Radial Basis Functional Link Nets Used as a Prospectivity Mapping Tool for Orogenic Gold Deposits Within the Central Lapland Greenstone Belt, Northern Fennoscandian Shield

Nykänen, Vesa

doi:10.1007/s11053-008-9062-0

Cited by 104 publications

(42 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These advanced, data-driven approaches are being used more frequently in spatial studies to identify and classify areas as well as to predict the distribution of real-world phenomena having to do with flooding, landslides, mines, among others (Biswajeet and Saro, 2007;Nykanen, 2008;Yilmaz, 2009;Choi et al, 2010;Pradhan, 2013). The ANN algorithm imitates the structure of the human brain and conducts predictions based on repeated trainings (Yeo and Yee, 2014).…”

Section: Introductionmentioning

confidence: 99%

Environmental modelling of visceral leishmaniasis by susceptibility-mapping using neural networks: a case study in north-western Iran

et al. 2014

View full text Add to dashboard Cite

Abstract. Visceral leishmaniasis (VL) is a potentially fatal vector-borne zoonotic disease, which has become an increasing public health problem in the north-western part of Iran. This work presents an environmental health modelling approach to map the potential of VL outbreaks in this part of the country. Radial basis functional link networks is used as a data-driven method for predictive mapping of VL in the study area. The high susceptibility areas for VL outbreaks account for 36.3% of the study area and occur mainly in the north (which may affect the neighbouring countries) and South (which is a warning for other provinces in Iran). These parts of the study area have many nomadic, riverside villages. The overall accuracy of the resultant map was 92% in endemic villages. Such susceptibility maps can be used as reconnaissance guides for planning of effective control strategies and identification of possible new VL endemic areas.

show abstract

Section: Introductionmentioning

confidence: 99%

Environmental modelling of visceral leishmaniasis by susceptibility-mapping using neural networks: a case study in north-western Iran

et al. 2014

View full text Add to dashboard Cite

show abstract

“…Proximity to granitoids has been applied as spatial proxy of orogenic gold deposits in different areas (e.g., Nykänen, 2008;Joly et al, 2012).…”

Section: Prospectivity Analysis Of Orogenic Gold Deposits In Saqez-samentioning

confidence: 99%

“…Orogenic-gold deposits are associated with indicative geochemical anomalies, which have been widely used as a reconnaissance-scale exploration tool (Nykänen, 2008;Nykänen et al, 2008a,b;Nykänen and Salmirinne, 2007;Bierlein and McKnight, 2005;Fu et al, 2012;Groves et al, 2000;Goldfarb et al, 2001;.…”

Section: General Characteristics Of Orogenic Gold Depositsmentioning

confidence: 99%

“…The explanation for that is that deformation causes the less competent metasedimentary country rocks to fail by shearing, but given that these rocks are very tight due to previous shortening and deformation no, or only very little, new space is created. The granitoid bodies, on the other hand, fail by fracturing creating low stress sites and space for gold deposition.The fracturing event triggers increased permeability and suction and thus focuses fluid flow into the newly created facture network / stockwork, centered upon granitoid intrusions.Orogenic-gold deposits are associated with indicative geochemical anomalies, which have been widely used as a reconnaissance-scale exploration tool (Nykänen, 2008; Nykänen et al, 2008a,b;Nykänen and Salmirinne, 2007;Bierlein and McKnight, 2005;Fu et al, 2012;Groves et al, 2000;Goldfarb et al, 2001;.In this study, to apply knowledge of critical processes of mineralization in an orogenic gold system to prospectivity analysis (e.g., Groves et al, 2000;McCuaig et al, 2010;Lisitsin et al, 2010;Herbert et al, 2014;Asadi et al, 2016;Duarte Campos, 2017), district-scale mapping of prospectivity for the deposit-type sought was considered appropriate to delineate target areas for further exploration at camp-scale. Following the discussion in Carranza et al (2015), district-scale of mapping was selected considering the sorts of data available in the study area (see next sub-section), which is covered by the 1:100,000 scale geological map ( Fig.…”

mentioning

confidence: 99%

“…3a). Figure 3b represents how application of the small fuzzification function models the relative importance of low evidence values.Proximity to granitoids has been applied as spatial proxy of orogenic gold deposits in different areas (e.g., Nykänen, 2008;Joly et al, 2012). …”

mentioning

confidence: 99%

See 2 more Smart Citations

Prospectivity analysis of orogenic gold deposits in Saqez-Sardasht Goldfield, Zagros Orogen, Iran

Almasi

Yousefi

Carranza

2017

Ore Geology Reviews

View full text Add to dashboard Cite

Diverse deposit-types or mineral systems form by diverse geological processes, so translation of knowledge about the controls of mineralization acquired from the 4D geological modeling into 2D spatial predictor maps is a major challenge for prospectivity analysis. In this regard, mathematical functions have been used to model the conceptual or perceived spatial relationships between geological variables and targeted type or system of mineralization. In this paper, due to the different models of spatial relationships between predictors and mineral deposits, we investigated the performance of different fuzzification functions to quantify the relationships. We demonstrated that various types of relationships between exploration features and a mineralization-type sought could be quantified using different fuzzification functions for prospectivity analysis. We illustrated the process of the prospectivity analysis by using a data set of orogenic gold deposits in Saqez-Sardasht Goldfield, Iran. Prospectivity modeling of orogenic gold mineralization in the study area showed that the NE-SW trending targets have priority for further prospecting of the deposits. Saqez-Sardasht Goldfield, Zagros Orogen, Iran (by A. Almasi, M. Yousefi, E. J.M. Carranza) Manuscript submitted to Ore Geology Reviews 2 Prospectivity analysis of orogenic gold deposits in IntroductionFor mineral prospectivity mapping (MPM) of a deposit-type sought in an area, mathematical functions have been used to model spatial relationships between geological variables system of mineralization (e.g., Bonham-Carter, 1994;Luo and Dimitrakopoulos, 2003; Porwal et al., 2003a,b,c;Carranza, 2008Carranza, , 2017. In MPM, mathematical functions, have been widely used to assign weights to discretized spatial evidence values as fuzzified evidential maps in the [0,1] range or to rank target areas as fuzzy prospectivity models (e.g., Bonham-Carter, 1994;Carranza and Hale, 2002;Luo and Dimitrakopoulos, 2003;Porwal et al., 2003c;Carranza, 2008Carranza, , 2009Carranza, , 2017Lisitsin et al., 2013;Mutele et al., 2017;Nykänen et al., 2017). The weights assigned to classes of discretized evidential values may be based on (a) expert judgment directly, (b) locations of known mineral occurrences (KMOs), (c) a combination of (a) and (b), or (d) subjectively-defined functions, so indirectly-assigned by analyst (e.g., Luo, 1990;Bonham-Carter, 1994;Cheng and Agterberg, 1999;Luo and Dimitrakopoulos, 2003;Porwal et al., 2003a Porwal et al., ,b,c, 2004Porwal et al., , 2006Carranza et al., 2005;Carranza, 2008Carranza, , 2014Porwal and Kreuzer, 2010;Mejía-Herrera et al., 2014;Carranza and Laborte, 2016;McKay and Harris, 2016). All these methods impart bias due to discretization of continuous spatial values, use of subjective expert judgments, and sparse or incomplete data on locations of KMOs in knowledge-and data-driven MPM (Coolbaugh et al., 2007;Lusty et al., 2012;Ford et al., 2016).To reduce bias in the assignment of weights to continuous-value spatial evidence, various re...

show abstract

The spatial leave-pair-out cross-validation method for reliable AUC estimation of spatial classifiers

Airola

Pohjankukka

Torppa

et al. 2018

Data Min Knowl Disc

Self Cite

View full text Add to dashboard Cite

Machine learning based classification methods are widely used in geoscience applications, including mineral prospectivity mapping. Typical characteristics of the data, such as small number of positive instances, imbalanced class distributions and lack of verified negative instances make ROC analysis and cross-validation natural choices for classifier evaluation. However, recent literature has identified two sources of bias, that can affect reliability of area under ROC curve estimation via cross-validation on spatial data. The pooling procedure performed by methods such as leave-one-out can introduce a substantial negative bias to results. At the same time, spatial dependencies leading to spatial autocorrelation can result in overoptimistic results, if not corrected for. In this work, we introduce the spatial leave-pair-out cross-validation method, that corrects for both of these biases simultaneously. The methodology is used to benchmark a number of classification methods on mineral prospectivity mapping data from the Central Lapland greenstone belt. The evaluation highlights the dangers of obtaining misleading results on spatial data and demonstrates how these problems can be avoided. Further, the results show the advantages of simple linear models for this classification task.

show abstract

Radial Basis Functional Link Nets Used as a Prospectivity Mapping Tool for Orogenic Gold Deposits Within the Central Lapland Greenstone Belt, Northern Fennoscandian Shield

Cited by 104 publications

References 31 publications

Environmental modelling of visceral leishmaniasis by susceptibility-mapping using neural networks: a case study in north-western Iran

Environmental modelling of visceral leishmaniasis by susceptibility-mapping using neural networks: a case study in north-western Iran

Prospectivity analysis of orogenic gold deposits in Saqez-Sardasht Goldfield, Zagros Orogen, Iran

The spatial leave-pair-out cross-validation method for reliable AUC estimation of spatial classifiers

Contact Info

Product

Resources

About