Rainfall Prediction using Machine Learning and Deep Learning Algorithms 
B.Meena Preethi1, R.Gowtham2, S.Aishvarya3, S.Karthick4, D.G.Sabareesh5
1B.Meena Preethi, Department of Computer Science, Sri Krishna Arts and Science College, Coimbatore (Tamil Nadu), India.
2R.Gowtham*, PG Scholar, Department of Computer Science, Sri Krishna Arts and Science College, Coimbatore (Tamil Nadu), India.
3S.Aishvarya, PG Scholar, Department of Computer Science, Sri Krishna Arts and Science College, Coimbatore (Tamil Nadu), India.
4S.Karthick, PG Scholar, Department of Computer Science, Sri Krishna Arts and Science College, Coimbatore (Tamil Nadu), India.
5D.G.Sabareesh, PG Scholar, Department of Computer Science, Sri Krishna Arts and Science College, Coimbatore (Tamil Nadu), India.
Manuscript received on November 16, 2021. | Revised Manuscript received on November 22, 2021. | Manuscript published on November 30, 2021. | PP: 251-254 | Volume-10 Issue-4, November 2021. | Retrieval Number: 100.1/ijrte.D66111110421 | DOI: 10.35940/ijrte.D6611.1110421
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The project entitled as “Rainfall Prediction using Machine Learning & Deep Learning Algorithms” is a research project which is developed in Python Language and dataset is stored in Microsoft Excel. This prediction uses various machine learning and deep learning algorithms to find which algorithm predicts with most accurately. Rainfall prediction can be achieved by using binary classification under Data Mining. Predicting the rainfall is very important in several aspects of one’s country and can help from preventing serious natural disasters. For this prediction, Artificial Neural Network using Forward and Backward Propagation, Ada Boost, Gradient Boosting and XGBoost algorithms are used in this model for predicting the rainfall. There are totally five modules used in this project. The Data Analysis Module will analyse the datasets and finding the missing values in the dataset. The Data Pre-processing includes Data Cleaning which is the process of filling the missing values in the dataset. The Feature Transformation Module is used to modify the features of the dataset. The Data Mining Module is used to train the dataset to models using any algorithm for learning the pattern. The Model Evaluation Module is used to measure the performance of the model and finalize the overall best accuracy for the prediction. Dataset used in this prediction is for the country Australia. This main aim of the project is to compare the various boosting algorithms with the neural network and find the best algorithm among them. This prediction can be major advantage to the farmers in order to plant the types of crops according to the needy of water. Overall, we analyse the algorithm which is feasible for qualitatively predicting the rainfall.
Keywords: Machine learning, Deep learning, Adaboost, Gradient Boosting, XGBoost, ANN