Climate factors showed stronger effect on the virome of H. longicornis. The most important climatic factors associated with the virome of H. longicornis were high temperature, and low relative humidity/precipitation, which increased the diversity, mainly the evenness of vertebrate associated viruses. In this study, we developed a deep learning model for prediction tick virus diversity by six cliamte factors (future climate data were downloaded from climate model of CMIP6).
climate variables
---------------------
tas : Near-Surface Air Temperature
tasmax : Daily Maximum Near-Surface Air Temperature
psl (Pa): Sea Level Pressure
pr (kg m-2 s-1): Precipitation
hurs (%): Near-Surface Relative Humidity
sfcWind (m s-1): Near-Surface Wind Speed
Requirements
----------------
tensorflow: 2.2.0
cuda: 10.2 (for using GPU)
cudnn: 7.6.5.32 (for using GPU)
numpy: 1.18.5
scripts
-----------
Three scripts are provided in "scripts" folder:
CMIP6_data_process.py: for processing climate data from climate model
train_model.py: for training model
prediction.py: for prediction via inputting the six climate factors introduced above
datasets
------------
In datasets folder:
CNRM-CM6-1-HR_sourceData provides the link for downloading the source data of the climate model
extratced data (for predition) after run CMIP6_data_process.py are in folder climate_extract_byCMIP6_data_process
latitude and longitude information is in latitude_and_longitude folder
the data need for training model are in for_model_training