I'm new to machine learning, and I have been trying to figure out how to apply neural network to rainfall forecasting. I have found resource related to my query, but I seem to still be a bit lost. I think a basic explanation without too much detail would help.

Let's say I have 10 climate features values for each month over a few years, and I want to predict rainfall for new month. How I can apply neural network to this problem is what I am trying to find out. How can I give input in this because we have 10(features) * 12 months * 10 years.

  • $\begingroup$ i want to apply ann $\endgroup$
    – divya
    Mar 13 '13 at 16:51
  • $\begingroup$ What resources have you found? Why don't you list them? How did you decide on using a Neural Network? I think your question's too vague and broad. $\endgroup$ Mar 13 '13 at 16:57

One paper you definitely ought to read is:

Williams, P. M., "Modelling Seasonality and Trends in Daily Rainfall Data", ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS, 1998, volume 10, pages 985-991 MORGAN KAUFMANN PUBLISHERS, ISSN 1049-5258.

For representing the input, I would suggest you read a good book on neural network techniques before you begin. The book by Chris Bishop on "Neural Networks for Pattern Recognition" is excellent, it focusses mainly on pattern recognition, but most of the issues apply equally to regression problems.

  • 1
    $\begingroup$ Do you mean Chris Bishop's book Neural Networks for Pattern Recognition? $\endgroup$
    – Sycorax
    Apr 5 '15 at 15:55
  • $\begingroup$ yes, that is the one, I've edited my answer, thanks. $\endgroup$ Apr 6 '15 at 11:19

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.