specleanr: An R package for automated flagging of environmental outliers in ecological data for modeling workflows

Developing species distribution models (SDM) requires high-quality species occurrence records. These records, stemming from varying sources with different sampling procedures, are often archived in open-access databases, which makes automated data quality checks inevitable. Temporal, geographic, and taxonomic quality checks are usually conducted in SDM workflows, but checking for records distant in environmental space, i.e., outliers, is often ignored. Here, we present specleanr, an R package that contains 20 outlier detection methods (ODMs) that can be ensembled to identify potential outliers in environmental predictors. These methods are categorized into (i) species-specific ecological range, (ii) univariate, and (iii) multivariate ODMs. All potential outliers flagged from the different methods are pooled to identify absolute outliers (records appearing in multiple methods). The local regression (LOESS) method is then used to automatically set a threshold that optimally identifies th..., , # specleanr: An R package for automated flagging of environmental outliers in ecological data for modeling workflows

Dataset DOI: [10.5061/dryad.6m905qgd7](https://doi.org/10.5061/dryad.6m905qgd7)

## Description of the data and file structure

1. The files include species occurrences from the Global Biodiversity Information Facility. Refer to the data links file to access the original data.
2. Environmental data was retrieved from CHELSA and Hydrography90m. These files included B101 to 19 for CHELSA and cti, order*strahler, slopecurv*dw_cel, accumulation, spi, sti, and subcatchment from Hydrography90m. The data link file has the URL to connect to the original dataset.
3. Model outputs were data outputs packaged after model implementation, including modeloutput and modeloutput2.
4. The sdm function was implemented in the sdm_function file.
5. sdmodeling file that processed all files.
6. species prediction were archived in species model prediction output.

### Files and variables

#### ...,