排序方式： 共有18条查询结果，搜索用时 31 毫秒
1.
Brandmeier Melanie Cabrera Zamora Irving Gibran Nykänen Vesa Middleton Maarit 《Natural Resources Research》2020,29(1):71-88
With an increasing demand for raw materials, predictive models that support successful mineral exploration targeting are of great importance. We evaluated different machine learning techniques with an emphasis on boosting algorithms and implemented them in an ArcGIS toolbox. Performance was tested on an exploration dataset from the Iberian Pyrite Belt (IPB) with respect to accuracy, performance, stability, and robustness. Boosting algorithms are ensemble methods used in supervised learning for regression and classification. They combine weak classifiers, i.e., classifiers that perform slightly better than random guessing to obtain robust classifiers. Each time a weak learner is added; the learning set is reweighted to give more importance to misclassified samples. Our test area, the IPB, is one of the oldest mining districts in the world and hosts giant volcanic-hosted massive sulfide (VMS) deposits. The spatial density of ore deposits, as well as the size and tonnage, makes the area unique, and due to the high data availability and number of known deposits, well-suited for testing machine learning algorithms. We combined several geophysical datasets, as well as layers derived from geological maps as predictors of the presence or absence of VMS deposits. Boosting algorithms such as BrownBoost and Adaboost were tested and compared to Logistic Regression (LR), Random Forests (RF) and Support Vector machines (SVM) in several experiments. We found performance results relatively similar, especially to BrownBoost, which slightly outperformed LR and SVM with respective accuracies of 0.96 compared to 0.89 and 0.93. Data augmentation by perturbing deposit location led to a 7% improvement in results. Variations in the split ratio of training and test data led to a reduction in the accuracy of the prediction result with relative stability occurring at a critical point at around 26 training samples out of 130 total samples. When lower numbers of training data were introduced accuracy dropped significantly. In comparison with other machine learning methods, Adaboost is user-friendly due to relatively short training and prediction times, the low likelihood of overfitting and the reduced number of hyperparameters for optimization. Boosting algorithms gave high predictive accuracies, making them a potential data-driven alternative for regional scale and/or brownfields mineral exploration.
相似文献2.
Much of the research that concerns the impacts of management measures in the eastern Baltic cod fishery has focused on fish stock rather than understanding fishermen's attitudes towards regulations. Hence, there is little information available on fishermen's responses although they are the ones whom the regulations affect most profoundly. This study analyses the views of fishermen towards management measures with an emphasis on fishing closures (marine protected areas, MPAs). Swedish log-book data from 1996 to 2005 were used to describe MPA induced fishing effort displacements. Fishermen argued that MPAs have been inefficient in conservation of cod stock. The enlargement of Bornholm MPA in 2005 caused substantial effort displacement towards areas dominated by smaller sized fish. This contributed to the increased discarding of juvenile cod. Enlarged MPAs also intensified competition between different fleet segments and reallocated fishing areas. To reduce fishing mortality, fishermen suggested days-at-sea (effort) regulation and an effective landings control system for all fleets that exploit cod stocks in the Baltic Sea Main Basin. These measures would better motivate fishermen for mutual rule compliance, which is a prerequisite for a sustainable cod fishery. 相似文献
3.
Vesa Nykänen 《Natural Resources Research》2008,17(1):29-48
Among the more popular spatial modeling techniques, artificial neural networks (ANN) are tools that can deal with non-linear
relationships, can classify unknown data into categories by using known examples for training, and can deal with uncertainty;
characteristics that provide new possibilities for data exploration. Radial basis functional link nets (RBFLN), a form of
ANN, are applied to generate a series of prospectivity maps for orogenic gold deposits within the Paleoproterozoic Central
Lapland Greenstone Belt, Northern Fennoscandian Shield, Finland, which is considered highly prospective yet clearly under
explored. The supervised RBFLN performs better than previously applied statistical weights-of-evidence or conceptual fuzzy
logic methods, and equal to logistic regression method, when applied to the same geophysical and geochemical data layers that
are proxies for conceptual geological controls. By weighting the training feature vectors in terms of the size of the gold
deposits, the classification of the neural network results provides an improved prediction of the distribution of the more
important deposits/occurrences. Thus, ANN, more specifically RBFLN, potentially provide a better tool to other methodologies
in the development of prospectivity maps for mineral deposits, hence aiding conceptual exploration. 相似文献
4.
Hannu Huhma Robert A. Cliff Vesa Perttunen Matti Sakko 《Contributions to Mineralogy and Petrology》1990,104(3):369-379
The Peräpohja schist belt in northern Finland rests unconformably on Archaean granitoids, and marks the early stages of Proterozoic crustal evolution in the Fennoscandian (Baltic) shield. 2440 Ma old layered mafic intrusions predate the supracrustal , and ca. 2200 Ma old sills of the gabbro-wehrlite association intrude the lowest quartzites and volcanics (Runkaus) of the sequence. The Sm-Nd mineral isochron of the Penikat layered intrusion gives an age of 2410±64 Ma. The initial Nd-values of the Penikat intrusion (Nd(2440) = –1.6) and the Runkausvaara sill (Nd(2200) 0) suggest that these mafic magmas were contaminated by older crustal material. The Sm-Nd and Pb isotopic results on the 2.44–2.2 Ga old Runkaus volcanics indicate mobility of Pb, fractionation of Sm/Nd during late greenschist facies metamorphism, and crustal contamination. The Pb-Pb data provide an age of 1972±80 Ma with a high initial 207Pb/204Pb ratio (1 = 8.49), while scattered Sm-Nd data result in an imprecise age of 2330±180 Ma, with an initial Nd-value of about zero. Secondary titanite gives an U-Pb age of ca. 2250 Ma. The Jouttiaapa basalts, in contrast, ascended from the mantle without interaction with older crust. These LREE depleted tholeiites mark a break in continental sedimentation, and yield a Sm-Nd age of 2090±70 Ma. Their initial Nd = + 4.2 ±0.5 implies that the subcontinental early Proterozoic mantle had been depleted in LREE for a long period of time. The first lava flows are strongly depleted in LREE, suggesting that their source was significantly more depleted than the source of mid-ocean ridge basalts today. 相似文献
5.
Geoscientific Information Systems (GIS) provide tools to quantitatively analyze and integrate spatially referenced information
from geological, geophysical, and geochemical surveys for decision-making processes. Excellent coverage of well-documented,
precise and good quality data enables testing of variable exploration models in an efficient and cost effective way with GIS
tools. Digital geoscientific data from the Geological Survey of Finland (GTK) are being used widely as spatial evidence in
exploration targeting, that is ranking areas based on their exploration importance. In the last few years, spatial analysis
techniques including weights-of-evidence, logistic regression, and fuzzy logic, have been increasingly used in GTK’s mineral
exploration and geological mapping projects. Special emphasis has been put into the exploration for gold because of the excellent
data coverage within the prospective volcanic belts and because of the increased activity in gold exploration in Finland during
recent years. In this paper, we describe some successful case histories of using the weights-of-evidence method for the Au-potential
mapping. These projects have shown that, by using spatial modeling techniques, exploration targets can be generated by quantitatively
analyzing extensive amounts of data from various sources and to rank these target areas based on their exploration potential. 相似文献
6.
Lake and reservoir water quality affected by metals leaching from tropical soils, Bangladesh 总被引：2，自引：0，他引：2
Md. R. Islam W. P. Lahermo R. Salminen S. Rojstaczer V. Peuraniemi 《Environmental Geology》2000,39(10):1083-1089
The release of metals during weathering has been studied in order to assess its geochemical controls and possible effects
on environmental health in Bangladesh. A total of 27 soil samples and 7 surface water samples were collected from four locations
covering three major regions in the country. Results show that weathering effects are a strong function of climatic conditions.
Surface waters are typically enriched in Al, Mg, Ca, Na, K, As, Ba, Cr, Cu, Ni, Pb and Zn. The solubility of metal ions, organometallic
complexes, co-precipitation or co-existence with the colloidal clay fraction are the main processes that lead to metal enrichment
in lake and reservoir water. Aluminium concentrations exceed World Health Organization (WHO) drinking-water standards in all
samples, and in two regions, arsenic concentrations also significantly exceed WHO standards. The elevated levels of As indicate
that arsenic contamination of water supplies in Bangladesh is not confined to groundwater.
Received: 4 June 1999 · Accepted: 17 August 1999 相似文献
7.
A recently published study has shown that small-scale geologic map data can reproduce mineral assessments made with considerably
larger scale data. This result contradicts conventional wisdom about the importance of scale in mineral exploration, at least
for regional studies. In order to formally investigate aspects of scale, a weights-of-evidence analysis using known gold occurrences
and deposits in the Central Lapland Greenstone Belt of Finland as training sites provided a test of the predictive power of
the aeromagnetic data. These orogenic-mesothermal-type gold occurrences and deposits have strong lithologic and structural
controls associated with long (up to several kilometers), narrow (up to hundreds of meters) hydrothermal alteration zones
with associated magnetic lows. The aeromagnetic data were processed using conventional geophysical methods of successive upward
continuation simulating terrane clearance or ‘flight height’ from the original 30 m to an artificial 2000 m. The analyses
show, as expected, that the predictive power of aeromagnetic data, as measured by the weights-of-evidence contrast, decreases
with increasing flight height. Interestingly, the Moran autocorrelation of aeromagnetic data representing differing flight
height, that is spatial scales, decreases with decreasing resolution of source data. The Moran autocorrelation coefficient
scems to be another measure of the quality of the aeromagnetic data for predicting exploration targets. 相似文献
8.
Mineralogical changes during intense chemical weathering of sedimentary rocks in Bangladesh 总被引：1，自引：0，他引：1
Md. R. Islam Rojstaczer Stuart Aario Risto Peuraniemi Vesa 《Journal of Asian Earth Sciences》2002,20(8):88
Bangladesh is situated in a subtropical to tropical climatic zone. A recently weathered crust has developed on sedimentary bedrock (sandstone, siltstone, shale and claystones) of Tertiary–Quaternary age. Weathered samples were collected from 16 sections totaling 68 samples and were analyzed mineralogically. The main primary minerals identified in the weathered crust of sedimentary rocks are quartz, plagioclase, K-feldspar, biotite, muscovite, sparse carbonate and epidote. The secondary minerals are kaolinite, illite, chlorite, gibbsite and goethite. Weathering initiated along the grain boundaries and cleavage planes of the minerals, forming small cloudy materials which were very difficult to identify. In the advanced stage of weathering, these cloudy materials have turned into secondary minerals. In region 1, high rain fall (7100 mm/yr) and monsoonic climate resulted in a kaolinite–gibbsite–goethite suite through the weathering of feldspars and biotite. The occurrence of gibbsite in the relatively elevated lands of Sylhet and Fe-kaolinite throughout the study areas is indicative of a humid–tropical climate during formation of the weathered crust. 相似文献
9.
10.