Feature Selection of PERSIANN, based on Multiple Regression Analysis with Principal Component Analysis & Using Three-Cornered Hat method to evaluate Precipitation products
- Author(s): Akbari Asanjan, Ata
- Advisor(s): Sorooshian, Soroosh
- Gao, Xiaogang
- et al.
My thesis addresses two aspects of satellite precipitation estimation. In the first chapter,
feature selection aspect of PERSIANN algorithm will be discussed. In the second chapter,
the Generalized Three-Cornered Hat method is used for intercomparison of PERSIANN-CDR and TRMM and CRU datasets over Iran. For this part, a part of author’s collaboration with Professor Katiraie of Azad University, Tehran (Corresponding author: KatiraieBoroujerdy) will be represented. Chapter three presents the summary and conclusions.
The PERSIANN model is an Artificial Neural Network-based (ANN) model for precipitation
estimation using satellite information, and the datasets generated by it have gained
popularity for application in both weather and climate studies. Research related to the
PERSIANN system is ongoing, and it mainly focuses on improving its accuracy required for various applications. One of these improvements in the system includes the input feature selection of the model which can help the Neural Network to better learn the precipitation pattern by adding more relevant information. The Multiple Regression Analysis (MRA), by taking the advantage of Principal Component Analysis (PCA) to solve the collinearity is employed as the framework for ranking those features or inputs that are most useful for the learning process.
Later on, to evaluate how well the algorithm is doing, a reliable in-situ observation set is
required in order to test and compare the satellite-based observations. Often we are
challenged with lack of availability of adequate reference ground-based observations. This
became the motivation to come up with a creative and reliable method to compare any
datasets regarding the precipitation characteristics. In order to do that, the use of
Generalized Three-Cornered Hat (GTCH) for comparing the reliability of each dataset
without having a reference is presented in chapter two. Using this method has enabled us
to compare at least three datasets in order to compare them in spatial resolution.