Application of geochemical zonality coefficients in mineral prospectivity mapping

Indices of geochemical zonality (Vz) of multielements around mineral deposits and their spatial associations with particular geological, geochemical, and structural factors are critical aspects that must be considered in mineral exploration. Values of Vz indices allow distinction between sub-ore and supra-ore anomalies, which are associated with outcropping and blind deposits, respectively. In this paper, we used a map of a Vz index (Zn?Pb/Cu*Ag) in weights-of-evidence analysis of regional-scale prospectivity for porphyry-Cu deposits in the area covered by 1:100,000 scale map sheet of Jebal-Barez (Kerman province, southern Iran). For comparison, we used a Cu map instead of the Vz map in the weights-of-evidence (WofE) analysis. The Vz-in-WofE prospectivity model outperforms the Cu-in-WofE prospectivity model. In fact, prior to writing this paper, blind porphyry-Cu mineralization was intersected at depth by borehole exploration in a high prospectivity zone delineated by the Vz-in-WofE model. The results demonstrate the usefulness of the Vz-in-WofE for regional-scale targeting of blind mineral deposits.     

Objective selection of suitable unit cell size in data-driven modeling of mineral prospectivity

In GIS-based data-driven modeling of mineral prospectivity, a suitably fine unit cell size is used for spatial representation of known occurrences of mineral deposits of the type sought (D) in a study area (T). However, until now, the unit cell size is chosen subjectively. In this paper, a methodology is proposed for objective selection of the most suitable unit cell size for data-driven modeling of mineral prospectivity using a raster-based GIS. A set of choices of suitable unit cell sizes is first derived via point pattern analysis of a set of known occurrences of mineral deposits of the type sought. Then, (a) the lower limit of a set of choices of suitable unit cell sizes is considered and defined according to the map scales from which spatial data for mineral prospectivity mapping were derived, and (b) the upper limit of the same set of choices of suitable unit cell sizes is considered (and revised as necessary) based on knowledge of spatial extents of mineral deposits of the type sought or via analysis of reflexive nearest neighbour points. Finally, it is shown that fractal analysis of spatial contrast between unit cells containing D and unit cells not containing D in T provides for objective selection of the most suitable unit cell size. In a case study application of the weight-of-evidence method to mineral prospectivity mapping, using the most suitable unit cell size, found via the proposed methodology, results in spatial evidence weights and weight uncertainties that are nearly identical to those derived by using the finest (i.e., lower limit) unit cell size. In contrast to using the most suitable unit cell size, using coarser unit cell sizes result in higher positive weights, lower negative weights and higher weight uncertainties of spatial evidence of mineral prospectivity. The proposed methodology for objective selection of the most suitable unit cell size in data-driven modeling of mineral prospectivity using a raster-based GIS is robust and can easily be implemented.     

Landsat urban mapping based on a combined spectral-spatial methodology

Urban mapping using Landsat Thematic Mapper (TM) imagery presents numerous challenges. These include spectral mixing of diverse land cover components within pixels, spectral confusion with other land cover features such as fallow agricultural fields and the fact that urban classes of interest are of the land use and not the land cover category. A new methodology to address these issues is proposed. This approach involves, as a first step, the generation of two independent but rudimentary land cover products, one spectral-based at the pixel level and the other segment-based. These classifications are then merged through a rule-based approach to generate a final product with enhanced land use classes and accuracy. A comprehensive evaluation of derived products of Ottawa, Calgary and cities in southwestern Ontario is presented based on conventional ground reference data as well as inter-classification consistency analyses. Producer accuracies of 78% and 73% have been achieved for urban ‘residential’ and ‘commercial/industrial’ classes, respectively. The capability of Landsat TM to detect low density residential areas is assessed based on dwelling and population data derived from aerial photography and the 2001 Canadian census. For low population densities (i.e. below 3000 persons/km²), density is observed to be monotonically related to the fraction of pixels labeled ‘residential’. At higher densities, the fraction of pixels labeled ‘residential’ remains constant due to Landsat's inability to distinguish between high-rise apartment dwellings and commercial/industrial structures.     

Noise-driven numerical irreversibility in molecular dynamics technique

It is widely believed that, in molecular dynamics (MD) simulations, round-off errors can cause numerical irreversibility since, in the standard MD, floating-point real number arithmetic is employed and round-off errors cannot be avoided. To investigate the characteristic of this numerical irreversibility, the ‘bit-reversible algorithm’, which is completely time-reversible and is free from any round-off error, is made use of as a test bed. Through this study, it is clearly demonstrated that, other than the extent of the stability of the system, the appearance of irreversibility is related to the ‘quantity’ of the controlled noise. By means of the bit-reversible simulation added to the controlled noise of an appropriate ‘quantity’, the characteristic of the numerical irreversibility in the standard MD is revealed.     

Comparison of support vector machine,artificial neural network,and spectral angle mapper algorithms for crop classification using LISS IV data

The Resourcesat-2 is a highly suitable satellite for crop classification studies with its improved features and capabilities. Data from one of its sensors, the linear imaging and self-scanning (LISS IV), which has a spatial resolution of 5.8 m, was used to compare the relative accuracies achieved by support vector machine (SVM), artificial neural network (ANN), and spectral angle mapper (SAM) algorithms for the classification of various crops and non-crop covering a part of Varanasi district, Uttar Pradesh, India. The separability analysis was performed using a transformed divergence (TD) method between categories to assess the quality of training samples. The outcome of the present study indicates better performance of SVM and ANN algorithms in comparison to SAM for the classification using LISS IV sensor data. The overall accuracies obtained by SVM and ANN were 93.45% and 92.32%, respectively, whereas the lower accuracy of 74.99% was achieved using the SAM algorithm through error matrix analysis. Results derived from SVM, ANN, and SAM classification algorithms were validated with the ground truth information acquired by the field visit on the same day of satellite data acquisition.     

CHRIS 高光谱图像森林类型分类方法比较研究

以长白山为试验区,选择CHRIS/PROBA高光谱零度角遥感数据,在对其进行预处理的基础上,通过应用最大似然法(MLC)、最小距离法、支持向量机法(SVM)和光谱角填图法(SAM)等几种常用的高光谱遥感分类方法对影像进行森林类型分类。利用混淆矩阵对分类结果进行验证,结果显示:在高光谱遥感森林类型分类中,SVM总体分类精度最高,为84.60％;其次是MLC,为 83.53％,最小距离法73.81％,SAM 56.49％。Kappa系数从高到底为:SVM 0.78,MLC 0.77,最小距离法0.68,SAM 0.52。经过比较分析,得出SVM分类方法精度最高,这表明该方法用于高光谱遥感森林分类中的实用性和优越性。     

Assessing the utility of airborne hyperspectral and LiDAR data for species distribution mapping in the coastal Pacific Northwest, Canada

To effectively manage forested ecosystems an accurate characterization of species distribution is required. In this study we assess the utility of hyperspectral Airborne Imaging Spectrometer for Applications (AISA) imagery and small footprint discrete return Light Detection and Ranging (LiDAR) data for mapping 11 tree species in and around the Gulf Islands National Park Reserve, in coastal South-western Canada. Using hyperspectral imagery yielded producer's and user's accuracies for most species ranging from > 52-95.4 and > 63-87.8%, respectively. For species dominated by definable growth stages, pixel-level fusion of hyperspectral imagery with LiDAR-derived height and volumetric canopy profile data increased both producer's (+ 5.1-11.6%) and user's (+ 8.4-18.8%) accuracies. McNemar's tests confirmed that improvements in overall accuracies associated with the inclusion of LiDAR-derived structural information were statistically significant (p < 0.05). This methodology establishes a specific framework for mapping key species with greater detail and accuracy then is possible using conventional approaches (i.e., aerial photograph interpretation), or either technology on its own. Furthermore, in the study area, acquisition and processing costs were lower than a conventional aerial photograph interpretation campaign, making hyperspectral/LiDAR fusion a viable replacement technology.     

Stacked Autoencoder-based deep learning for remote-sensing image classification: a case study of African land-cover mapping

Land-cover mapping is an important research topic with broad applicability in the remote-sensing domain. Machine learning algorithms such as Maximum Likelihood Classifier (MLC), Support Vector Machine (SVM), Artificial Neural Network (ANN), and Random Forest (RF) have been playing an important role in this field for many years, although deep neural networks are experiencing a resurgence of interest. In this article, we demonstrate early efforts to apply deep learning-based classification methods to large-scale land-cover mapping. Based on the Stacked Autoencoder (SAE), one of the deep learning models, we built a classification framework for large-scale remote-sensing image processing. We adjusted and optimized the model parameters based on our test samples. We compared the performance of the SAE-based approach with traditional classification algorithms including RF, SVM, and ANN with multiple performance analytics. Results show that the SAE classifier trained with an entire set of African training samples achieves an overall classification accuracy of 78.99% when assessed by test samples collected independently of training samples, which is higher than the accuracies achieved by the other three classifiers (76.03%, 77.74%, and 77.86% of RF, SVM, and ANN, respectively) based on the same set of test samples. We also demonstrated the advantages of SAE in prediction time and land-cover mapping results in this study.     

Teachers' acceptance and use of an educational portal

In this study, teachers' acceptance and use of an educational portal is assessed based on data from two sources: usage data (number of logins, downloads, uploads, reactions and pages viewed) and an online acceptance questionnaire. The usage data is extracted on two occasions from the portal's database: at survey completion (T1) and twenty-two months later (T2). Framework for this study is C-TAM-TPB (Combined Technology Acceptance Model and Theory of Planned Behavior). 919 usable responses from teachers are obtained. Based on the observed use data at T1, four types of portal users are distinguished: ‘new’ (N = 37), ‘light’ (N = 641), ‘medium’ (N = 201), and ‘heavy’ (N = 40). Path analyses show that all predictor variables in C-TAM-TPB influence teachers' portal acceptance, but their significance level varies depending on the user type. The strongest predictors of behavioral intention to use the portal are attitude (‘new’) and perceived usefulness (‘light’, ‘medium’ and ‘heavy’), with variance explained ranging from .39 (‘medium’) to .71 (‘heavy’). The observed use data show that the portal is primarily used to search for and download material, rather than for sharing material or information. The use data at T2 show that teachers become more efficient in their search behavior and that the majority of the teachers use the portal more frequently. Guidelines are proposed to policymakers and school boards aiming to introduce a similar technology to teachers.     

A simplified multi-class support vector machine with reduced dual optimization

Support vector machine (SVM) was initially designed for binary classification. To extend SVM to the multi-class scenario, a number of classification models were proposed such as the one by Crammer and Singer (2001). However, the number of variables in Crammer and Singer’s dual problem is the product of the number of samples (l) by the number of classes (k), which produces a large computational complexity. This paper presents a simplified multi-class SVM (SimMSVM) that reduces the size of the resulting dual problem from l × k to l by introducing a relaxed classification error bound. The experimental results demonstrate that the proposed SimMSVM approach can greatly speed-up the training process, while maintaining a competitive classification accuracy.     

Q-高斯核支持向量机的财务危机预报

针对科学实践、经济生活等诸多领域数据分布相对复杂的分类问题,使用传统支持向量机(SVM)无法很好地刻画其变量间的相关性,从而影响分类性能。对于这一情况,提出使用经典高斯函数的参数推广形式--Q-高斯函数作为SVM的核函数构建财务危机预警模型。结合沪深股市A股制造业上市公司的财务数据分别建立T-2和T-3财务预警模型进行实证分析,采用显著性检验筛选出合适的财务指标并利用交叉验证方法确定模型参数。相比高斯核SVM财务危机预警模型,使用Q-高斯核SVM建立的T-2和T-3模型的预报准确率都提高了大约3%,而且成本较高的第Ⅰ类错误最多降低了14.29%。     

Effects of stereoscopic movies: The positions of stereoscopic objects and the viewing conditions

The present study investigates the effects of relative positions of stereoscopic objects (PSO) (‘Far’ (from viewers) vs. ‘Near’ (to viewers) vs. ‘Both’) and seat location on viewers’ psychological responses. People who watched a movie with ‘Both’ conditions reported more arousal and satisfaction compared to people who watched a movie with either the ‘Far’ or ‘Near’ condition. More importantly, interaction effects were reported such as more dizziness (a) with the ‘Near’ condition if sitting on the left or right side in the cinema and (b) with the ‘Far’ condition if sitting in the middle of the cinema. Additionally, people who wore glasses felt more eye fatigue than those who did not. Secondly, people felt less presence, sensation of depth, and arousal if they had prior experience viewing stereoscopic movies. The results indicate that viewing experience with different PSOs and/or seat locations can influence psychological response.     

The application of discriminant analysis for mapping cereals and pasture using object-based features

High mapping accuracies occur where crops differ spectrally (e.g.>90.0%; canola, corn, soybeans) and vice versa (e.g. <75.0%; cereals and pasture). Developing improved mapping methods has been an ongoing priority of Agriculture and Agri-Food Canada (AAFC) remote-sensing science. To this end, this study tests a data-driven object-based classification method using Discriminant Analysis (DA) method for mapping cereals and pasture from satellite data. In this approach, variables (number >400) derived from the image segmentation and object-based feature extraction of multi-date and multi-band optical (RapidEye) and microwave (RADARSAT-2) imagery were applied in a data-driven approach. We use in situ and satellite information collected over two study sites with different levels of heterogeneity (Winnipeg, Brandon) situated in the Canadian Prairies during the 2013 growing season to assess: (a) the type of DA model that most accurately classifies the cereals and pasture cover classes; and (b) how the classification accuracies obtained by the application of this DA model compare to those obtained from more traditional Maximum Likelihood (ML), Decision Tree (DT), and Random Forest (RF) classifications. We found that our DA-based approach was able to map cereals and pastures at our two study sites with the highest accuracies, but these accuracies did not improve significantly with the use of more complex DA model (including priori classification probabilities, more input principle components (PCs), the use of weights proportional to field area). Our results are encouraging for the wider application of the data-driven pre-processing of the inputs to the image classification by DA.     

遥感图像林型纹理特征的ICA与SVM分类

遥感图像纹理特征是光谱相近林型准确分类的有效方法,然而其带来分类特征向量维数增加和计算量增大。因此,对南方山区林地TM图像进行独立成分分析ICA降维,通过计算灰度共生矩阵获取纹理特征,使用SVM分类,研究林地类型的快速分类方法。结果表明,ICA与SVM法利用遥感图像纹理特征可较准确地实现林地类型分类,分类总精度、Kappa系数分别为85.4%、0.73,均高于SVM法、BP神经网络法、最大似然法、最小距离法;其对阔叶林、针叶林、竹林的分类精度依次为78.2%、80.1%、84.3%,误识率主要是由于混交林而造成两类林地之间存在交集,易出现的针阔混交林使得阔叶林、针叶林的分类精度低于竹林。     

Mapping invasive plants using hyperspectral imagery and Breiman Cutler classifications (randomForest)

Invasive nonindigenous plants are threatening the biological integrity of North American rangelands, as well as the economies that are supported by those ecosystems. Spatial information is critical to fulfilling invasive plant management strategies. Traditional invasive plant mapping has utilized ground-based hand or GPS mapping. The shortfalls of ground-based methods include the limited spatial extent covered and the associated time and cost. Mapping vegetation with remote sensing covers large spatial areas and maps can be updated at an interval determined by management needs. The objective of the study was to map leafy spurge (Euphorbia esula L.) and spotted knapweed (Centaurea maculosa Lam.) using 128-band hyperspectral (5-m and 3-m resolution) imagery and assess the accuracy of the resulting maps. Beiman Cutler classifications (BCC) were used to classify the imagery using the randomForest package in the R statistical program. BCC builds multiple classification trees by repeatedly taking random subsets of the observational data and using random subsets of the spectral bands to determine each split in the classification trees. The resulting classification trees vote on the correct classification. Overall accuracy was 84% for the spotted knapweed classification, with class accuracies ranging from 60% to 93%; overall accuracy was 86% for the leafy spurge classification, with class accuracies ranging from 66% to 93%. Our results indicate that (1) BCC can achieve substantial improvements in accuracy over single classification trees with these data and (2) it might be unnecessary to have separate accuracy assessment data when using BCC, as the algorithm provides a reliable internal estimate of accuracy.     

High-resolution multispectral techniques for mapping former Little Ice Age terrestrial ice cover in the Canadian High Arctic

Multispectral classification approaches were applied to high-resolution ASTER (15 m) and ETM+ (30 m) imagery for the purpose of developing new techniques for mapping recently deglaciated LIA perennial ice cover in the Canadian Arctic. Four areas in the Queen Elizabeth Islands, with dissimilar surficial geology and diverse topographic complexity, were selected to test the efficacy of both sensors for mapping these subtle landscape features. Automated classification (band calculation) methods were found to be most effective on quartzitic sandstone and siliceous crystalline bedrock, whereas, semi-automated (supervised classification) techniques were most successful on substrates comprised primarily of carbonate lithologies. ASTER's superior spatial resolution yielded higher accuracies in topographically complex areas; however, ETM+ was more effective over a wider variety of substrate lithologies and topographic settings, with a mean overall accuracy of 91% (mean κ statistic = 0.71), compared to 87% (mean κ statistic = 0.60) for ASTER.     

Improved classification of conservation tillage adoption using high temporal and synthetic satellite imagery

Conservation tillage management has been advocated for carbon sequestration and soil quality preservation purposes. Past satellite image analyses have had difficulty in differentiating between no-till (NT) and minimal tillage (MT) conservation classes due to similarities in surface residues, and may have been restricted by the availability of cloud-free satellite imagery. This study hypothesized that the inclusion of high temporal data into the classification process would increase conservation tillage accuracy due to the added likelihood of capturing spectral changes in MT fields following a tillage disturbance. Classification accuracies were evaluated for Random Forest models based on 250-m and 500-m MODIS, 30-m Landsat, and 30-m synthetic reflectance values. Synthetic (30-m) data derived from the Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM) were evaluated because high frequency Landsat image sets are often unavailable within a cropping season due to cloud issues. Classification results from a five-date Landsat model were substantially better than those reported by previous classification tillage studies, with 94% total and ≥ 88% class producer's accuracies. Landsat-derived models based on individual image scenes (May through August) yielded poor MT classifications, but a monthly increase in accuracy illustrated the importance of temporal sampling for capturing regional tillage disturbance signatures. MODIS-based model accuracies (90% total; ≥ 82% class) were lower than in the five-date Landsat model, but were higher than previous image-based and survey-based tillage classification results. Almost all the STARFM prediction-based models had classification accuracies higher than, or comparable to, the MODIS-based results (> 90% total; ≥ 84% class) but the resulting model accuracies were dependent on the MODIS/Landsat base pairs used to generate the STARFM predictions. Also evident within the STARFM prediction-based models was the ability for high frequency data series to compensate for degraded synthetic spectral values when classifying field-based tillage. The decision to use MODIS or STARFM-based data within conservation tillage analysis is likely situation dependent. A MODIS-based approach requires little data processing and could be more efficient for large-area mapping; however a STARFM-based analysis might be more appropriate in mixed-pixel situations that could potentially compromise classification accuracy.     

Fuzzy failure modes and effects analysis by using fuzzy TOPSIS-based fuzzy AHP

Failure mode and effects analysis (FMEA) is a widely used engineering technique for designing, identifying and eliminating known and/or potential failures, problems, errors and so on from system, design, process, and/or service before they reach the customer (Stamatis, 1995). In a typical FMEA, for each failure modes, three risk factors; severity (S), occurrence (O), and detectability (D) are evaluated and a risk priority number (RPN) is obtained by multiplying these factors. There are significant efforts which have been made in FMEA literature to overcome the shortcomings of the crisp RPN calculation. In this study a fuzzy approach, allowing experts to use linguistic variables for determining S, O, and D, is considered for FMEA by applying fuzzy ‘technique for order preference by similarity to ideal solution’ (TOPSIS) integrated with fuzzy ‘analytical hierarchy process’ (AHP). The hypothetical case study demonstrated the applicability of the model in FMEA under fuzzy environment.