ABSTRACT :

In India, Agriculture is the key point for survival. For agriculture, rainfall is most important. These days rainfall prediction has become a major problem. Prediction of rainfall gives awareness to people and know in advance about rainfall to take certain precautions to protect their crop from rainfall. Many techniques came into existence to predict rainfall. Machine Learning algorithms are mostly useful in predicting rainfall. Some of the major Machine Learning algorithms are ARIMA Model(Auto-Regressive Integrate d Moving Average), Artificial Neural Network, Logistic Regression, Support Vector Machine and Self Organizing Map. Two commonly used models predict seasonal rainfall such as Linear and Non-Linear models. The first models are ARIMA Model. While using Artificial Neural Network(ANN) predicting rainfall can be done using Back Propagation NN, Cascade NN or Layer Recurrent Network. Artificial NN is same as Biological Neural Networks.

EXISTING SYSTEM :

The achievement of Agriculture is dependent on rainfall. It also helps with water resources. Rainfall information in the past helps farmers better manage their crops, leading to economic growth in the country. Prediction of precipitation is beneficial to prevent flooding that saves people’s lives and property. Fluctuation in the timing of precipitation and its amount makes forecasting of rainfall a problem for meteorological scientists. Forecasting is one of the utmost challenges for researchers from a variety of fields, such as weather data mining, environmental machine learning, functional hydrology, and numerical forecasting, to create a predictive model for accurate rainfall. In these problems, a common question is how to infer the past predictions and make use of future predictions. A variety of sub-processes are typically composed of the substantial process in rainfall. It is at times not promis ing to predict the precipitation correctly by on its global system. Climate forecasting stands out for all countries around the globe in all the benefits and services provided by the meteorological department. The job is very complicated because it needs specific numbers and all signals are intimated without any assurance. Accurate precipitation forecasting has been an important issue in hydrological science as early notice of stern weather can help avoid natural disaster injuries and damage if prompt and accurate forecasts are made. The theory of the modular model and the integrati2on of different models has recently gained more interest in rainfall forecasting to address this challenge. A huge range of rainfall prediction methodologies is available in India. In India, there are two primary methods of forecasting rainfall. Regression, Artificial Neural Network (ANN), Decision Tree algorithm, Fuzzy logic and team process of data handling are the majority frequently used computational methods used for weather forecasting The basic goal is to follow information rules and relationships while gaining intangible and potentially expensive knowledge. Artificial NN is a promising part of this wide field.

PROPOSED SYSTEM  :

In this paper, the rainfall has been predicted using deep learning techniques. Two deep learning techniques which were used are Multilayer Perceptron and Auto-Encoders. Auto -Encoders are responsible in time series forecasting by performing the feature extraction as mentioned in [8] and the MLP is used in prediction and classification tasks. Firstly the auto-encoders extract all the non-linear features from the data. This auto – encoder consists of three layers:

 Input Layer

  Hidden Layer

 Output Layer

The auto-encoder extracts all the non-linear features and then send to MLP, this helps in making a prediction. The performance of methodology is also evaluated by using RMSE(Root MSE) and MSE(Mean Square Error). The architecture in the figure(3) shows how the inputs Of the autoencoder network are connected to the MLP using a sigmoid function

SYSTEM REQUIREMENTS

SOFTWARE REQUIREMENTS:
• Programming Language : Python
• Font End Technologies : TKInter/Web(HTML,CSS,JS)
• IDE : Jupyter/Spyder/VS Code
• Operating System : Windows 08/10

HARDWARE REQUIREMENTS:

 Processor : Core I3
 RAM Capacity : 2 GB
 Hard Disk : 250 GB
 Monitor : 15″ Color
 Mouse : 2 or 3 Button Mouse
 Key Board : Windows 08/10