Data-driven topo-climatic mapping with machine learning methods

Automatic environmental monitoring networks enforced by wireless communication technologies provide large and ever increasing volumes of data nowadays. The use of this information in natural hazard research is an important issue. Particularly useful for risk assessment and decision making are the spatial maps of hazard-related parameters produced from point observations and available auxiliary information. The purpose of this article is to present and explore the appropriate tools to process large amounts of available data and produce predictions at fine spatial scales. These are the algorithms of machine learning, which are aimed at non-parametric robust modelling of non-linear dependencies from empirical data. The computational efficiency of the data-driven methods allows producing the prediction maps in real time which makes them superior to physical models for the operational use in risk assessment and mitigation. Particularly, this situation encounters in spatial prediction of climatic variables (topo-climatic mapping). In complex topographies of the mountainous regions, the meteorological processes are highly influenced by the relief. The article shows how these relations, possibly regionalized and non-linear, can be modelled from data using the information from digital elevation models. The particular illustration of the developed methodology concerns the mapping of temperatures (including the situations of Föhn and temperature inversion) given the measurements taken from the Swiss meteorological monitoring network. The range of the methods used in the study includes data-driven feature selection, support vector algorithms and artificial neural networks.     

Investigation of general regression neural network architecture for grade estimation of an Indian iron ore deposit

The mineral resource estimation requires accurate prediction of the grade at location from limited borehole information. It plays the dominant role in the decision-making process for investment and development of various mining projects and hence become an important and crucial stage. This paper evaluvates the use of two distinct artificial neural network (ANN)-based models, general regression neural network (GRNN) and multilayer perceptron neural network (MLP NN), to improve the grade estimation from Koira iron ore region in Sundargarh district, Odisha. ANN-based models capture the inherent complex structure of mineral deposits and provide a reliable generalization of the iron grade. The ANN-based approach does not require any preliminary geological study and is free from any statistical assumption on the raw data before its application. The GRNN is a one-pass learning algorithm and does not require any iterative procedure for training less complex structure and requires only one learning parameter for optimization. In this investigation, the spatial coordinates and multiple lithological units were taken as input variables and the iron grade was taken as the output variable. The comparative analysis of these models has been carried out and the results obtained were validated with traditional geostatistical method ordinary kriging (OK). The GRNN model outperforms the other methods, i.e. MLP and OK, with respect to generalization and predictability of the grades at an un-sampled location.     

Comparison of machine learning models for gully erosion susceptibility mapping

Gully erosion is a disruptive phenomenon which extensively affects the Iranian territory,especially in the Northern provinces.A number of studies have been recently undertaken to study this process and to predict it over space and ultimately,in a broader national effort,to limit its negative effects on local communities.We focused on the Bastam watershed where 9.3% of its surface is currently affected by gullying.Machine learning algorithms are currently under the magnifying glass across the geomorphological community for their high predictive ability.However,unlike the bivariate statistical models,their structure does not provide intuitive and quantifiable measures of environmental preconditioning factors.To cope with such weakness,we interpret preconditioning causes on the basis of a bivariate approach namely,Index of Entropy.And,we performed the susceptibility mapping procedure by testing three extensions of a decision tree model namely,Alternating Decision Tree(ADTree),Naive-Bayes tree(NBTree),and Logistic Model Tree(LMT).We dichotomized the gully information over space into gully presence/absence conditions,which we further explored in their calibration and validation stages.Being the presence/absence information and associated factors identical,the resulting differences are only due to the algorithmic structures of the three models we chose.Such differences are not significant in terms of performances;in fact,the three models produce outstanding predictive AUC measures(ADTree=0.922;NBTree=0.939;LMT=0.944).However,the associated mapping results depict very different patterns where only the LMT is associated with reasonable susceptibility patterns.This is a strong indication of what model combines best performance and mapping for any natural hazard-oriented application.     

地球化学异常识别的两种机器学习算法之比较

在Sklearn的Python语言代码基础上,开发了基于孤独森林和一类支持向量机的多元地球化学异常识别方法程序。选择吉林省和龙地区为实验区,从1∶5万水系沉积物资料中提取地球化学异常。把实验区已知矿点的空间分布位置作为"地真"数据,绘制两种机器学习算法的ROC曲线并计算AUC值,用来对比两种方法的多元地球化学异常识别效果。研究结果表明:两种机器学习算法都能够有效识别多元地球化学异常,所提取的多元地球化学异常与已知矿点具有显著的空间关联性;孤独森林算法在数据处理耗时和多元地球化学异常识别效果方面略优于一类支持向量机。     

低品位磷矿的生物选矿、化工冶金一体化研究

利用生物冶金的方法,将不溶性磷源转化为水溶性或枸溶性磷源,从而提供了一条利用低品位磷矿的新途径.讨论了生物和微生物在磷化工中的研究与应用,介绍了用自制菌磷肥在田间试验所取得的结果,提出了利用生物工程的方法处理低品位磷矿而直接生产磷肥的技术路线.     

中国大型、超大型铜矿床密集区综合信息预测的方法研究

大型、超大型矿床的研究，是自20世纪70年代以来世界地质行业关注的重大课题。本文结合近几年来国家和部委的多项应用研究重大项目的科研成果，选择大型、超大型铜矿床密集区作为研究对象，在综合信息理论与方法体系的指导下，提出了把GIS用于矿产资源评价并真正达到决策分析目的关键是建立知识库，建立因变量图层、自变量图层和控制图层以及编制相应的属性表，系统地总结了一套操作性较强的综合信息预测大型、超大型铜矿床密集区的思路和方法。     

Mill-leach-waste cutoff grades for sulphidic copper ore

Summary Recent mining literature on cutoff grade theory has come to reflect some viewpoints and analyses expressed earlier in the economic literature. Agreement is best when the cutoff grade policy is established by analysis in stages, starting from the limits of the deposit, and using the maximum net present value objective. In the derivation of the optimal cutoff grade policy a dynamic programming approach is then applied to solve the overall problem as a series of linked, nonlinear, stage optimization problems. A wholly satisfactory use of a dynamic programming methodology requires that two conditions be satisfied: the separability and optimality conditions. The former is, strictly, violated by a heap-leaching or dump-leaching process, the latter by possible forms of resource rent taxation. This paper considers the problem of including such a leaching process in a cutoff grade policy analysis along aforementioned lines. It concludes that a workable method of doing so may be found which, in particular, may be quite satisfactory in arid climates where, in addition, some practical leaching experience already exists.     

Influence of the ore block model estimation on the determination of the mining cutoff grade policy for sustainable mine production

Strategic mine planning includes different cut-off grade policy depending on economic parameters of mining projects and grade–tonnage distribution of the deposit. Minimizing incorrect classification of ore and waste during grade–tonnage distribution is of critical importance for a mining operation. This article reviews the influence of the ore grade–tonnage distribution over the cut-off grade policy in a given mining operation. In this study, firstly, the interpolation parameters used to characterize the grade–tonnage distribution in the orebody are given. The resulting distribution of ore and waste is used to analyze uncertainty, risk impact, and to justify mine-planning decisions, according to the interpolation technique used and the number of geological settings and sampling scenarios being considered. Then, the working scheme of the cut-off grade policy and economic parameters are compared according to the resulting estimation from the inverse distance and the nearest neighbor methods.     

Non-parametric machine learning methods for interpolation of spatially varying non-stationary and non-Gaussian geotechnical properties

Spatial interpolation has been frequently encountered in earth sciences and engineering.A reasonable appraisal of subsurface heterogeneity plays a significant role in planning,risk assessment and decision making for geotechnical practice.Geostatistics is commonly used to interpolate spatially varying properties at un-sampled locations from scatter measurements.However,successful application of classic geostatistical models requires prior characterization of spatial auto-correlation structures,which poses a great challenge for unexperienced engineers,particularly when only limited measurements are available.Data-driven machine learning methods,such as radial basis function network(RBFN),require minimal human intervention and provide effective alternatives for spatial interpolation of non-stationary and non-Gaussian data,particularly when measurements are sparse.Conventional RBFN,however,is direction independent(i.e.isotropic)and cannot quantify prediction uncertainty in spatial interpolation.In this study,an ensemble RBFN method is proposed that not only allows geotechnical anisotropy to be properly incorporated,but also quantifies uncertainty in spatial interpolation.The proposed method is illustrated using numerical examples of cone penetration test(CPT)data,which involve interpolation of a 2D CPT cross-section from limited continuous 1D CPT soundings in the vertical direction.In addition,a comparative study is performed to benchmark the proposed ensemble RBFN with two other non-parametric data-driven approaches,namely,Multiple Point Statistics(MPS)and Bayesian Compressive Sensing(BCS).The results reveal that the proposed ensemble RBFN provides a better estimation of spatial patterns and associated prediction uncertainty at un-sampled locations when a reasonable amount of data is available as input.Moreover,the prediction accuracy of all the three methods improves as the number of measurements increases,and vice versa.It is also found that BCS prediction is less sensitive to the number of measurement data and outperforms RBFN and MPS when only limited point observations are available.     

An SVM-based machine learning method for the separation of alteration zones in Sungun porphyry copper deposit

Sungun porphyry copper deposit is in East Azarbaijan province, NW of Iran. There exist four hypogene alteration types in Sungun: potassic, propylitic, potassic–phyllic, and phyllic. Copper mineralization is essentially associated more with the potassic and less with the phyllic alterations and their separation is, therefore, quite important. This research has tried to separate these two alteration zones in Sungun porphyry copper deposit using the Support Vector Machine (SVM) method based on the fluid inclusion data, and seven variables including homogenization temperatures, salinity, pressure, depth, density and the Cu grade have been measured and calculated for each separate sample. To apply this method, use is made of the radial basis function (RBF) as the kernel function. The best values for λ and C (the most important SVM parameters) that perform well in the training and test data are 0.0001 and 1, respectively. If these values for λ and C are applied, the phyllic and potassic alteration zones in the training and test data will be separated with an accuracy of about 95% and 100%, respectively. This method can help geochemists in separating the alteration zones because classifying and separating samples microscopically is not only very hard, but also quite time and money consuming.     

跨孔电波衰减成像初始振幅估算方法比较

跨孔电磁法衰减层析成像是一种利用电磁波振幅信息的方法,通过发射端到接收端电磁波的振幅变化来反演介质衰减常数分布。发射端振幅也就是初始振幅,一般情况下是未知的,它的精度很大程度上影响到层析成像结果,需要在反演前得到或者通过特殊反演方法来处理。本文总结了4种初始振幅处理方法——线性拟合法、矩阵反演法、双频电磁波法以及相邻道比值法,通过合成数据验证了这四种方法的可行性,并且指出了每种方法的优缺点:线性拟合法适合物性变化不大的情况;矩阵反演法对物性情况要求不高,但计算量较大;双频电磁波法能直接得到电导率分布,但只适合良导体情况;相邻道比值法适用情况最广,但容易受干扰影响。     

西藏冈底斯多金属成矿带斑岩铜矿定位预测与资源潜力评价

自1999年开展地质大调查以来,冈底斯成矿带斑岩铜矿研究取得了重大进展.本文在全面收集冈底斯成矿带地质、矿产和物化探资料基础上,建立了本区GIS平台上的资源预测评价系统.采用数理统计分析,确定了冈底斯成矿带斑岩铜矿定位预测的定量化标志35个,认为对斑岩铜矿预测影响比较重要的地质变量(因素权重>0.2)为花岗岩体(不限时代)、Cu、Mo、W、Au、Ag、Bi化探异常、Cu-Mo、Cu-Mo-Au、Cu-Au-Ag组合化探异常、矿床规模、重力场中低负异常场等.在此基础上,开展了工作区斑岩铜矿的定位预测,圈定了斑岩铜矿成矿远景区33处,计算结果与实际矿产分布和地质理论分析相吻合.采用面金属量法对冈底斯成矿带斑岩铜矿的资源潜力进行了估算,结果表明,冈底斯地区仍具有良好的斑岩铜矿找矿远景,1 000 m以浅的潜在铜资源量可达1亿吨以上.其中,驱龙-甲马-拉抗俄、松多雄、白容-冲江、松多握、吉如、达布、汤不拉、龙卡朗、崩不弄金矿、洞嘎、雄村、麦热-仁钦则、蒙哑啊东北、吹败子、岗达、沙让-亚贵拉、青龙-龙马拉、冲木达、洛麦南、拉屋找矿潜力较大.     

天鹿铜矿床粉砂岩型铜矿石特征

天鹿铜矿床是前陆盆地古生代海相砂页岩型铜矿,铜矿石主要为粉砂岩型,包括辉铜矿矿石、辉铜矿斑铜矿矿石、斑铜矿矿石、黄铜矿斑铜矿矿石、黄铜矿矿石、黄铁矿黄铜矿矿石6种自然类型。矿石结构主要为结晶结构和交代结构,矿石构造以浸染状为主。主矿层中的矿化沿岩层厚度具有明显的垂直分带性,从底部到顶板为:辉铜矿→斑铜矿→黄铜矿→黄铁矿,为典型的化学沉积成因铜的硫化物排列组合特征。上述特点与我国及国外海相砂页岩型铜矿一致。     

Comparison of groundwater recharge estimation methods for the semi-arid Nyamandhlovu area, Zimbabwe

The Nyamandhlovu aquifer is the main water resource in the semi-arid Umguza district in Matebeleland North Province in Zimbabwe. The rapid increase in water demand in the city of Bulawayo has prompted the need to quantify the available groundwater resources for sustainable utilization. Groundwater recharge estimation methods and results were compared: chloride mass balance method (19–62 mm/year); water-table fluctuation method (2–50 mm/year); Darcian flownet computations (16–28 mm/year); ¹⁴C age dating (22–25 mm/year); and groundwater modeling (11–26 mm/year). The flownet computational and modeling methods provided better estimates for aerial recharge than the other methods. Based on groundwater modeling, a final estimate for recharge (from precipitation) on the order of 15–20 mm/year is believed to be realistic, assuming that part of the recharge water transpires from the water table by deep-rooted vegetation. This recharge estimate (2.7–3.6% of the annual precipitation of 555 mm/year) compares well with the results of other researchers. The advantages/disadvantages of each recharge method in terms of ease of application, accuracy, and costs are discussed. The groundwater model was also used to quantify the total recharge of the Nyamandhlovu aquifer system (20?×?10⁶–25?×?10⁶ m³/year). Groundwater abstractions exceeding 17?×?10⁶ m³/year could cause ecological damage, affecting, for instance, the deep-rooted vegetation in the area.     

综合物探在西藏尼木地区斑岩铜矿找矿中的应用

西藏尼木地区斑岩铜矿是近年发现的大型斑岩型铜矿.在矿产勘查过程中采用综合物探方法进行圈定勘查目标、缩小找矿靶区、确定异常源、推测矿化空间等项工作,取得了较好的勘查效果,说明在西藏尼木县斑岩铜矿区综合运用地面高精度磁测、激电中梯、激电测深等物探勘查方法,能减少物探的多解性,较好地解决具体的地质问题.     

基于机器学习的区域滑坡危险性评价方法综述

我国滑坡灾害分布范围广,危害严重。区域滑坡危险性评价一直都是滑坡灾害防灾减灾的重要内容之一。近年来,随着大数据和人工智能技术的飞速发展,机器学习技术逐渐在滑坡灾害危险性评价方面得到广泛应用,并取得了较好效果。在大量研读文献的基础上,系统阐述了基于机器学习技术的滑坡危险性评价方法研究现状。综述从评价因子选择与量化归一化、数据清洗与样本集构建、模型选取与训练评价等三个关键环节对现有研究成果进行分析评述,最后对机器学习滑坡危险性评价方法的发展趋势提出讨论意见。     

Developments of geochemical methods for ore prospecting in Bulgaria

Three periods in the development of geochemical methods for ore prospecting in Bulgaria may be distinguished — initial (1954–1960), middle (1961–1969) and contemporary (since 1970) — which are characterized by successively increasing numbers of samples and improving methods of geochemical data evaluation. Geochemical methods have been recognized as effective, rapid and relatively cheap methods for prospecting for ore deposits (Cu, Pb, Zn, Au, W, Mo, etc.), some nonmetalliferrous raw materials (fluorite, barite, phosphorites) and hydrocarbons. They are used in all stages of exploration at scales from 1:200,000 to 1:200. They have contributed to the elucidation of the ore perspectives in many regions, and a number of new ore bodies and deposits have been discovered.Basic geochemical methods applied to ore prospecting in the country utilize soil and rock to detect secondary and primary aureoles. Stream-sediment surveys, hydrochemical and atmochemical methods are of more restricted use. Samples are analyzed by emission spectrometry, atomic absorption and other methods. A united system of computerized processing of geochemical data has been developed, including automatic drawing of geochemical maps.Interpretation of the data consists in selection of prospective geochemical anomalies and prognostication of the composition, morphology, depth and industrial significance of hidden ore bodies. The main problem in the mathematical processing of data is the presentation of polydimensional results from analyses in the form of generalized quantities — multiplicative or additive geochemical indicator ratios for the type of mineralization, coefficients of zoning, intensity, etc. The geochemical indices for evaluation of the newly found anomalies are derived through studies of the primary geochemical aureoles of typical standard ore deposits.Residual secondary soil aureoles in most cases are well correlated in composition and structure with the ore bodies and primary aureoles which have generated them. Their successful use is related to the landscape-geochemical conditions in the ore regions. Micro- and macro-chemical zoning of ground waters and different concentration of soluble components in different elevation belts are used for evaluation of hydrochemical anomalies.     

安基山铜矿床地质—地球物理模型及其找矿意义

安基山铜矿床是长江中下游成矿带东段的典型矿床之一,对控制该矿床的3条主勘探线的钻孔岩心进行了系统的物性测定,建立了矿床地质体与物性体的相关关系,通过对物性体正演的重、磁异常与实测异常对比,以及对矿区地球物理场的平而和剖面分布规律的总结,建立了安基山铜矿床的地质-地球物理模型,在此基础上建立了具有普遍意义的中等剥蚀深度下的同类矿床的地质一地球物理模型,阐述了模型的找矿意义。