Grid pattern recognition in road networks using the C4.5 algorithm

Pattern recognition in road networks can be used for different applications, including spatiotemporal data mining, automated map generalization, data matching of different levels of detail, and other important research topics. Grid patterns are a common pattern type. This paper proposes and implements a method for grid pattern recognition based on the idea of mesh classification through a supervised learning process. To train the classifier, training datasets are selected from worldwide city samples with different cultural, historical, and geographical environments. Meshes are subsequently labeled as composing or noncomposing grids by participants in an experiment, and the mesh measures are defined while accounting for the mesh’s individual characteristics and spatial context. The classifier is generated using the C4.5 algorithm. The accuracy of the classifier is evaluated using Kappa statistics and the overall rate of correctness. The average Kappa value is approximately 0.74, which corresponds to a total accuracy of 87.5%. Additionally, the rationality of the classifier is evaluated in an interpretation step. Two other existing grid pattern recognition methods were also tested on the datasets, and comparison results indicate that our approach is effective in identifying grid patterns in road networks.     

Temporal replication of the national land cover database using active machine learning

Regional and national level land cover datasets, such as the National Land Cover Database (NLCD) in the United States, have become an important resource in physical and social science research. Updates to the NLCD have been conducted every 5 years since 2001; however, the procedure for producing a new release is labor-intensive and time-consuming, taking 3 or 4 years to complete. Furthermore, in most countries very few, if any, such releases exist, and thus there is high demand for efficient production of land cover data at different points in time. In this paper, an active machine learning framework for temporal updating (or backcasting) of land cover data is proposed and tested for three study sites covered by the NLCD. The approach employs a maximum entropy classifier to extract information from one Landsat image using the NLCD, and then replicate the classification on a Landsat image for the same geographic extent from a different point in time to create land cover data of similar quality. Results show that this framework can effectively replicate the land cover database in the temporal domain with similar levels of overall and within class agreement when compared against high resolution reference land cover datasets. These results demonstrate that the land cover information encapsulated in the NLCD can effectively be extracted using solely Landsat imagery for replication purposes. The algorithm is fully automated and scalable for applications at landscape and regional scales for multiple points in time.     

Student Perceptions of a Recreation Trail Assignment as a Valuable Learning Experience for Geography Undergraduates

Charging undergraduate geography students with the task of designing a recreational trail in their local community offers an engaging experiential opportunity with potential to advance geographic learning in a real-world setting. This article presents an assignment in which students were asked to develop a recreational trail proposal for an undeveloped local conservation area and the results of a survey that asked the students to reflect and report upon the educational value of this experience one year later. Results of the survey validated the assignment's lasting value to the students across the cognitive, psychomotor, and affective learning domains.     

Prediction of Seaward Slope Recession in Berm Breakwaters Using M5' Machine Learning Approach

In the design process of berm breakwaters, their front slope recession has an inevitable rule in large number of model tests, and this parameter being studied. This research draws its data from Moghim’s and Shekari’s experiment results. These experiments consist of two different 2D model tests in two wave flumes, in which the berm recession to different sea state and structural parameters have been studied. Irregular waves with a JONSWAP spectrum were used in both test series. A total of 412 test results were used to cover the impact of sea state conditions such as wave height, wave period, storm duration and water depth at the toe of the structure, and structural parameters such as berm elevation from still water level, berm width and stone diameter on berm recession parameters. In this paper, a new set of equations for berm recession is derived using the M5'' model tree as a machine learning approach. A comparison is made between the estimations by the new formula and the formulae recently given by other researchers to show the preference of new M5'' approach.     

大数据环境下内蒙古浩布高地区铅锌多金属矿智能矿产预测研究

传统机器学习算法已广泛应用于矿产预测,但面对地质大数据的高维稀疏、不平衡小样本等特性仍缺乏有效处理和分析的方法,设计适合地质大数据特点的机器学习算法是智能矿产预测亟需解决的新问题。本文以内蒙古浩布高地区的铅锌多金属矿产预测为例,提出了一种面向地质大数据的半监督协同训练矿产预测模型。首先对研究区地质找矿信息和地球化学异常信息进行定量分析,提取断裂构造、二叠系地层、燕山期侵入岩、地层与岩体接触带、围岩蚀变及Pb、Zn、Sn、Cu地球化学异常共9种找矿因子。然后利用递归特征消除法优选找矿因子组合,不包括Sn异常在内的8个找矿因子组合被选为最优组合。最后,利用支持向量机和随机森林算法作为基分类器进行半监督协同训练矿产预测,绘制成矿概率分布图。ROC曲线和预测度曲线分析结果表明,半监督协同训练模型的AUC值和预测效率都高于随机森林和支持向量机模型。研究结果也为大数据环境下的智能矿产预测提供了一种新的思路。     

基于岩石图像深度学习的岩性自动识别与分类方法

岩石岩性的识别与分类对于地质分析极为重要,采用机器学习的方法建立识别模型进行自动分类是一条新的途径。基于Inception-v3深度卷积神经网络模型,建立了岩石图像集分析的深度学习迁移模型,运用迁移学习方法实现了岩石岩性的自动识别与分类。采用此方法对所采集的173张花岗岩图像、152张千枚岩图像和246张角砾岩图像进行了学习和识别分类研究,通过训练学习建立岩石图像深度学习迁移模型,并分别采用训练集和测试集中的岩石图像对模型进行了检验分析。对于训练集中的岩石图像,每组岩石分别用3张图像测试,三种岩石的岩性分类均正确,且分类概率值均达到90%以上,显示了模型良好的鲁棒性;对于测试集中的岩石图像,每组岩石分别采用9张图像进行识别分析,三种岩石的岩性分类均正确,并且千枚岩组图像分类概率均高于90%,但是花岗岩组2张图像和角砾岩组的1张图像分类概率值不足70%,概率值较其他岩石图像低,推测其原因是训练集中相同模式的岩石图像较少,导致模型的泛化能力减小。为了提高识别精确度,对准确率较低的岩石图像进行截取,分别取其中的3张图像加入训练集进行再训练,增加与测试图像具有相同模式的训练样本;在新的模型中,对3张图像进行二次检验,测试概率值均达到85%以上,说明在数据足够的状况下模型具有良好的学习能力。与传统的机器学习方法相比,所提出的岩石图像深度学习方法具有以下优点:第一,模型通过搜索图像像素点提取物体特征,不需要手动提取待分类物体特征;第二,对于图像像素大小,成像距离及光照要求低;第三,采用适当的训练集可获得较好的识别分类效果,并具有良好鲁棒性和泛化能力。     

卷积神经网络及其在矿床找矿预测中的应用——以安徽省兆吉口铅锌矿床为例

大数据人工智能地质学刚刚起步,基于大数据智能算法的地质研究是非常有意义的探索性实验。利用大数据和机器学习解决矿产预测问题,有助于人们克服不能全面考虑地质变量的困难及评估当前模型在已有数据中的可靠性。元素地表分布特征量主要受原岩成分、成矿作用影响和地表过程的影响,它们携带某些指示矿体就位的信息,即矿体在地下空间就位时在地表的响应,且未在地表过程中消失。以往的地球化学勘查工作仅仅识别异常,但未能发现矿体在地表响应的成矿特征量。本文以安徽省兆吉口铅锌矿床为例,通过机器学习,利用卷积神经网络算法,不断挖掘元素Pb分布特征与矿体地下就位空间的耦合相关性。经过1000次训练后,可以得到准确率0. 93,损失率0. 28的卷积神经网络模型。这种神经网络模型就是矿体在地下就位时元素在地表分布的响应,可以用来进行矿产资源预测。应用该模型对未知区进行预测,结果显示第53号区域具有很大概率存在尚未发现的矿体。     

Mapping fractional landscape soils and vegetation components from Hyperion satellite imagery using an unsupervised machine-learning workflow

An unsupervised machine-learning workflow is proposed for estimating fractional landscape soils and vegetation components from remotely sensed hyperspectral imagery. The workflow is applied to EO-1 Hyperion satellite imagery collected near Ibirací, Minas Gerais, Brazil. The proposed workflow includes subset feature selection, learning, and estimation algorithms. Network training with landscape feature class realizations provide a hypersurface from which to estimate mixtures of soil (e.g. 0.5 exceedance for pixels: 75% clay-rich Nitisols, 15% iron-rich Latosols, and 1% quartz-rich Arenosols) and vegetation (e.g. 0.5 exceedance for pixels: 4% Aspen-like trees, 7% Blackberry-like trees, 0% live grass, and 2% dead grass). The process correctly maps forests and iron-rich Latosols as being coincident with existing drainages, and correctly classifies the clay-rich Nitisols and grasses on the intervening hills. These classifications are independently corroborated visually (Google Earth) and quantitatively (random soil samples and crossplots of field spectra). Some mapping challenges are the underestimation of forest fractions and overestimation of soil fractions where steep valley shadows exist, and the under representation of classified grass in some dry areas of the Hyperion image. These preliminary results provide impetus for future hyperspectral studies involving airborne and satellite sensors with higher signal-to-noise and smaller footprints.     

Evaluation of effectiveness of three fuzzy systems and three texture extraction methods for building damage detection from post-event LiDAR data

Building damage maps after disasters can help us to better manage the rescue operations. Researchers have used Light Detection and Ranging (LiDAR) data for extracting the building damage maps. For producing building damage maps from LiDAR data in a rapid manner, it is necessary to understand the effectiveness of features and classifiers. However, there is no comprehensive study on the performance of features and classifiers in identifying damaged areas. In this study, the effectiveness of three texture extraction methods and three fuzzy systems for producing the building damage maps was investigated. In the proposed method, at first, a pre-processing stage was utilized to apply essential processes on post-event LiDAR data. Second, textural features were extracted from the pre-processed LiDAR data. Third, fuzzy inference systems were generated to make a relation between the extracted textural features of buildings and their damage extents. The proposed method was tested across three areas over the 2010 Haiti earthquake. Three building damage maps with overall accuracies of 75.0%, 78.1% and 61.4% were achieved. Based on outcomes, the fuzzy inference systems were stronger than random forest, bagging, boosting and support vector machine classifiers for detecting damaged buildings.     

Supervised classification of electric power transmission line nominal voltage from high-resolution aerial imagery

For many researchers, government agencies, and emergency responders, access to the geospatial data of US electric power infrastructure is invaluable for analysis, planning, and disaster recovery. Historically, however, access to high quality geospatial energy data has been limited to few agencies because of commercial licenses restrictions, and those resources which are widely accessible have been of poor quality, particularly with respect to reliability. Recent efforts to develop a highly reliable and publicly accessible alternative to the existing datasets were met with numerous challenges – not the least of which was filling the gaps in power transmission line voltage ratings. To address the line voltage rating problem, we developed and tested a basic methodology that fuses knowledge and techniques from power systems, geography, and machine learning domains. Specifically, we identified predictors of nominal voltage that could be extracted from aerial imagery and developed a tree-based classifier to classify nominal line voltage ratings. Overall, we found that line support height, support span, and conductor spacing are the best predictors of voltage ratings, and that the classifier built with these predictors had a reliable predictive accuracy (that is, within one voltage class for four out of the five classes sampled). We applied our approach to a study area in Minnesota.