Data for: Spatial prediction of plant invasion using a hybrid of machine learning and geostatistical method

Modelling ecological patterns and processes often involves large-scale and complex high-dimensional spatial data. Due to the nonlinearity and multicollinearity of ecological data, traditional geostatistical methods have faced great challenges in model accuracy. As machine learning has increased our ability to construct models on big data, the main focus of the study is to propose the use of statistical models that hybridize machine learning and spatial interpolation methods to cope with the increasingly large-scale and complex ecological data. Here, two machine learning algorithms, boosted regression tree (BRT) and least absolute shrinkage and selection operator (LASSO), were combined with ordinary kriging (OK) to model plant invasions across the eastern United States. The accuracy of the hybrid models and conventional models was evaluated by 10-fold cross-validation. Based on an invasive plants dataset of 15 ecoregions across the eastern United States, the results showed that the hybri..., , , # Invasive plants data

The U.S. Forest Inventory and Analysis program (FIA) has been collecting invasive plants occurrence and distribution through all public and private U.S. forests for several decades. It has provided large-scale samples and high-dimensional variables which can be used in statistical models to reflect local ecological differences of plots varying in environment and invasion of non-native species (Cleland et al., 1997).

## Description of the data and file structure

**newinvasion.csv**: This is the main dataset at the plot level, containing invasive plant cover and 41 ecological variables used as auxiliary predictors to improve spatial prediction. Detailed descriptions of all variables are provided below.

* **LAT**: Latitude in decimal degrees (Iannone et al., 2016)
* **LON**: Longitude in decimal degrees (Iannone et al., 2016)
* **Mean_Annual_Temp**: Mean annual temperature (°C × 100) (Iannone et al., 2016)
* **annual_Precip**: Annual precipitation (mm) (Iannone e..., ,