Generalized linear and generalized additive models in studies of species distributions: setting the scene

Guisan, Antoine; Edwards, Thomas C.; Hastie, Trevor

doi:10.1016/s0304-3800(02)00204-1

Cited by 1,885 publications

(1,278 citation statements)

References 61 publications

Supporting

Mentioning

1,250

Contrasting

Unclassified

Order By: Relevance

“…GAMs (e.g., Hastie and Tibshirani 1987;Guisan and Zimmermann 2000) provide a flexible nonparametric means that can deal with non-normal data and non-linear relationship between the response and the set of predictor variables. GAMs are the extensions of linear regression models that use the data to automatically estimate the appropriate functional relationship for each predictor (Guisan et al 2002). In a GAM, a link function is utilized to establish a relationship between the mean of the response variable and a smooth function of the predictor variable(s).…”

Section: Methodsmentioning

confidence: 99%

Topographic controls on vegetation index in a hilly landscape: a case study in the Jiaodong Peninsula, eastern China

et al. 2012

View full text Add to dashboard Cite

This study examined topographic influence on spatial and temporal variability in the normalized difference vegetation index (NDVI) derived from the Satellite Pour l'Observation de la Terre-Vegetation at the regional and landscape scales in the Jiaodong Peninsula. The generalized additive models were used to quantify the spatial variation of NDVI attributable to local terrain and topographically related variables including altitude, exposure to incoming solar radiation, topographic wetness index, distance to the nearest stream and distance from the coast. NDVI distribution shows significant dependence on topography. The variables explained 38.3 % of variance in NDVI at the peninsula, and 30-45.3 % of variance in NDVI at the woodland, cropland, and grassland landscapes. At the Jiaodong Peninsula scale, NDVI is influenced primarily by distance from the coast. However, topographic wetness index has the most explanatory power for NDVI at the woodland, cropland, and grassland landscapes. Through a statistical nonparametric correlation analysis (Spearman's r), the study indicates that spatial distribution of NDVI changes during the period 1998-2009 and future change trend of persistence determined by Hurst exponent is closely associated with topography and topography-based attribution. These results highlight the importance of topographic changes at landscape and regional scales as an important control factor on NDVI patterns.

show abstract

Section: Methodsmentioning

confidence: 99%

Topographic controls on vegetation index in a hilly landscape: a case study in the Jiaodong Peninsula, eastern China

et al. 2012

View full text Add to dashboard Cite

show abstract

“…Statistical predictive modelling techniques have been widely used and have shown to be proficient in explaining the relationship between fish distribution and surrounding environmental features (Guisan et al 2002;Ko et al 2008;Vasconcelos et al 2013). Traditionally, models used in ecology to predict potential species distributions were multivariate in nature and based on linear functions (Ko et al 2008).…”

Section: Statistical Multiple Regression Modelmentioning

confidence: 99%

“…Multiple regressions are one of the oldest statistical techniques and has long been used in biological research (Guisan et al 2002). It is very useful for predicting fish distributions in unsurveyed areas.…”

Section: Statistical Multiple Regression Modelmentioning

confidence: 99%

Determination of Potential Fishing Grounds of Rastrelliger kanagurta Using Satellite Remote Sensing and GIS Technique

Nurdin

Mustapha²,

Lihan³

et al. 2015

JSM

View full text Add to dashboard Cite

show abstract

“…The response curve is hence more data than model driven. This is because the data determine the nature of the relationship between the response and the set of explanatory variables rather than assuming some form of parametric relationship (Guisan et al, 2002). A starting model including all continuous predictors smoothed with three degrees of freedom was fitted first.…”

Section: Statistical Techniquesmentioning

confidence: 99%

Downscaling of coarse‐grained geomorphological data

Luoto

Hjort

2007

Earth Surf Processes Landf

View full text Add to dashboard Cite

One of the basic limitations to the use of geomorphological maps is their coarse resolution relative to the needs of pure and applied geomorphological research. In response to this, attempts have been made to 'downscale' geomorphological information to finer spatial resolutions. However, the potential of statistical downscaling in geomorphology has been insufficiently examined. We downscaled four different periglacial features (wind deflation, palsa mire, earth hummock and sorted solifluction sheet) from a 100 ha grid to a 1 ha grid resolution utilizing two different techniques: point sampling (PSA) and direct (DA) approaches. We assessed the predictive accuracy of the models with the area under the curve (AUC) of a receiver operating characteristic plot using independent evaluation data. The PSA technique yielded encouraging results with a mean accuracy of 0·81, whereas the performance of DA was poorer. The predictive performance of the palsa mire and solifluction sheet models was excellent (AUC values from 0·89 to 0·96), whereas the AUC values of deflation and earth hummock models were lower (AUC = = = = = 0·57-0·81). The application of a point sampling approach as used here provides an efficient method to translate geomorphological information to finer resolution. However, further testing of the downscaling approaches is required before they can be applied to real-world situations.

show abstract

Generalized linear and generalized additive models in studies of species distributions: setting the scene

Cited by 1,885 publications

References 61 publications

Topographic controls on vegetation index in a hilly landscape: a case study in the Jiaodong Peninsula, eastern China

Topographic controls on vegetation index in a hilly landscape: a case study in the Jiaodong Peninsula, eastern China

Determination of Potential Fishing Grounds of Rastrelliger kanagurta Using Satellite Remote Sensing and GIS Technique

Downscaling of coarse‐grained geomorphological data

Contact Info

Product

Resources

About