Isolation Forest-Based Presence-Only Species Distribution Modeling
Download historic Bioclimatic indicators (BIOs) named CMCC-BioClimInd.
Convert predicted suitability to presence-absence map.
Detect areas influenced by a changing environment variable.
Remove environmental variables that have high correlation with others.
Evaluate the model based on presence-only data.
Format the occurrence dataset for usage in itsdm
Download future Bioclimatic indicators (BIOs) named CMCC-BioClimInd.
A function to parse the future climate from worldclim version 2.1.
Calculate independent responses of each variables.
Build Isolation forest species distribution model and explain the the ...
Isolation forest-based presence-only species distribution modeling
Calculate marginal responses of each variables.
Display the figure and map of the EnviChange object.
Exhibit suspicious outliers in an observation dataset.
Show independent response curves.
Show marginal response curves.
Display results of conversion to presence-absence (PA).
Show model evaluation.
Show variable dependence plots and variable interaction plots obtained...
Display Shapley values-based spatial variable dependence maps.
Display spatial variable dependence maps.
Display variable importance.
Exhibit variable contribution for target observations.
Print summary information from EnviChange object.
Print summary information from EnvironmentalOutlier object.
Print summary information from FormatOccurrence object.
Print summary information from PAConversion object.
Print summary information from model evaluation object (POEvaluation...
Print summary information from POIsotree object.
Print summary information from ReducedImageStack object.
Print summary information from variable importance object (`VariableAn...
Estimate suitability on stars object using trained `isolation.forest...
Calculate Shapley value-based variable dependence.
Calculate shapley values-based spatial response.
Calculate spatial response or dependence figures.
Function to detect suspicious outliers based on environmental variable...
Function to evaluate relative importance of each variable.
Evaluate variable contributions for targeted observations.
Download environmental variables made by worldclim version 2.1.
Collection of R functions to do purely presence-only species distribution modeling with isolation forest (iForest) and its variations such as Extended isolation forest and SCiForest. See the details of these methods in references: Liu, F.T., Ting, K.M. and Zhou, Z.H. (2008) <doi:10.1109/ICDM.2008.17>, Hariri, S., Kind, M.C. and Brunner, R.J. (2019) <doi:10.1109/TKDE.2019.2947676>, Liu, F.T., Ting, K.M. and Zhou, Z.H. (2010) <doi:10.1007/978-3-642-15883-4_18>, Guha, S., Mishra, N., Roy, G. and Schrijvers, O. (2016) <https://proceedings.mlr.press/v48/guha16.html>, Cortes, D. (2021) <doi:10.48550/arXiv.2110.13402>. Additionally, Shapley values are used to explain model inputs and outputs. See details in references: Shapley, L.S. (1953) <doi:10.1515/9781400881970-018>, Lundberg, S.M. and Lee, S.I. (2017) <https://dm-gatech.github.io/CS8803-Fall2018-DML-Papers/shapley.pdf>, Molnar, C. (2020) <ISBN:978-0-244-76852-2>, Štrumbelj, E. and Kononenko, I. (2014) <doi:10.1007/s10115-013-0679-x>. itsdm also provides functions to diagnose variable response, analyze variable importance, draw spatial dependence of variables and examine variable contribution. As utilities, the package includes a few functions to download bioclimatic variables including 'WorldClim' version 2.0 (see Fick, S.E. and Hijmans, R.J. (2017) <doi:10.1002/joc.5086>) and 'CMCC-BioClimInd' (see Noce, S., Caporaso, L. and Santini, M. (2020) <doi:10.1038/s41597-020-00726-5>.
Useful links