Landslide susceptibility mapping is a typical two-class classification problem where generating pseudo absence (non-slide) data plays an important role.In this paper,a new method,target space exteriorization sampling ...Landslide susceptibility mapping is a typical two-class classification problem where generating pseudo absence (non-slide) data plays an important role.In this paper,a new method,target space exteriorization sampling method (TSES),is presented to generate pseudo absence data based on presence data directly in feature space.TSES exteriorizes a presence sample to become a pseudo absence one by replacing the value of one of its features with a new one outside the value range of this feature of all presence data.This method is compared with two existing methods,buffer controlled sampling (BCS) and iteratively refined sampling (IRS),in a study area of Shenzhen city.The pseudo absence data generated by each of these three methods are organized into 20 subsets with increasing data sizes to study the effects of the proportion of pseudo absence data to presence data.The landslide susceptibility maps of the study area are calculated with all these datasets by general additive model (GAM).It can be concluded that,through a 10-fold validation,TSES and IRS-based models have similar AUC values that are both greater than that of BCS,but TSES outperforms BCS and IRS in prediction efficiency.TSES results also have more reasonable spatial and histogram distributions than BCS and IRS,which can support categorization of an area into more susceptibility ranks,while IRS shows a tendency to separate the whole study area into two susceptibility extremes.It can be also concluded that when using BCS,the pseudo absence data proportion to the presence data would be about 50% to get a considerable result,while for IRS or TSES the minimum proportion is 40%.展开更多
The generalized linear model （GLM） and generalized additive model （GAM） were applied to the standardization of catch per unit effort （CPUE） for Chilean jack mackerel from Chinese factory trawl fishing fleets in ...The generalized linear model （GLM） and generalized additive model （GAM） were applied to the standardization of catch per unit effort （CPUE） for Chilean jack mackerel from Chinese factory trawl fishing fleets in the Southeast Pacific Ocean from 2001 to 2010 by removing the operational, environmental, spatial and temporal impacts. A total of 9 factors were selected to build the GLM and GAM, i.e., Year, Month, Vessel, La Nifia and E1 Nifio events （ELE）, Latitude, Longitude, Sea surface temperature （SST）, SST anomaly （SSTA）, Nino3.4 index and an interaction term between Longitude and Latitude. The first 5 factors were significant components in the GLM, which in combination explained 27.34% of the total variance in nominal CPUE. In the stepwise GAM, all factors explained 30.78% of the total variance, with Month, Year and Vessel as the main factors influencing CPUE. The higher CPUE occurred during the period April to July at a SST range of 12-15℃ and a SSTA range of 0.2-1.0℃. The CPUE was significantly higher in normal years compared with that in La Nifia and E1 Nifio years. The abundance of Chilean jack mackerel declined during 2001 and 2010, with an increase in 2007. This work provided the relative abundance index of Chilean jack mackerel for stock as- sessment by standardizing catch and effort data of Chinese trawl fisheries and examined the influence of temporal, spatial, environ- mental and fisheries operational factors on Chilean jack mackerel CPUE.展开更多
基金supported by the Research Fund from Hong Kong Polytechnic University(Grant Nos.G-U632,G-YF24)National Key Technologies Research and Development Program of China(Grant Nos.2008BAJ11B04,2006BAJ14B04)+1 种基金National Natural Science Foundation of China(Grant Nos.40928001,40701134,40771171)National High technology Research and Development Program of China("863"Program)(Grant No.2007AA120502)
文摘Landslide susceptibility mapping is a typical two-class classification problem where generating pseudo absence (non-slide) data plays an important role.In this paper,a new method,target space exteriorization sampling method (TSES),is presented to generate pseudo absence data based on presence data directly in feature space.TSES exteriorizes a presence sample to become a pseudo absence one by replacing the value of one of its features with a new one outside the value range of this feature of all presence data.This method is compared with two existing methods,buffer controlled sampling (BCS) and iteratively refined sampling (IRS),in a study area of Shenzhen city.The pseudo absence data generated by each of these three methods are organized into 20 subsets with increasing data sizes to study the effects of the proportion of pseudo absence data to presence data.The landslide susceptibility maps of the study area are calculated with all these datasets by general additive model (GAM).It can be concluded that,through a 10-fold validation,TSES and IRS-based models have similar AUC values that are both greater than that of BCS,but TSES outperforms BCS and IRS in prediction efficiency.TSES results also have more reasonable spatial and histogram distributions than BCS and IRS,which can support categorization of an area into more susceptibility ranks,while IRS shows a tendency to separate the whole study area into two susceptibility extremes.It can be also concluded that when using BCS,the pseudo absence data proportion to the presence data would be about 50% to get a considerable result,while for IRS or TSES the minimum proportion is 40%.
基金co-funded by the National High Technology Research and Development program of China(No.2012AA092301)the Agriculture Science Technology Achievement Transformation Fund(No.2010C00001)the Project of Fishery Exploration in High Seas of the Ministry of Agriculture of China(2010–2011)
文摘The generalized linear model （GLM） and generalized additive model （GAM） were applied to the standardization of catch per unit effort （CPUE） for Chilean jack mackerel from Chinese factory trawl fishing fleets in the Southeast Pacific Ocean from 2001 to 2010 by removing the operational, environmental, spatial and temporal impacts. A total of 9 factors were selected to build the GLM and GAM, i.e., Year, Month, Vessel, La Nifia and E1 Nifio events （ELE）, Latitude, Longitude, Sea surface temperature （SST）, SST anomaly （SSTA）, Nino3.4 index and an interaction term between Longitude and Latitude. The first 5 factors were significant components in the GLM, which in combination explained 27.34% of the total variance in nominal CPUE. In the stepwise GAM, all factors explained 30.78% of the total variance, with Month, Year and Vessel as the main factors influencing CPUE. The higher CPUE occurred during the period April to July at a SST range of 12-15℃ and a SSTA range of 0.2-1.0℃. The CPUE was significantly higher in normal years compared with that in La Nifia and E1 Nifio years. The abundance of Chilean jack mackerel declined during 2001 and 2010, with an increase in 2007. This work provided the relative abundance index of Chilean jack mackerel for stock as- sessment by standardizing catch and effort data of Chinese trawl fisheries and examined the influence of temporal, spatial, environ- mental and fisheries operational factors on Chilean jack mackerel CPUE.
