationship between increased runoff and urban development is apparent, which indicates increased chances of flooding. Initial results of this work are made available to the public in GIS format via internet using Arc Internet Map Server (ArcIMS) at .     

Application of Distributed Temperature Sensing for coupled mapping of sedimentation processes and spatio‐temporal variability of groundwater discharge in soft‐bedded streams

The delineation of groundwater discharge areas based on Distributed Temperature Sensing (DTS) data of the streambed can be difficult in soft‐bedded streams where sedimentation and scouring processes constantly change the position of the fibre optic cable relative to the streambed. Deposition‐induced temperature anomalies resemble the signal of groundwater discharge while scouring will cause the cable to float in the water column and measure stream water temperatures. DTS applied in a looped layout with nine fibre optic cable rows in a 70 × 5 m section of a soft‐bedded stream made it possible to detect variability in streambed temperatures between October 2011 and January 2012. Detailed monthly streambed elevation surveys were carried out to monitor the position of the fibre optic cable relative to the streambed and to quantify the effect of sedimentation processes on streambed temperatures. Based on the simultaneous interpretation of streambed temperature and elevation data, a method is proposed to delineate potential high‐groundwater discharge areas and identify deposition‐induced temperature anomalies in soft‐bedded streams. Potential high‐discharge sites were detected using as metrics the daily minimum, maximum and mean streambed temperatures as well as the daily amplitude and standard deviation of temperatures. The identified potential high‐discharge areas were mostly located near the channel banks, also showing temporal variability because of the scouring and redistribution of streambed sediments, leading to the relocation of pool‐riffle sequences. This study also shows that sediment deposits of 0.1 m thickness already resulted in an increase in daily minimum streambed temperatures and decrease in daily amplitude and standard deviation. Scouring sites showed lower daily minimum streambed temperatures and higher daily amplitude and standard deviation compared with areas without sedimentation and scouring. As a limitation of the approach, groundwater discharge occurring at depositional and scouring areas cannot be identified by the metrics applied. Copyright © 2015 John Wiley & Sons, Ltd.