A Hybrid Logistic Regression: Gene Expression Programming Model and Its Application to Mineral Prospectivity Mapping

2021 ◽  
Author(s):  
Fan Xiao ◽  
Weilin Chen ◽  
Jun Wang ◽  
Oktay Erten
Keyword(s):  
Gene Expression ◽  
Logistic Regression ◽  
Programming Model ◽  
Gene Expression Programming ◽  
Mineral Prospectivity Mapping ◽  
Mineral Prospectivity ◽  
Prospectivity Mapping

scholarly journals An improved logistic regression model based on a spatially weighted technique (ILRBSWT v1.0) and its application to mineral prospectivity mapping

2018 ◽  
Vol 11 (6) ◽  
pp. 2525-2539 ◽  
Author(s):  
Daojun Zhang ◽  
Na Ren ◽  
Xianhui Hou
Keyword(s):  
Logistic Regression ◽  
Regression Model ◽  
Logistic Regression Model ◽  
Mineral Prospectivity Mapping ◽  
Model Based ◽  
Geological Processes ◽  
Data Processing Method ◽  
Mineral Prospectivity ◽  
Improved Model ◽  
Prospectivity Mapping

Abstract. The combination of complex, multiple minerogenic stages and mineral superposition during geological processes has resulted in dynamic spatial distributions and nonstationarity of geological variables. For example, geochemical elements exhibit clear spatial variability and trends with coverage type changes. Thus, bias is likely to occur under these conditions when general regression models are applied to mineral prospectivity mapping (MPM). In this study, we used a spatially weighted technique to improve general logistic regression and developed an improved model, i.e., the improved logistic regression model, based on a spatially weighted technique (ILRBSWT, version 1.0). The capabilities and advantages of ILRBSWT are as follows: (1) it is a geographically weighted regression (GWR) model, and thus it has all advantages of GWR when managing spatial trends and nonstationarity; (2) while the current software employed for GWR mainly applies linear regression, ILRBSWT is based on logistic regression, which is more suitable for MPM because mineralization is a binary event; (3) a missing data processing method borrowed from weights of evidence is included in ILRBSWT to extend its adaptability when managing multisource data; and (4) in addition to geographical distance, the differences in data quality or exploration level can be weighted in the new model.

scholarly journals Improved logistic regression model based on a spatially weighted technique (ILRBSWT v1.0) and its application to mineral prospectivity mapping

2018 ◽  
Author(s):  
Daojun Zhang ◽  
Na Ren ◽  
Xianhui Hou
Keyword(s):  
Logistic Regression ◽  
Regression Model ◽  
Logistic Regression Model ◽  
Mineral Prospectivity Mapping ◽  
Model Based ◽  
Geological Processes ◽  
Geochemical Elements ◽  
Mineral Prospectivity ◽  
Improved Model ◽  
Prospectivity Mapping

Abstract. Due to complexity, multiple minerogenic stages, and superposition during geological processes, the spatial distributions of geological variables also exhibit specific trends and non-stationarity. For example, geochemical elements exhibit obvious spatial non-stationarity and trends because of the deposition of different types of coverage. Thus, bias may clearly occur under these conditions when general regression models are applied to mineral prospectivity mapping (MPM). In this study, we used a spatially weighted technique to improve general logistic regression and developed an improved model called the improved logistic regression model based on spatially weighted technique (ILRBSWT, version 1.0). The capabilities and advantages of ILRBSWT are as follows: (1) ILRBSWT is essentially a geographically weighted regression (GWR) model, and thus it has all its advantages when dealing with spatial trends and non-stationarity; (2) the current software employed for GWR mainly applies linear regression whereas ILRBSWT is based on logistic regression, which is used more commonly in MPM because mineralization is a binary event; (3) a missing data process method borrowed from weights of evidence is included to extend the adaptability when dealing with multisource data; and (4) the differences of data quality or exploration level can also be weighted in the new model as well as the geographical distance.

scholarly journals A Monte Carlo-based framework for risk-return analysis in mineral prospectivity mapping

2020 ◽  
Vol 11 (6) ◽  
pp. 2297-2308 ◽  
Author(s):  
Ziye Wang ◽  
Zhen Yin ◽  
Jef Caers ◽  
Renguang Zuo
Keyword(s):  
Monte Carlo ◽  
Risk Return ◽  
Mineral Prospectivity Mapping ◽  
Mineral Prospectivity ◽  
Prospectivity Mapping
Sign in / Sign up

Export Citation Format

Share Document