Kao, Szu-YuEnns, Eva ATomamichel, MeganDoll, AdamEscobar, Luis EQiao, HuijieCraft, Meggan EPhelps, Nicholas B D2020-10-282020-10-282020-10-28https://hdl.handle.net/11299/216936The data sets contain annual and weekly simulated boater movements. The annual movement data are provided in .csv format. The weekly movement data are in .txt format. We provided an example python script to demonstrate how to load the weekly boater movement data.The data contains simulated boater movements across lakes in the state of Minnesota (MN). The data were simulated based on the boater inspection program conducted by the Minnesota Department of Natural Resources in 2014-2017. Using the inspection survey, we employed machine learning technique, XGBoost, to construct three predictive boater movement models. First, we predicted the number of boater traffic on a lake for a year. Second, we predicted the boater connection between any pair of lakes in MN. Third, we predicted the number of boaters between two lakes that were predicted to have connection.CC0 1.0 Universalboater movementnetwork analysisaquatic invasive speciesDatasethttps://doi.org/10.13020/DJW8-2V86