Short-term Quantitative Precipitation Forecasting is important for aviation and navigation safety control, flood forecasting, early flood warning, and natural hazard management. Obtaining accurate and timely precipitation forecasts in short range of time (0-6 hours) is a challenging task. Addressing the challenges in forecasting accurate short-term rainfall is an open question in the field of hydrometeorology and is a major objective. This dissertation introduces a machine learning, in specific deep learning, framework to accurately forecast high- and low-intensity precipitation events. In details, this dissertation introduces an effective precipitation forecasting framework by (1) developing an infrared cloud-top brightness temperature forecasting model, and (2) proposing an effective infrared to rainfall intensity mapping model using satellite and radar data. The proposed framework is effective due to(1) solving a physical problem using a continuous infrared data in which evolution is dominated by the continuity law of heat transfer, (2) providing forecasts for various ranges of rainfall intensities, and (3) introducing a framework with potentials to become a

quasi-global scale product. As the initial attempt to develop the precipitation forecasting model, a forecasting model was proposed by extrapolating infrared imageries using an advanced Deep Neural Network (DNN) and applying the forecasted infrared into an effective rainfall retrieval algorithm to obtain the short-term precipitation forecasts. To achieve such tasks, we propose a Long Short-Term Memory (LSTM) and the Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN), respectively. The precipitation forecasts obtained from LSTM combined with PERSIANN were compared with a Recurrent Neural Network (RNN), Persistency method, and Farnebackoptical flow each combined with the PERSIANN algorithm and the numerical model results from the first version of Rapid Refresh (RAPv1.0) over three regions in the United States, including the states of Oregon, Oklahoma, and Florida. Furthermore, to improve the forecasting skills of the proposed method, a new infrared forecasting method was developed by improving the LSTM model (such as efficient use of neighborhood pixel information, resolving the loss of resolution problem and introducing more efficient objectives compared to maximum likelihood estimates). The new proposed infrared forecasting algorithm is a semi-conditional Generative AdversarialNetwork (GAN) consisting of convolutional, recurrent (LSTM) and convolutional-recurrent (ConvLSTM) layers in order to forecast temporally and spatially coherent infrared images. The results are compared with the non-adversarial version of the proposed model and demonstrate superior performances. In addition to this precipitation forecasting improvement step, a new precipitation estimation algorithm is introduced to replace the PERSIANN algorithm in order to increase the infrared-rainfall translation accuracy and enable the framework to become an end-to-end model. The new precipitation estimation model is a conditional GAN, termed as PERSIANN-GAN, which translates 0.25◦×0.25◦ infrared data into same resolution precipitation estimates by defining a more flexible objective function. The PERSIANN-GAN results are compared with two Convolutional Neural Networks (CNNs) baseline models one without adversarial part and with bypass connections and the other one without adversarial part and without bypass connections. The model performances were also compared to the well-known operational PERSIANN product. The comparison results demonstrate higher visual and statistical performances of PERSIANN-GAN.

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.