首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献，搜索用时 15 毫秒
1.
The Random Forests (RF) algorithm has recently become a fledgling method for data-driven predictive mapping of mineral prospectivity, and so it is instructive to further study its efficacy in this particular field. This study, carried out using Baguio gold district (Philippines), examines (a) the sensitivity of the RF algorithm to different sets of deposit and non-deposit locations as training data and (b) the performance of RF modeling compared to established methods for data-driven predictive mapping of mineral prospectivity. We found that RF modeling with different training sets of deposit/non-deposit locations is stable and reproducible, and it accurately captures the spatial relationships between the predictor variables and the training deposit/non-deposit locations. For data-driven predictive mapping of epithermal Au prospectivity in the Baguio district, we found that (a) the success-rates of RF modeling are superior to those of weights-of-evidence, evidential belief and logistic regression modeling and (b) the prediction-rate of RF modeling is superior to that of weights-of-evidence modeling but approximately equal to those of evidential belief and logistic regression modeling. Therefore, the RF algorithm is potentially much more useful than existing methods that are currently used for data-driven predictive mapping of mineral prospectivity. However, further testing of the method in other areas is needed to fully explore its usefulness in data-driven predictive mapping of mineral prospectivity.  相似文献   

2.
Data-driven prospectivity mapping can be undermined by dissimilarity in multivariate spatial data signatures of deposit-type locations. Most cases of data-driven prospectivity mapping, however, make use of training sets of randomly selected deposit-type locations with the implicit assumption that they are coherent (i.e., with similar multivariate spatial data signatures). This study shows that the quality of data-driven prospectivity mapping can be improved by using a training set of coherent deposit-type locations. Analysis and selection of coherent deposit-type locations was performed via logistic regression, by using multiple sets of deposit occurrence favourability scores of univariate geoscience spatial data as independent variables and binary deposit occurrence scores as dependent variable. The set of coherent deposit-type locations and three sets of randomly selected deposit-type locations were each used in data-driven prospectivity mapping via application of evidential belief functions. The prospectivity map based on the training set of coherent deposit-type locations resulted in lower uncertainty, better goodness-of-fit to the training set, and better predictive capacity against a cross-validation set of economic deposits of the type sought. This study shows that explicit selection of training set of coherent deposit-type locations should be applied in data-driven prospectivity mapping.  相似文献   

3.
Qualitative and quantitative knowledge about the spatial association between mineral occurrences and geological features are important in mineral potential mapping. Two existing methods for quantifying spatial association between mineral occurrences and curvilinear geological features are applied to the Baguio district of the Philippines. An experimental method is described and applied to the study area as well. The results of the three methods are highly similar, which demonstrates the effectiveness of the experimental method presented here for quantifying spatial association between mineral occurrences and curvilinear geological features. It is shown that gold occurrence in the Baguio district are strongly spatially associated with northeasterly trending faults/fractures rather than with northwesterly trending faults/fractures. It is also shown that the spatial association between the gold occurrence and older batholithic intrusives is stronger than the spatial association between gold occurrence and younger porphyry intrusives. These spatial geoinformation characteristics can be used as evidential data layers in GIS-based mineral potential mapping.  相似文献   

4.
In this paper, point pattern analysis, fractal analysis and Fry analysis were employed to study the spatial pattern of known occurrences of mineral deposits of the type sought, whereas distance distribution method was applied to study the spatial associations between various geological features and known occurrences of mineral deposits of the type sought. In the Aroroy district (Philippines), the results of the applications of these spatial analytical techniques support a conceptual model of district-scale mechanism of geologic controls on low-sulphidation epithermal Au mineralization, which involves a more-or-less regular mesh of interlinked zones of extension faults/fractures at and/or around intersections of NNW- and NW-trending strike-slip faults/fractures. Integration of spatial evidential data layers representing these structural controls and surficial geochemical anomalies, via knowledge-guided application of data-driven evidential belief functions, results in delineation of prospective areas occupying about 25% of the district, in which there is about 70% likelihood of undiscovered occurrences of low-sulphidation epithermal Au deposits.  相似文献   

5.
In the southwestern part of the Ashanti Belt, the results of fractal and Fry analyses of the spatial pattern of 51 known mines/prospects of (mostly lode) gold deposits and the results of analysis of their spatial associations with faults and fault intersections suggest different predominant structural controls on lode gold mineralisation at local and district scales. Intersections of NNE- and NW-trending faults were likely predominantly involved in local-scale structural controls on lode gold mineralisation, whilst NNE-trending faults were likely predominantly involved in district-scale structural controls on lode gold mineralisation. The results of the spatial analyses facilitate the conceptualisation and selection of spatial evidence layers for lode gold prospectivity mapping in the study area. The applications of the derived map of lode gold prospectivity and a map of radial density of spatially coherent lode gold mines/prospects results in a one-level prediction of 37 undiscovered lode gold prospects. The applications of quantified radial density fractal dimensions of the spatial pattern of spatially coherent lode gold mines/prospects result in an estimate of 40 undiscovered lode gold prospects. The study concludes finally that analysis of the spatial pattern of discovered mineral deposits is the key to a strong link between mineral prospectivity mapping and assessment of undiscovered mineral deposits.  相似文献   

6.
This paper proposes that the spatial pattern of known prospects of the deposit‐type sought is the key to link predictive mapping of mineral prospectivity (PMMP) and quantitative mineral resource assessment (QMRA). This proposition is demonstrated by PMMP for hydrothermal Au‐Cu deposits (HACD) and by estimating the number of undiscovered prospects for HACD in Catanduanes Island (Philippines). The results of analyses of the spatial pattern of known prospects of HACD and their spatial associations with geological features are consistent with existing knowledge of geological controls on hydrothermal Au‐Cu mineralization in the island and elsewhere, and are used to define spatial recognition criteria of regional‐scale prospectivity for HACD. Integration of layers of evidence representing the spatial recognition criteria of prospectivity via application of data‐driven evidential belief functions results in a map of prospective areas occupying 20% of the island with fitting‐ and prediction‐rates of 76% and 70%, respectively. The predictive map of prospective areas and a proxy measure for degrees of exploration based on the spatial pattern of known prospects of HACD were used in one‐level prediction of undiscovered mineral endowment, which yielded estimates of 79 to 112 undiscovered prospects of HACD. Application of radial‐density fractal analysis of the spatial pattern of known prospects of HACD results in an estimate of 113 undiscovered prospects of HACD. Thus, the results of the study support the proposition that PMMP can be a part of QMRA if the spatial pattern of discovered prospects of the deposit‐type sought is considered in both PMMP and QMRA.  相似文献   

7.
Gengma region, Sanjiang district is known to have some large-scale gold deposits. GIS predictive model for hydroghermal gold potential was carried out in this region using weights of evidence modeling technique. Datasets used include large-scale hydroghermal gold deposit records, geological, geophysical and remote sensing imagery. Based on the geological and mineral characteristics of areas with known gold occurrences in Sanjiang, several geological features were thought to be indicative of areas with potential for the occurrence of hydroghtermal gold deposits. Indicative features were extracted from geoexploration datasets for use as input in the predictive model. The features include host rock lithology, geologic structures, wallrock alteration and associated (volcanic-plutonic) igneous rocks. To determine which of the indicative geological features are important spatial predictors of area with potential for gold deposits, spatial analysis was done through the modeling method. The input maps were buffered and the optimum distance of spatial association for each geological feature was determined by calculating the contrast and studentized contrast. Five feature maps were converted to binary predictor patterns and used as evidential layers for predictive modeling. The binary patterns were integrated in two combinations, each of which consists of four patterns in order to avoid over prediction due to the effect of duplicate features in the two structural evidences. The two produced potential maps define almost similar favorable zones. Areas of intersections between these zones in the two potential maps placed the highest predictive favorable zones in the region.  相似文献   

8.
数据驱动的证据权法被用来进行金矿潜力制作。为了确定秦岭~松潘金矿的潜力区,需利用地质、地球化学、地球物理等数据。数据采集、图形处理、空间分析都是在GIS平台上进行的。预测结果表明,证据权法在综合不同空间数据上是有效的,最终的预测图件圈出了最有利的矿化区,可用于进一步勘查研究。  相似文献   

9.
We present a mineral systems approach to predictive mapping of orogenic gold prospectivity in the Giyani greenstone belt (GGB) by using layers of spatial evidence representing district-scale processes that are critical to orogenic gold mineralization, namely (a) source of metals/fluids, (b) active pathways, (c) drivers of fluid flow and (d) metal deposition. To demonstrate that the quality of a predictive map of mineral prospectivity is a function of the quality of the maps used as sources of spatial evidence, we created two sets of prospectivity maps — one using an old lithologic map and another using an updated lithological map as two separate sources of spatial evidence for source of metals/fluids, drivers of fluid flow and metal deposition. We also demonstrate the importance of using spatially-coherent (or geologically-consistent) deposit occurrences in data-driven predictive mapping of mineral prospectivity. The best predictive orogenic gold prospectivity map obtained in this study is the one that made use of spatial evidence from the updated lithological map and spatially-coherent orogenic gold occurrences. This map predicts 20% of the GGB to be prospective for orogenic gold, with 89% goodness-of-fit between spatially-coherent inactive orogenic gold mines and individual layers of spatial evidence and 89% prediction-rate against spatially-coherent orogenic gold prospects. In comparison, the predictive gold prospectivity map obtained by using spatial evidence from the old lithological map and all gold occurrences has 80% goodness-of-fit but only 63% prediction-rate. These results mean that the prospectivity map based on spatially-coherent gold occurrences and spatial evidence from the updated lithological map predicts exploration targets better (i.e., 28% smaller prospective areas with 9% stronger fit to training gold mines and 26% higher prediction-rate with respect to validation gold prospects) than the prospectivity map based on all known gold occurrences and spatial evidence from the old lithological map.  相似文献   

10.
This study aims to elaborate on the mineral potential maps using various models and verify the accuracy for the epithermal gold (Au) — silver (Ag) deposits in a Geographic Information System (GIS) environment assuming that all deposits shared a common genesis. The maps of potential Au and Ag deposits were produced by geological data in Taebaeksan mineralized area, Korea. The methodological framework consists of three main steps: 1) identification of spatial relationships 2) quantification of such relationships and 3) combination of multiple quantified relationships. A spatial database containing 46 Au-Ag deposits was constructed using GIS. The spatial association between training deposits and 26 related factors were identified and quantified by probabilistic and statistical modelling. The mineral potential maps were generated by integrating all factors using the overlay method and recombined afterwards using the likelihood ratio model. They were verified by comparison with test mineral deposit locations. The verification revealed that the combined mineral potential map had the greatest accuracy (83.97%), whereas it was 72.24%, 65.85%, 72.23% and 71.02% for the likelihood ratio, weight of evidence, logistic regression and artificial neural network models, respectively. The mineral potential map can provide useful information for the mineral resource development.  相似文献   

11.
The weights-of-evidence is a data-driven method that provides a simple approach to integration of diverse geo-data set information. In this study, we will use weights-of-evidence to build a model for predicting tracts in the Ahar–Arasbaran zone of Urumieh-Dokhtar orogenic belt (northwestern Iran) that are favorable for porphyry copper deposits. Weights of evidence are a data-driven method requiring known deposits and occurrences that are used as training points in the evaluated area. This zone hosts two major porphyry Cu deposits (The Sarcheshmeh deposit contains 450 million tonnes of sulfide ore with an average grade of 1.13 % Cu and 0.03 % Mo and Sungun deposit, which has 500 million tonnes of sulfide reserves grading 0.76 % Cu and 0.01 % Mo), and a number of subeconomic porphyry copper deposits are all associated with Mid- to Late Miocene diorite/granodiorite to quartz-monzonite stocks. Five evidential layers including geology, alteration, geochemistry, geophysics, and faulting are chosen for potential mapping. Weight factors were determined based on the applied method to generate last mineral prospectivity map. The studied area reduces to less than 11.78 %, while large zones are excluded for further studies. This result represents a significant area reduction and may help to better focus on mineral exploration targeting porphyry copper deposits in the Ahar–Arasbaran zone.  相似文献   

12.
This paper describes the geology and tectonics of the Paleoproterozoic Kumasi Basin, Ghana, West Africa, as applied to predictive mapping of prospectivity for orogenic gold mineral systems within the basin. The main objective of the study was to identify the most prospective ground for orogenic gold deposits within the Paleoproterozoic Kumasi Basin. A knowledge-driven, two-stage fuzzy inference system (FIS) was used for prospectivity modelling. The spatial proxies that served as input to the FIS were derived based on a conceptual model of gold mineral systems in the Kumasi Basin. As a first step, key components of the mineral system were predictively modelled using a Mamdani-type FIS. The second step involved combining the individual FIS outputs using a conjunction (product) operator to produce a continuous-scale prospectivity map. Using a cumulative area fuzzy favourability (CAFF) curve approach, this map was reclassified into a ternary prospectivity map divided into high-prospectivity, moderate-prospectivity and low-prospectivity areas, respectively. The spatial distribution of the known gold deposits within the study area relative to that of the prospective and non-prospective areas served as a means for evaluating the capture efficiency of our model. Approximately 99% of the known gold deposits and occurrences fall within high- and moderate-prospectivity areas that occupy 31% of the total study area. The high- and moderate-prospectivity areas illustrated by the prospectivity map are elongate features that are spatially coincident with areas of structural complexity along and reactivation during D4 of NE–SW-striking D2 thrust faults and subsidiary structures, implying a strong structural control on gold mineralization in the Kumasi Basin. In conclusion, our FIS approach to mapping gold prospectivity, which was based entirely on the conceptual reasoning of expert geologists and ignored the spatial distribution of known gold deposits for prospectivity estimation, effectively captured the main mineralized trends. As such, this study also demonstrates the effectiveness of FIS in capturing the linguistic reasoning of expert knowledge by exploration geologists. In spite of using a large number of variables, the curse of dimensionality was precluded because no training data are required for parameter estimation.  相似文献   

13.
《International Geology Review》2012,54(11):1009-1029
Integrated multispectral, geologic, mineralogic, and geochemical studies of the Santa Teresa district, Sonora, Mexico, were used to map the lithology and identify zones of alteration characteristic of known gold deposits within the area. Forty sedimenthosted, bulk-mineable, leachable, fine-grained, disseminated gold prospects have been identified. These deposits vary in size and grade from 1.5 million tons of ore averaging up to 2.8 grams Au/ton to less than 2,000 tons of ore averaging less than 1.0 gm Au/ton. A variety of deposit types exist in the district, having the characteristics of hot-spring sinter, skarns, epithermal high-level veins, bonanza silver veins, granite and porphyry-related mineralization, and sedimenthosted disseminated deposits. The latter is presently the most important economically and is characterized by decalcification, silicification, argillic alteration, and anomalous Au, Ag, As, Hg, and Te.

Digital image processing techniques were used with Landsat 5 Thematic Mapper data to enhance lithologies and to detect alteration associated with the mineral deposits. Thematic Mapper imagery was combined with field mapping and laboratory analysis into a geographic information system. Pertinent information was integrated in order to produce lithologic and alteration maps for regions of interest within the Santa Teresa district to aid exploration.  相似文献   

14.
Weights of evidence (WofE) is an artificial intelligent method for integration of information from diverse sources for predictive purpose in supporting decision making. This method has been commonly used to predict point events by integrating point training layer and binary or ternary evidential layers (multiclass evidence less commonly used). Omnibus weights of evidence integrates fuzzy training layer and diverse evidential layers. This method provides new features in comparison with the ordinary WofE method. This new method has been implemented in a geographic information system-geophysical data analysis system and the method includes the following contents: (1) dual fuzzy weights of evidence (DFWofE), in which training layer and evidential layers can be treated as fuzzy sets. DFWofE can be used to predict not only point events but also area or line events. In this model a fuzzy training layer can be defined based on point, line, and areas using fuzzy membership function; and (2) degree-of-exploration model for WofE is implemented through building a degree of exploration map. This method can be used to assess possible spatial correlations between the degree of exploration and potential evidential layers. Importantly, it would also make it possible to estimate undiscovered resources, if the degree of exploration map is combined with other models that predict where such resources are most likely to occur. These methods and relevant systems were validated using a case study of mineral potential prediction in Gejiu (个旧) mineral district, Yunnan (云南), China.  相似文献   

15.
张士红 《地质与勘探》2020,56(2):239-252
四川省会理-会东矿集区是我国著名的铜资源基地。近年来,随着找矿勘查工作的深入,又提交了多处大中型铜矿床,表明该地区仍具有较大的找矿潜力。本文基于获取的地质、化探和物探数据,应用随机森林(Random Forest,RF)方法,在研究区开展"拉拉式"铜矿成矿潜力预测,取得了较好的效果:随机森林模型预测的平均袋外误差率为6. 25%,受试者工作特征曲线(Receiver Operating Characteristic Curve,ROC)的AUC值为0. 938。利用偏依赖图(Partial Dependence Plot,PDP)分析解释了预测变量与已知矿床(点)的响应关系,按平均精度下降法排序预测要素的重要性,对"拉拉式"矿床的找矿预测工作具有重要意义的前4个变量依次为:Cu元素含量,中-晚元古代(超)基性岩体临近度,Ni元素含量和PC2因子得分。从成矿地质条件角度分析,河口群地层无疑是"拉拉式"铜矿的重要找矿预测要素,但在随机森林模型中的重要性排序相对靠后。究其原因,一方面是与其它连续数值型预测要素不同,河口群地层是二值(0～1)变量;另外,河口群地层的分布范围受覆盖层的影响较大。根据随机森林模型生成的拉拉地区成矿有利度信息,圈定了6处找矿远景区。红铜山-落凼-红泥坡-姜驿高成矿有利度区带呈北北东向展布,主体上与研究区内重要的地质-地球化学-地球物理预测要素异常空间分布一致;其中蒿枝坝-落凼-红泥坡-姑鲁迷找矿远景区是本区已探明铜矿的主要分布区,其内还有进一步勘探的潜力;同时,该异常区呈半环形态,结合地质勘探揭示的变质火山岩厚度分布,及其西部受一组后期北北东向走滑断裂限制的特点,显示出古火山活动中心在西部,并可能存在被切割分离的另一半环异常,这为该地区后续地质研究和铜矿勘查指明了方向。  相似文献   

16.
高阳 《地质与勘探》2021,57(1):198-209
本次研究的中蒙俄跨境区在大地构造位置上位于中亚造山带东部,是多种矿产的成矿密集区。本区成矿区带包括2个Ⅰ级成矿域、2个Ⅱ级成矿省和9个Ⅲ级成矿带。区内金属矿床的分布主要受北东-北北东向及北西向两组断裂的控制。研究区重点金属矿产中,铜矿床以斑岩型为主;金矿床以岩浆热液型为主,也有部分作为伴生矿种产于斑岩型铜(金)矿床之中;铅、锌矿床以热液脉型为主;铀矿床以火山岩型为主。铜、金、铅、锌、铀成矿作用与燕山期岩浆及其热液活动关系最为密切。本研究区具有良好的成矿地质条件和巨大的找矿前景,是进一步开展铜、金、铅、锌、铀等金属矿产找矿工作的重点地区。  相似文献   

17.
INTRODUCTIONThe GIS-based WofE model is a statistics-basedmethod that weights a variety of evidential data onthe basis of prior probabilities (PRP) and combinesall these weights to produce a potential map of poste-rior probability (POP) . The model can be used toprovide support for decision-makers in many fields .For example ,this model was originally used in themedical field,especially for prediction of the proba-bility that a new patient would be diagnosed with adisease .In geology …  相似文献   

18.
The central Iranian volcanic-sedimentary belt in Kerman province of Iran that is located within the Urumieh-Dokhtar magmatic arc zone is chosen to integrate diverse evidential layers for mineral potential mapping. The studied area has high potential of mineral occurrences especially porphyry copper, and the prepared potential maps aim to outline new prospect zones for further investigation. Two evidential layers including the downward continued map and the analytic signal of filtered magnetic data are generated to be used as geophysical plausible traces of porphyry copper occurrences. The low values of the resistivity layer acquired from airborne frequency domain electromagnetic data are also used as an electrical criterion in this study. Four remote sensing evidential layers including argillic, phyllic, propylitic, and hydroxyl alterations are extracted from Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) images in order to map the altered areas associated with porphyry copper deposits. The Enhanced Thematic Mapper Plus (ETM+) images are used as well to prepare iron oxide layer. Since potassic alteration is generally the mainstay of copper ore mineralization, the airborne potassium radiometry data is used to explore both phyllic and potassic alteration. Finally, the geochemical layers of Cu/B/Pb/Zn elements and the main geochemical component responsible for ore mineralization extracted from principal component analysis are included in the integration process to prepare final potential maps. The conventional and the extended version of VIKOR method (as a well-known algorithm in multi-criteria decision making problems) produced two mineral potential maps, and the results were compared with the ones acquired from prevalent methods of the index overlay and fuzzy logic operators of sum and gamma. The final mineral potential maps based upon desired geo-data set indicate adequately matching of high potential zones with previous working and active mines of copper deposits.  相似文献   

19.
Mineral targets are local geological anomalies. In a study area of a number of unit cells, mapping mineral prospectivity can be implemented by identifying anomaly cells from the unit cell population. One-class support vector machine (OCSVM) models can yield useful results in anomaly detection in high-dimensional data or without any assumptions on the distribution of the inlying data. The OCSVM model was applied to mapping gold prospectivity of the Laotudingzi-Xiaosiping district, an area with a complex geological background, in Jilin Province, China. The decision function value of each unit cell belonging to an anomaly was computed on the basis of the trained OCSVM model and used to express gold prospectivity of the cell. The receiver operating characteristic (ROC) curve, area under curve (AUC) and data-processing efficiency were used to compare the performance of the OCSVM model and a restricted Boltzmann machine (RBM) model in mapping gold prospectivity. The results show that the OCSVM model outperforms the RBM model in terms of ROC, AUC and data-processing efficiency. Gold targets were optimally delineated by using the Youden index to maximise the spatial association between the delineated gold targets and known gold deposits. The gold targets delineated by the OCSVM model occupy 11% of the study area and contain 88% of the known gold deposits; and the gold targets delineated by the RBM model occupy 10% of the study area and contain 81% of the known gold deposits. Therefore, the OCSVM model is a feasible mineral prospectivity mapping approach.  相似文献   

20.
This paper demonstrates a modeling procedure of mineral potential mapping based on singularity theory, and further presents an idea to look into metallogeny of Sn–Cu polymetallic deposits in southeastern Yunnan mineral district, China by applying a localized regression method. Mineralization is a typical cascade process generally accompanied by irregular geological, geochemical and geophysical signatures. Singularity index as an efficient anomaly analytical tool helps to identify anomalies as well as characterize formation processes of these anomalies. In this study, the singularity-based mineral potential mapping method was utilized to characterize hydrothermal mineralization associated with magmatic, tectonic and sedimentary processes in this district. Based on the results, a mineral prospectivity model was constructed to delineate target areas. In addition to mineral prospectivity, controlling effects of geo-processes on mineralization are spatially non-stationary. Geographically-weighted regression analysis was thus employed to investigate these spatially-varied controlling effects and it has contributed to improve understanding to local metallogeny in the study area. Results of the spatial analysis presented can be used to guide following stages of mineral exploration in the district.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号