RAINFALL PREDICTION USING MACHINE LEARNING …

1 RAINFALL PREDICTION USING MACHINE LEARNING TECHNIQUES A THESIS SUBMITTED TO THE GRADUATE SCHOOL OF APPLIED SCIENCES OF NEAR EAST UNIVERSITY By ZANYAR RZGAR AHMED In Partial Fulfillment of the Requirements for the Degree of Master of Science in COMPUTER ENGINEERING NICOSIA, 2018 ZANYAR RZGAR RAINFALL PREDICTION USING MACHINE NEU AHMED LEARNING TECHNIQUES 2018 RAINFALL PREDICTION USING MACHINE LEARNING TECHNIQUES A THESIS SUBMITTED TO THE GRADUATE SCHOOL OF APPLIED SCIENCES OF NEAR EAST UNIVERSITY By ZANYAR RZGAR AHMED In Partial Fulfillment of the Requirements for the Degree of Master of Science in Computer Engineering NICOSIA, 2018 Zanyar Rzgar Ahmed: RAINFALL PREDICTION USING MACHINE LEARNING TECHNIQUES Approval of Director of Graduate School of Applied Sciences Prof.

2 Dr. Nadire Cavus We certify this thesis is satisfactory for the award of the degree of Master of Science in Computer Engineering Examining Committee in Charge: Assoc. Prof. Dr. Melike Sah Direkoglu Department of Computer Engineering, NEU Assist. Prof. Dr. Kamil Dimililer Department of Automotive Engineering, NEU Prof. Dr. Rahib H. Abiyev Supervisor, Department of Computer Engineering, NEU I hereby declare that all information in this document has been obtained and presented in accordance with academic rules and ethical conduct. I also declare that, as required by these rules and conduct, I have fully cited and referenced all material and results that are not original to this work. Name, Last name: Zanyar Rzgar Ahmed Signature: Date: To my ii ACKNOWLEDGEMENTS I am grateful and obliged wholeheartedly to Prof. Dr. Rahib Abiyev for his great supervision, assistance, tolerance and persistence throughout my thesis at Near East University.

3 His advice and guidance were the key to success and not only helped me academically but I learnt a lot about sociology as well. The supervision of the supervisor helped me to long way since I first started. He not only motivated me to portray the research skills through the thesis but also been a role model for me. This opportunity to develop and write a thesis is not only very honourable for me but also their presence in the focus, it is always essential to carry out such independent studies to move beyond success and prosperity in their life. I am grateful to my parents and family, especially my elder brother Dr. Ramyar Ahmed who has always supported me on every step. He has always been sympathetic and caring. Also, to my friend Sabeel who assisted me throughout the research. I am also thankful to the NEU Grand Library administration, as it encouraged an appropriate and motivating study environment that helped me to stay consistent and aligned with my study.

4 Iii ABSTRACT This study seeks a distinctive and efficient MACHINE LEARNING system for the PREDICTION of RAINFALL . The study experimented with different parameters of the RAINFALL from Erbil, Nicosia and Famagusta in order to assess the efficiency and durability of the model. The neuro-fuzzy and neural networks model is focused on this study. The LEARNING of data is completed USING hybrid and backpropagation network algorithm. The RAINFALL parameters in this study are collected, trained and tested to achieve the sustainable results through ANFIS and ANN models. The monthly RAINFALL predictions obtained after training and testing are then compared with actual data to ensure the accuracy of the model. The results of this study outline that the model is successful in predicting the monthly RAINFALL data with the particular parameters. The training and testing of data through neuro-fuzzy model helped in not only minimizing the errors up to RMSE of , and , but also maximizing the reliability and durability of the predicted data.

5 The results of the study highlight that the ANFIS model is most suitable among the artificial networks for the RAINFALL PREDICTION . The outcome data with ANFIS system presented maximum accuracy with minimum error through the comparison between the actual data and predicted outcome data. Keywords: MACHINE LEARNING ; neuro-fuzzy; neural networks; parameters; RAINFALL PREDICTION iv ZET Bu al ma, ya tahmininde ay rt edici ve etkili bir makine renimi sistemi istemektedir. al ma, modelin etkinli ini ve dayan kl l n de erlendirmek i in Erbil, Lefko a ve Ma usa'ndan gelen ya lar n farkl parametreleri ile deney yapm t r. N ron bulan k ve sinir a lar modeli bu al maya odaklanm t r. Verilerin renilmesi melez ve geri yay l m a algoritmas kullan larak tamamlanm t r. Bu al madaki ya parametreleri ANFIS ve ANN modelleri ile s rd r lebilir sonu lar n elde edilmesi i in toplanm , e itilmi ve test edilmi tir.

6 Daha sonra, e itim ve testten sonra elde edilen ayl k ya tahminleri, modelin do rulu unu sa lamak i in ger ek verilerle kar la t r l r. Bu al man n sonu lar , modelin ayl k ya verilerini belirli parametrelerle tahmin etmede ba ar l oldu unu g stermektedir. N ronal bulan k model arac l yla verilerin e itimi ve test edilmesi, yaln zca , ve RMSE hatalar n en aza indirmenin yan s ra tahmin edilen verilerin g venilirli ini ve dayan kl l n en st d zeye karmada yard mc oldu. al man n sonu lar , ya tahmini i in yapay a lar aras nda ANFIS modelinin en uygun oldu unu g stermektedir. ANFIS sistemi ile elde edilen sonu verileri, ger ek verilerle tahmin edilen sonu verileri aras ndaki kar la t rma yoluyla minimum hata ile maksimum do rulu a sahiptir. Anahtar Kelimeler: makine renimi; N ro-bulan k; n ral a lar; parametreler; ya tahmini v TABLE OF CONTENTS ACKNOWLEDGEMENTS .. ii ABSTRACT.

7 Iii ZET .. iv TABLE OF CONTENTS .. v LIST OF FIGURES .. viii LIST OF TABLES .. xi LIST OF ABBREVIATIONS .. xii CHAPTER 1: INTRODUCTION .. 1 Aim of the Study .. 3 Significance of Study .. 3 Limitations of the Study .. 4 Problem Statement .. 4 Methodology .. 4 The Study region and data .. 4 Overview of the 5 CHAPTER 2: LITERATURE REVIEW .. 6 CHAPTER 3: RAINFALL .. 10 Introduction to RAINFALL .. 10 Types of 12 Conventional precipitation .. 12 Orographic RAINFALL .. 13 Cyclonic or frontal RAINFALL .. 14 vi Measurement of RAINFALL .. 15 Ordinary rain Gauge .. 15 Self-recording rain Gauge .. 15 Zonal distribution of 16 Regime of 17 Equatorial RAINFALL 17 Tropical RAINFALL regime .. 17 Monsoon RAINFALL regime .. 18 Mediterranean RAINFALL regime .. 18 Continental RAINFALL 19 Maritime RAINFALL regime .. 19 CHAPTER 4: MACHINE LEARNING TECHNOLOGIES .. 20 Introduction to MACHINE LEARNING .. 20 Artificial neural 20 Neurons.

8 21 Structure of ANN .. 21 22 Feedforward neural network .. 22 Backpropagation algorithm .. 23 Nonlinear autoregressive exogenous model (NARX) .. 23 Adaptive Neuro-Fuzzy Inference system .. 24 ANFIS architecture .. 24 Hybrid LEARNING algorithm .. 27 CHAPTER 5: SIMULATION .. 28 Data processing .. 28 Data Pre-Processing for Erbil .. 31 Data Pre-Processing for Nicosia .. 36 Data Pre-Processing for Famagusta .. 41 Flowchart for RAINFALL PREDICTION .. 46 vii Selection of the input and output data .. 47 Feature Extraction .. 48 Training, Testing and Validation .. 49 ANN .. 49 Applying backpropagation and NARX model for Erbil .. 49 Applying backpropagation and NARX model for Nicosia .. 53 Applying backpropagation and NARX model for Famagusta .. 56 ANFIS .. 58 Applying ANFIS for 59 Applying ANFIS for Nicosia .. 60 Applying ANFIS for Famagusta .. 61 CHAPTER 6: DISCUSSION AND 65 Comparing results .. 65 Actual and predicted data for Erbil.

9 66 Actual and predicted data for Nicosia .. 67 Actual and predicted data for Famagusta .. 69 CONCLUSION .. 71 REFERENCES .. 72 APPENDICES .. 79 APPENDIX A: DATABASE FOR ERBIL .. 80 APPENDIX B: DATABASE FOR NICOSIA .. 81 APPENDIX C: DATABASE FOR FAMAGUSTA .. 83 viii LIST OF FIGURES Figure : Heavy and unstable clouds of conventional RAINFALL .. 12 Figure : Wave cloud formation on Amsterdam Island in the far Southern Indian Ocean .. 13 Figure : Cyclonic RAINFALL cloud formation .. 14 Figure : Neuron scheme .. 21 Figure : Structure of ANN .. 22 Figure : ANFIS architecture .. 25 Figure : Map of Iraq; (a) Erbil (b) focus area of this study (north Iraq) .. 29 Figure : Map of Northern Cyprus; showing Nicosia and Famagusta .. 30 Figure : Trends in the distribution of RAINFALL for Erbil .. 31 Figure : Monthly average temperature for Erbil .. 32 Figure : Trends in humidity for Erbil .. 32 Figure : Average wind speed for Erbil .. 33 Figure : Correlation between humidity and RAINFALL for Erbil.

10 33 Figure : Correlation between temperature and RAINFALL for Erbil.. 34 Figure : Correlation between wind direction and RAINFALL for Erbil .. 34 Figure : Correlation between wind speed and RAINFALL for Erbil.. 35 Figure : Trends in distribution of RAINFALL for Nicosia .. 37 Figure : Average temperature for Nicosia .. 37 Figure : Trends in humidity for 38 Figure : Trends in wind speed for Nicosia .. 38 Figure : Trends in average air pressure for Nicosia .. 39 Figure : Trends in wind direction for Nicosia .. 39 ix Figure : Correlation for RAINFALL with humidity and temperature .. 40 Figure : Correlation for RAINFALL with wind direction and RAINFALL with wind speed .. 40 Figure : Trends in distribution of RAINFALL in Famagusta .. 42 Figure : Average temperature for Famagusta .. 42 Figure : Trends in humidity for Famagusta .. 43 Figure : Trends in average wind speed for Famagusta .. 43 Figure : Average wind direction for Famagusta .. 44 Figure : Trends in average air pressure for Famagusta.