判别流形学习算法的高光谱数据降维与树种识别

高光谱遥感影像的波段光谱特征是各类地物内在物理化学性质的反映,在对不同地物进行分类与识别时具有巨大潜能,但由于其波段多造成的信息冗余,需要对高光谱数据进行有效降维,以提高高光谱影像的分类准确度。本文提出了基于判别局部片排列的流形学习算法（DLA）对Hypersion高光谱数据进行降维,通过对局部样本数据进行流形学习框架内的优化训练,将原始光谱特征空间转换为低维的最优判别流形子空间,然后在该子空间内利用最大似然分类器对Hypersion影像中的每个像素进行分类,并与主成分分析（PCA）、原始光谱特征（spectral）降维方法的分类效果进行比较。结果表明,DLA能够有效提高高光谱数据的分类准确度,对不同树种分类取得了满意效果。     

Unsupervised ore/waste classification on open-cut mine faces using close-range hyperspectral data

The remote mapping of minerals and discrimination of ore and waste on surfaces are important tasks for geological applications such as those in mining. Such tasks have become possible using ground-based, close-range hyperspectral sensors which can remotely measure the reflectance properties of the environment with high spatial and spectral resolution. However, autonomous mapping of mineral spectra measured on an open-cut mine face remains a challenging problem due to the subtleness of differences in spectral absorption features between mineral and rock classes as well as variability in the illumination of the scene. An additional layer of difficulty arises when there is no annotated data available to train a supervised learning algorithm. A pipeline for unsupervised mapping of spectra on a mine face is proposed which draws from several recent advances in the hyperspectral machine learning literature. The proposed pipeline brings together unsupervised and self-supervised algorithms in a unified system to map minerals on a mine face without the need for human-annotated training data. The pipeline is evaluated with a hyperspectral image dataset of an open-cut mine face comprising mineral ore martite and non-mineralised shale. The combined system is shown to produce a superior map to its constituent algorithms, and the consistency of its mapping capability is demonstrated using data acquired at two different times of day.     

Real-time probabilistic sediment concentration forecasting using integrated dynamic network and error distribution heterogeneity

Sediment forecasting at a dam site is important for the operation and management of water and sediment in a reservoir. However, the forecast results generally have some uncertainties, which may hinder the operation of the dam. In this study, a real-time sediment concentration probabilistic forecasting model is proposed based on a dynamic network model. Under this framework, the Elman neural network (ENN) and nonlinear auto-regressive with exogenous inputs (NARX) neural network models were established for sediment concentration forecasting with different lead times. A hybrid algorithm, which combined the Levenberg–Marquardt algorithm and real-time recurrent learning, was used to train the model. Using the aforementioned method, the sediment concentration was forecast for at the Sanmenxia Dam, China, and, subsequently, the forecast results were evaluated. Among the selected lead time, the results at 5 h exhibited the highest accuracy and practical significance. Compared with the ENN model, the sediment concentration peak error using the NARX neural network was reduced by 4.5%, and the sediment yield error was reduced by 0.043%. Therefore, the NARX neural network was selected as the deterministic sediment forecasting model. Additionally, the probability density function of the sediment concentration was derived based on the heterogeneity of the error distribution, and the sediment concentration interval, with different confidence levels, expected values, and median values, was forecast. The Nash–Sutcliffe coefficient of efficiency for the sediment concentration, as forecasted based on the median value, was the highest (0.04 higher than that using a deterministic model), whereas the error of the sediment concentration peak and sediment yield remained unaltered. These results indicated the accuracy and superiority of the proposed real-time sediment probabilistic forecasting hybrid model.     

Zircon classification from cathodoluminescence images using deep learning

Zircon is a widely-used heavy mineral in geochronological and geochemical research because it can extract important information to understand the history and genesis of rocks. Zircon has various types, and an accurate examination of zircon type is a prerequisite procedure before further analysis. Cathodoluminescence (CL) imaging is one of the most reliable ways to classify zircons. However, current CL image examination is conducted by manual work, which is time-consuming, bias-prone, and requires expertise. An automated and bias-free method for zircon classification is absent but necessary. To this end, deep convolutional neural networks (DCNNs) and transfer learning are applied in this study to classify the common types of zircons, i.e., igneous, metamorphic, and hydrothermal zircons. An atlas with over 4000 CL images of these three types of zircons is created, and three DCNNs are trained using these images. The results of this study indicate that the DCNNs can distinguish hydrothermal zircons from other zircons, as indicated by the highest accuracy of 100%. Although similar textures in igneous and metamorphic zircons pose great challenges for zircon classification, the DCNNs successfully classify 95% igneous and 92% metamorphic zircons. This study demonstrates the high accuracy of DCNNs in zircon classification and presents the great potentiality of deep learning techniques in numerous geoscientific disciplines.     

大数据与数学地球科学研究进展——大数据与数学地球科学专题代序

大数据与数学地球科学的核心应用技术包括高维数据降维、图像数据处理、无限数据流挖掘、机器学习、关联规则算法与推荐系统算法等。人工智能地质学,包括大数据-智能矿床成因模型与找矿模型的构建,是具有重要价值的研究方向。高维数据降维旨在从初始高维特征集合中选出低维特征集合,有效地消除无关和冗余特征,增强学习结果的易理解性。哈希算法、聚类分析、主成分分析等是较常用的数学降维工具。机器学习是人工智能的核心,是使计算机具有智能的根本途径。机器学习与人工智能各种基础问题的统一性观点正在形成。深度学习的训练模型往往需要海量数据作为支撑,因此迁移学习方法日益受到重视。图像模式识别是大数据挖掘的重要技术。网络中的社区结构识别对理解整个网络的结构和功能有重要价值,可帮助分析、预测网络各元素间的交互关系。沉浸式虚拟现实技术是实现大数据可视化的重要方向,对具有多元、异构、时空性、非线性、多尺度地质矿产勘查数据的展示要求有特别的价值。引入VR技术进行矿产地质大数据的可视化,可实现大数据时代矿产勘查数据的新认知。无限数据流在地质、地球化学、地球物理监测中大量存在,甚至可以持续自动产生。对数据流数据的计算包括对点查询、范围查询、内积查询、分位数计算、频繁项计算等。关联规则和推荐系统算法是大数据挖掘中的重要算法,其应用范围越来越广泛。贝叶斯原理在大数据时代有独特的价值,贝叶斯网络是成因建模的一个革命性工具。智能地质学研究刚刚起步,构建大数据-智能矿床成因模型与找矿模型是智能地质学研究的重要内容。矿床模型研究方式的变革,将出现于互联网、云计算技术环境下全球各地的矿床研究团队的共同参与。     

高等学校老校区土地资源集约利用评价研究

开展高等学校保留老校区土地资源集约利用评价研究是提高土地利用效率、促进高等教育资源有效利用和优化整合的基础。提出老校区土地资源集约利用评价的思路,即老校区土地资源集约利用评价应在对校区土地开发强度现状评价的基础上,着重进行学校主体搬迁后学校实体建筑和无形资产利用等变化的评价,采用基于层次分析法、特尔菲法和实地调研法的评价方法,构建了包括学校土地开发强度、实体建筑利用程度和综合影响力3个指标层16个评价指标的评价指标体系。为控制搬迁后老校区土地资源利用率下降,建议明确完善老校区功能定位,进行资源优化重组,提高校区综合影响力。     

利用行人轨迹挖掘城市区域功能属性

城市土地利用功能区是城市规划中的一个重要概念,遥感技术手段在城市土地利用类型识别和动态监测中取得了很大进展。然而,由于城市实际功能的复杂,往往很难从遥感影像中获得城市各个区域的社会、经济或文化等功能属性。互联网技术的发展和移动定位设备的普及,极大地便利了行人移动轨迹数据的获取。本文从行人移动规律和模式与城市功能分区之间高度相关的角度出发,通过机器学习的方法,从大量行人轨迹数据中挖掘隐含的城市功能属性与强度。该方法首先利用矢量栅格化和数学形态学方法,将城市不同等级的路网分割为互不相同的空间单元;其次,根据行人轨迹数据的时空分布特点,定义9个变量并构建高斯混合模型(Gaussian mixture model,GMM),对上述空间单元进行非监督分类,得到7种城市用地类型;随后,结合选定的60个样本区以及人为标识的6种功能区(教育用地、绿地休闲区、一般商业区、政府设施、中心商业区、住宅区),依据样本功能区GPS轨迹时间分布特征,最终对7种城市用地类型进行功能配对;最后,利用核密度估计方法进行功能区强度的可视化。该框架结合机器学习的优势,结果具有较高的准确度。     

An experimental approach for selection/elimination in stream network generalization using support vector machines

Multi-representation databases (MRDB) are used in several Geographical Information System applications for different purposes. MRDB are mainly obtained through model and cartographic generalizations. The model generalization is essentially achieved with the selection/elimination process in which a decision must be made to include or exclude the object at the target level. In this study, support vector machines (SVM) was, for the first time, used for the selection/elimination process in stream network generalization. Within this context, the attributes to be used as input data in the SVM method were determined and weighted according to the associations determined in a chi-squared independence test. 1:100,000-scale (medium resolution) stream networks were derived from two 1:24,000-scale (high resolution) stream networks with different patterns in the United States Geological Survey National Hydrography Data-sets. The derived stream networks were quite similar to the 1:100,000-scale original stream networks in both qualitative and visual aspects.     

移动学习模式下测绘专业知识测试系统设计与实现

随着WIFI和智能移动终端的普及,移动学习正在快速地发展。本文主要介绍了智能移动终端上的测绘专业知识测试系统的总体设计和部分实体E-R图,从系统登录与注册模块、个人中心模块、教师编辑试题模块、编辑测试模块、学生自测模块、学生考试模块等方面阐述了测绘专业知识系统的设计与实现,弥补了测绘专业在移动学习应用上的短缺状况。     

Bidding and performance in multiple unit combinatorial fishery quota auctions: Role of information feedbacks

This article explores the role of market information and learning in multiple unit combinatorial markets for fishing quota. Combinatorial auctions allow trading of packages of different types of quotas (for example for different regions or industry) in the same auction market. Bidders can submit package bids which would allow them to enjoy synergy benefits. However, to realize the full benefit bidders require comprehensive understanding of the market. This article focuses on the impact of varying levels of information feedback on performance in multiple unit forward combinatorial auctions using laboratory experiments. In a general context of trade in fishery quota, it was asked whether (a) providing additional market information and (b) learning through time helps in more efficient outcomes. It is found that much of the benefits of information are derived from structural effects, like repeated rounds and package valuations. Providing additional market information does not improve auction performances to a large extent. These results will be useful in designing more efficient combinatorial markets for fisheries quota.