I want to make a susceptibility map of an area by using ArcGIS Pro and R.
I am studying forest fires, so considering the independent variables are precipitation, air temperature, surface temperature, altitude, slope, etc., the dependent variables are fire occurrence, and fire does not occur. I have obtained the fire position information, and randomly sample a certain number of non-fire positions and information. Meanwhile, through these points, information about fire-related factors was obtained. The analysis of these data was performed in R using logistic regression and random forest methods, and I have obtained the importance of each fire-related factor.
Currently, in R I can predict the probabilities of fires and non-fires, which I calculate from the model and the properties of the known points, but I want to extend this prediction to the entire study area. I have tried converting the raster layer of the study area into a point layer in ArcGIS and extracting the information of various fire-related factors through these points, and then importing these points into R for prediction. However, due to a large amount of data, some data are missing. I am currently planning to superimpose the face information of each relevant factor in R for prediction. I don't know if it is feasible.