Dear all,
I am currently doing a project that is integrating the GIS and ANN together for watershed management. However I am stucked in how to inputting the files into the neural network.
Please kindly share with me the procedures and your help is highly appreciated!
Hi Jacky,
You can import a shapefile directly in matlab through:
newdata = shaperead(olddata.shp);
I am not sure about the format of your DEM. It is certainly not a shapefile as it will be a grid.
Good luck,
Jetse
Hi, you can not directly take into account as DEM to ann afaik. However, you can import DEM as matrix, it is easy for train network for what kind of process you would like, you can, as follows.
https://www.mathworks.com/help/nnet/ref/trainnetwork.html
trainedNet = trainNetwork(X,Y,layers,options)
trains a network for image classification and regression problems. X contains the predictor variables and Y contains the categorical labels or numeric responses.
you can read in the files as text (if you dump them as such),
then you can extract shape descriptors, moments etc., and feed them as features to your neural network classifier.
Thank you so much for all the answer.
Understanding that the DEM shape file can be converted into Grid files, meaning with x and Y coordinates.
I would like to ask as if I am inputting few layers, i.e. soil type layer, DEM Layer, Landuse Layer and also some excel file data for the rainfall and water level. can it be done this way?
Thank you so much for your answer.
- Badges
- Science topic
- Similar topics
- Geoscience
- Geoinformatics
- Geographic Information System