A high-resolution profile of July precipitation
Climate downscaling is used to produce high-resolution climate profiles useful in climate studies. A previously constructed climate-downscaling neural network (NN) was modified and trained. The NN was then used to create a high-resolution profile of July rainfall for an area in Luzon, Philippines. We present in this paper the precipitation profile obtained and an evaluation of it. The methodology used in its production is also discussed. Validation and error analysis show that the resulting map is a good profile of July precipitation. However, due to the presence of data limitations, less confidence can be placed in the profile of some locations in the map. Performance analysis of the NN used also shows that there is still a need to improve its downscaling ability.