A machine learning approach to tungsten prospectivity modelling using knowledge-driven feature extraction and model confidenc

Novel mineral prospectivity modelling presented here applies knowledge-driven feature extraction to a datadriven machine learning approach for tungsten mineralisation.The method emphasises the importance of appropriate model evaluation and develops a new Confidence Metric to generate spatially refined and robust exploration targets.The data-driven Random ForestTM algorithm is employed to model tungsten mineralisation in SW England using a range of geological,geochemical and geophysical evidence layers which include a depth to granite evidence layer.Two models are presented,one using standardised input variables and a second that implements fuzzy set theory as part of an augmented feature extraction step.The use of fuzzy data transformations mean feature extraction can incorporate some user-knowledge about the mineralisation into the model.The typically subjective approach is guided using the Receiver Operating Characteristics(ROC)curve tool where transformed data are compared to known training samples.The modelling is conducted using 34 known true positive samples with 10 sets of randomly generated true negative samples to test the random effect on the model.The two models have similar accuracy but show different spatial distributions when identifying highly prospective targets.Areal analysis shows that the fuzzy-transformed model is a better discriminator and highlights three areas of high prospectivity that were not previously known.The Confidence Metric,derived from model variance,is employed to further evaluate the models.The new metric is useful for refining exploration targets and highlighting the most robust areas for follow-up investigation.The fuzzy-transformed model is shown to contain larger areas of high model confidence compared to the model using standardised variables.Finally,legacy mining data,from drilling reports and mine descriptions,is used to further validate the fuzzy-transformed model and gauge the depth of potential deposits.Descriptions of mineralisation corroborate that the targets generated in these models could be undercover at depths of less than 300 m.In summary,the modelling workflow presented herein provides a novel integration of knowledge-driven feature extraction with data-driven machine learning modelling,while the newly derived Confidence Metric generates reliable mineral exploration targets.

Prospectivity modeling of porphyry copper deposits: recognition of efficient mono-and multi-element geochemical signatures in the Varzaghan district, NW Iran

The Varzaghan district at the northwestern margin of the Urumieh–Dokhtar magmatic arc, is considered a promising area for the exploration of porphyry Cu deposits in Iran. In this study we identified mono-and multi-element geochemical anomalies associated with Cu–Au–Mo–Bi mineralization in the central parts of the Varzaghan district by applying the concentration–area fractal method. After mono-element geochemical investigations, principal component analysis was applied to ten selected elements in order to acquire a multi-element geochemical signature based on the mineralization-related component. Quantitative comparisons of the obtained fractal-based populations were carried out in accordance with known Cu occurrences using Student's t-values. Then,significant mono-and multi-element geochemical layers were separately combined with related geologic and structural layers to generate prospectivity models, using the fuzzy GAMMA approach. For quantitative evaluation of the effectiveness of different geochemical signatures in final prospectivity models, a prediction-area plot was adapted. The results show that the multi-element geochemical signature of principal component one(PC1) is more effective than mono-element layers in delimiting exploration targets related to porphyry Cu deposits.

Incorporating conceptual and interpretation uncertainty to mineral prospectivity modelling

Prospectivity analyses are used to reduce the exploration search space for locating areas prospective for mineral deposits.The scale of a study and the type of mineral system associated with the deposit control the evidence layers used as proxies that represent critical ore genesis processes.In particular,knowledge-driven approaches(fuzzy logic)use a conceptual mineral systems model from which data proxies represent the critical components.These typically vary based on the scale of study and the type of mineral system being predicted.Prospectivity analyses utilising interpreted data to represent proxies for a mineral system model inherit the subjectivity of the interpretations and the uncertainties of the evidence layers used in the model.In the case study presented,the prospectivity for remobilised nickel sulphide(NiS)in the west Kimberley,Western Australia,is assessed with two novel techniques that objectively grade interpretations and accommodate alternative mineralisation scenarios.Exploration targets are then identified and supplied with a robustness assessment that reflects the variability of prospectivity value for each location when all models are considered.The first technique grades the strength of structural interpretations on an individual line-segment basis.Gradings are obtained from an objective measure of feature evidence,which is the quantification of specific patterns in geophysical data that are considered to reveal underlying structure.Individual structures are weighted in the prospectivity model with grading values correlated to their feature evidence.This technique allows interpreted features to contribute prospectivity proportional to their strength in feature evidence and indicates the level of associated stochastic uncertainty.The second technique aims to embrace the systemic uncertainty of modelling complex mineral systems.In this approach,multiple prospectivity maps are each generated with different combinations of confidence values applied to evidence layers to represent the diversity of processes potentially leading to ore deposition.With a suite of prospectivity maps,the most robust exploration targets are the locations with the highest prospectivity values showing the smallest range amongst the model suite.This new technique offers an approach that reveals to the modeller a range of alternative mineralisation scenarios while employing a sensible mineral systems model,robust modelling of prospectivity and significantly reducing the exploration search space for Ni.

Geological Characteristics and Regional Prospecting Model of Wulanchongji Gold Orebody, Alxa Youqi, Inner Mongolia, China

Five gold deposits (mineralization) were found in the study area by means of geological mapping, soil geochemical survey and trough exploration engineering. The ore-bearing lithology is mainly metamorphic feldspar sandstone of the Upper Carboniferous Benbatu Formation, and the gold (mineralization) body is controlled by both structural factors and stratigraphic factors of the Upper Carboniferous Benbatu Formation. The genetic type is preliminary concluded to be volcanic hydrothermal type, and the metallogenic age is late Variscan. In this paper, by studying the geological characteristics and metallogenic geological conditions of the gold orebody in the area, a regional prospecting model has been established, which is of great significance to better guide the prospecting work of similar gold deposits in the area and the region.

石英脉型钨多金属矿床的扇状成矿实例及找矿模型

石英脉型钨矿床是中国数量最多的钨矿床类型,但保有储量消耗迅速,迫切需要创新找矿模型,指导找矿突破。文章结合二十余年的找矿实践,通过详细分析扇状成矿矿床实例,构建了石英脉型钨矿床新的找矿模型。该模型强调赋矿裂隙为岩浆动力成因,在花岗岩体顶部呈扇状分布型式,岩浆期后热液恰在裂隙张开时充填其中而形成扇状成矿系统;提出“就岩找矿”、“就矿找矿”、“就矿找岩”的地质、地球化学和地球物理标志,指导矿床尺度的勘查工程部署。截至目前,该模型已在广东禾尚田钨锡矿床、广西珊瑚钨锡矿床、广西社垌钨钼矿床、江西盘古山钨铋矿床等获得了验证,找矿成效显著。

3D Geology Modeling from 2D Prospecting Line Profile Map

Using prospecting line profile map in combination with drilling and other information for 3D reconstruction of geological model is an important method of 3D geological modeling.?This paper?discusses the theory and implementation method of 2D prospecting line map into 3D prospecting line map and then into 3D model. The authors propose that it needs twice upgrading dimension to reconstruction 3D geology model from prospecting line profile map. The first upgrading dimension is to convert profile from 2D into 3D profile,?i.e.?the 2D points in the 2D profile map upgrading dimensional transformation to 3D points in a 3D profile. The second upgrading dimension is that transform 0D point 1D curve and 2D polygon feature into 1D curve, 2D surface and 3D solid feature. The paper reexamines contents and forms in prospecting line map from the two different viewpoints of geology and geographic information science. The process of 3D geology modeling from 2D prospecting map is summarized as follows. Firstly, profile is divided into several sections by beginning, end and drill point of the prospecting line. Next, a 3D folded upright profile frame is built by 2D folded prospecting line on the plan map. Then, 2D points of features on 2D profile are converted into 3D points on 3D profile section by section. And then, adding switch control points for the long line crossover two segments. Lastly, 1D curve features are upgraded to 2D surface.

基于动态哈夫模型及双边匹配的电动汽车充电引导策略

由于充电站中充电桩数目有限且电动汽车充电耗时长,陆续产生充电需求的各电动汽车用户存在对充电站资源的竞争。这不仅增加了用户排队概率,降低了充电站收益和利用率,而且使得用户在充电站规模、价格、评价等方面的个性化需求得不到充分满足。为此,提出了一种动态哈夫模型与双边匹配方法相结合的电动汽车充电引导策略。首先,对充电站客流、充电订单和充电桩详情等真实数据集进行大数据挖掘,分析公共充电站用户的充电站选择偏好和充电行为特征;然后,基于动态哈夫模型,结合用户充电站选择偏好量化不同区域用户前往不同充电站的概率,并生成充电站推荐列表;最后,将前景理论与双边匹配策略相结合,进行充电引导。算例分析表明,所提策略大幅降低了用户的排队概率,在满足用户个性化充电需求的同时,保障了充电站利益。

数学师范生数学核心素养模型建构与发展路径研究

关注数学师范生的数学核心素养,就是关注“数学教师教育要培养什么样的人”的根本教育问题。为解决这一问题,本研究以扎根理论为方法论指导,对14位大学数学教师进行深度访谈,利用MAXQDA20软件对访谈资料进行整理、编码和统计分析,构建起数学师范生数学核心素养模型。该模型包括数学核心知识、数学关键能力和数学价值观念3个核心要素,以及数学学科知识、数学教学知识、数学学科能力、数学教学能力、数学信念、数学价值观6个子要素。高师院校应将发展数学核心素养作为数学人才培养的根本目标,发展路径包括:基于数学教学知识理论开发素养为本的整合课程、基于协同创新理论建立导向素养发展的教学方式、基于设计思维理论形成促进素养转化的学习过程。

农药喷雾系统建模与仿真技术研究综述

农药使用效果与农药喷雾过程密切相关,农药喷雾过程的建模与仿真可弥补因植物生长周期差异、病虫害发生程度不同以及田间作业自然环境不可控等造成的试验研究困难。分析农药施用的抗性、再增猖獗、残留(resistance,resurgence,residue,3R)/效果、效率、生态(efficacy,efficiency,eco-environment,3E)/方法、模型、测试(method,model,measurement,3M),重点综述农药喷雾过程的雾化、输运、沉积等关键环节的模拟仿真研究状况。根据模拟仿真技术发展趋势,提出农药喷雾半实物仿真系统设计的建议,并提出雾化模型及新型喷头雾化机理、群体农药雾滴多相流场模拟、靶标定制与识别模型、综合农药雾滴飘移模型、植物生长模型与农药喷雾系统耦合等建议,以促进原创农药精确喷雾技术研究和高质量植保机械研发。

中国奶酪市场引力效应与伙伴国贸易前景——以中欧为例

在世界未有之大变局下,奶酪贸易不确定性加剧,严重威胁中国奶酪供需平衡。本文在构建随机前沿引力模型与显性竞争优势指数的基础上,预测中欧奶酪贸易前景。研究结果表明,中欧奶酪贸易效率分布不均,不同国家贸易前景存在较大差异。随机前沿引力模型结果显示:双方人口规模、人均GDP促进中欧奶酪贸易,但双方之间的距离阻碍中欧奶酪贸易;贸易伙伴国政府支出、商业自由度、投资自由度等促进贸易效率,但贸易伙伴国政府诚信、税收负担、贸易自由度和生产者价格对贸易效率有阻碍作用。为了提高中欧奶酪贸易效率,中国应对不同“贸易前景”性质的国家采取异质性进口策略,构筑通达、互联互通的贸易环境、打造自由的营商制度环境,促进中欧奶酪贸易效率,保障中国奶酪贸易安全。

青海省食用菌产业经营模式及展望

当前,青海省食用菌产业发展逐步趋于产业化、规模化,农业产业化经营效益显著,对现有的产业经营模式提出了新的挑战和更高层次的要求。基于此,本文主要综述了青海省食用菌产业现状、产业经营模式发展概况,对食用菌产业发展中存在的主要问题和解决措施进行了剖析,并对未来进行了展望,以期为青海省食用菌产业发展提供参考。

基于前景理论框架和Heston模型的行为期权定价

行为期权定价是当前国际金融领域的热门研究主题之一。虽然随机波动率模型已成为国际衍生品定价领域的标准模型,但该模型对短到期期权(尤其是虚值期权)的定价仍不准确,其原因之一是传统的期权定价方法忽略了现实市场中的非理性心理和行为因素。针对上述问题,本文运用前景理论期权定价框架,引入价值函数来刻画投资者面对收益与损失的前景价值判断,引入决策权重函数来修正Heston随机波动率模型刻画的资产价格路径的概率密度函数,将期权合约签订与交割的现金流视为分散的心理账户情形,在市场均衡条件下推导出Heston模型下欧氏行为期权的定价公式。上证50ETF期权的实证结果表明:考虑了前景理论的Heston随机波动率模型,能显著地提升短到期虚值期权的定价准确度;参数校正结果发现,定价性能的提升要归因于Heston模型中纳入的表征非理性心理与情绪的行为参数;相对而言,投资者对实值期权的风险态度偏中性,因此行为参数对其定价精度的提升有限。

山东蒙阴地区金刚石遥感找矿模型的构建与应用

随着遥感传感器多样化及遥感数据处理技术的深入,遥感技术的原位、快速、有效等特点使其成为矿产勘查的重要技术手段。以山东蒙阴地区西峪金伯利岩带金刚石矿床为研究对象,对红旗矿区的金伯利岩体(岩脉)及围岩样品进行短波红外光谱测试,分析其光谱特征及蚀变矿物组成。红旗矿区样品在1391、1912、2318、2393 nm等波长处有吸收谷,这为ASTER遥感数据提取蚀变异常信息提供波谱依据,据此可分类型提取镁羟基异常、铝羟基异常、铁染异常信息。利用PALSAR雷达遥感数据、WorldView-2高分辨率遥感数据对研究区进行构造、岩性、水系解译,得出金伯利岩分布在NE向与NW向构造交汇部位,通过水系解译排除因冲刷沉积引起的假蚀变遥感异常,通过岩性增强界定岩性差异的边界,进而构建金伯利岩带金刚石矿床的遥感找矿模型,将找矿模型应用于矿区外围的找矿预测,叠加地质、化探、重砂等多元信息,在筛选后的遥感异常图上圈定了6个找矿靶区,为金刚石找矿和矿产资源评价提供依据。

融合成矿过程数值模拟信息的三维成矿预测方法研究:以安徽宣城茶亭地区为例

茶亭地区位于长江中下游成矿带南陵-宣城矿集区东北部,近年来陆续发现了多个斑岩型和矽卡岩型矿床,显示深部具有很好的热液矿床成矿潜力。目前传统的矿产勘查方法对区内隐伏矿的勘查效果不佳,制约了进一步的找矿突破。三维成矿预测是近年来隐伏矿找矿的重要手段之一,但三维预测信息的缺乏在一定程度上制约了该方法的预测效果。三维成矿过程数值模拟方法能为三维成矿预测方法提供新的预测信息,但对多元数值模拟信息的联合应用以及对三维成矿预测方法的支持能力等均有待深入研究。本文以安徽宣城茶亭地区为例,在力-热-流多场耦合的条件下对热液成矿过程进行三维数值模拟;通过将体应变增量、剪切应变增量等数值模拟变量信息与其他预测信息进行融合,实现深部找矿靶区的圈定。结果显示,成矿过程数值模拟方法可为三维成矿预测提供有效的预测信息,能显著提高预测能力;圈定的找矿靶区可为进一步的深部找矿勘查提供更为有效和可靠的线索和方向。

基于PROSPECT模型的植物叶片干物质估测建模研究

为了快速、准确估测植物叶片干物质含量,为作物长势及健康状况监控提供数据支撑,利用光谱分析技术探讨了干物质含量敏感光谱波段提取方法及其估测建模方法。试验数据由叶片辐射传输模型PROSPECT在干物质含量(0.001~0.02)g·cm^(-2)范围内进行模拟,随机产生1000条400~2500nm的光谱曲线,其中600条光谱曲线用于建模研究、400条光谱曲线作为模型验证数据,同时应用叶片光学特性数据库LOPEX93中325条叶片光谱-干物质含量数据进行进一步验证。首先应用试验数据进行局部敏感性分析,初步得到叶片干物质敏感波段范围,再运用改进Sobol算法进行全局敏感性分析,提取了干物质含量敏感的光谱波段范围,在此敏感波段范围运用波段组合算法计算归一化植被指数NDVI与叶片干物质含量相关系数,优选了4组相关性大的波段组合建立归一化干物质指数NDMI_((1644,1719))、NDMI_((1871,2294))、NDMI_((2150,2271))、NDMI_((1496,2282))用于干物质含量估测建模。结果表明:NDMI_((1644,1719))和NDMI_((1871,2294))模型中三次多项式形式(cubic)效果最佳、NDMI_((1496,2282))模型中幂指数形式(power)效果最佳,三者中NDMI_((1871,2294))的三次多项式模型最优,决定系数R^2为0.837,对叶片干物质含量具有较好的估测能力。

广西北山铅锌矿床矿体形貌及其成矿指示

广西北山铅锌矿床是桂北地区储量最大的铅锌矿床,开采历史悠久,为矿体形貌研究提供了良好条件。基于野外地质调查和前人研究成果,认为矿床的形成先后经历了层间滑动、倾伏褶皱和断裂3个构造变形阶段。矿体形貌研究发现,矿床从南到北具有不同的侧伏向和侧伏角,南部矿体向SW侧伏、侧伏角20°;中部矿体延伸近SN向,侧伏不明显;北部矿体向NE侧伏,侧伏角为10°。矿体形貌成因类型包括岩溶型矿体(Ⅰ号矿体群)、构造-岩溶型矿体(Ⅱ号矿体群)、构造型矿体(Ⅲ号矿体群)和流体型矿体(少量小矿体)。通过矿体形貌类型、成矿构造、矿体力性、力向、力度、韵度、时空等构造成矿参数研究,综合评价认为矿区具有较好的成矿条件,矿体形貌等级达到“良好”,推测矿床形成于印支期或之前。根据矿体形貌评价结果建立找矿模式,建议矿区下一步找矿方向应在已知Ⅲ号矿体群南部深处侧伏方向以及沿NNE向F3断层上盘或下盘寻找构造型矿体。

新时代我国农村养老工作的展望

农村养老在我国具有特别重要的实际意义,必须从政治高度认知农村养老的重要性,要依据国情、因地制宜讲好农村养老的中国故事;坚持以人民为中心的发展思想,积极推进供给侧改革,以农村养老服务中心建设为抓手,促使各项养老服务更接地气;全力激活农村家庭养老功能,在继续弘扬家庭养老传统的同时,支持家庭承担更多养老功能;不断丰富创新农村互助养老模式,在政策指引下县乡村各有侧重,同时健全三级养老服务网络;盘活房、地等资源,奠定农村养老的物质基础,积极进行“以地养老”探索;加强农村养老服务保障机制,通过五社联动、政府采购服务和建设农村老年协会等路径推进农村养老。

基于PROSPECT+SAIL模型的遥感叶面积指数反演

以PROSPECT+SAIL模型为基础,从物理机理角度反演植被叶面积指数(LAI)。首先,通过FLAASH模型进行大气校正,使得图像像元值表达植被冠层反射率;然后,根据LOPEX 93数据库和JHU光谱数据库选择植物生化参数和光谱数据,以PROSPECT模型模拟出的植物叶片反射率和透射率作为SAIL模型的输入参数,得到植被冠层反射率,将结果与遥感影像的植被冠层反射率对应,回归出植被LAI;最后,以地面实测数据对遥感反演数据进行验证,并分析了误差的可能来源。

基于PROSPECT和4-scale模型的光化学植被指数尺度转换

【目的】光化学植被指数(PRI)对于准确估计植被光能利用率(LUE)有着重要的作用。但在不同的尺度(叶片、冠层、景观尺度)上,PRI与LUE二者之间的关系及其影响因素不同。传感器获得的光谱为像元及冠层光谱,叶片尺度的PRILUE关系模型无法直接用于冠层尺度的数据,因此需要对冠层尺度的PRI指数进行尺度转换。【方法】首先通过叶片尺度的PROSPECT模型,模拟不同生化参数下叶片的反射率与透射率,进而计算叶片尺度PRI指数与简单比值PRI指数(记为SR-PRI)。其次,将获得的叶片尺度反射率、透射率作为参数输入到4-scale模型中,获取不同叶面积指数(LAI)下冠层尺度的反射率,计算得出冠层尺度的PRI、SR-PRI。建立不同LAI下PRI、SR-PRI的冠层−叶片尺度转换函数,并对不同尺度上影响PRI、SR-PRI的因子进行敏感性分析。【结果】PRI、SR-PRI在进行冠层与叶片尺度转化过程中,都表现出很明显的线性关系,并且拟合效果(R2)呈现出随LAI的增大而增大的趋势。对比相同LAI水平下的PRI、SR-PRI的拟合结果发现,SR-PRI的拟合效果普遍要优于PRI。【结论】4-scale模型用来进行PRI与SR-PRI在冠层、叶片间的尺度转换是可行的,通过建立不同LAI下的尺度转换函数,可以实现将冠层尺度的PRI、SR-PRI转化到叶片尺度。

辽宁省瓦房店金刚石原生矿找矿方法组合模型的建立

为了进一步扩大金刚石勘查成果,提交新增金刚石矿资源量,以辽宁省瓦房店地区金伯利岩型金刚石原生矿作为重点研究对象,总结归纳了应用地球物理、水系重砂、地球化学、遥感及三维地质等技术方法的找矿模型,建立了周期短且经济的3种找矿方法组合模型,即重砂法+地面高精度磁测+工程揭露(化探)找矿方法组岩模型、航空物探+地面高精度磁测+重砂法+工程揭露(化探)找矿方法组合模型以及遥感+重砂法+地面高精度磁测+化探+工程揭露找矿方法组合模型。研究成果可对辽宁省金刚石勘查工作起到指导意义。