Rainfall forecasting is very challenging due to its uncertain nature and dynamic climate change. It's always been a challenging task for meteorologists. In various papers for rainfall prediction, different Data Mining and Machine Learning (ML) techniques have been used. These techniques show better predictive accuracy. A deep learning approach has been used in this study to analyze the rainfall data of the Karnataka Subdivision. Three deep learning methods have been used for prediction such as Artificial Neural Network (ANN) - Feed Forward Neural Network, Simple Recurrent Neural Network (RNN), and the Long Short-Term Memory (LSTM) optimized RNN Technique. In this paper, a comparative study of these three techniques for monthly rainfall prediction has been given and the prediction performance of these three techniques has been evaluated using the Mean Absolute Percentage Error (MAPE%) and a Root Mean Squared Error (RMSE%). The results show that the LSTM Model shows better performance as compared to ANN and RNN for Prediction. The LSTM model shows better performance with mini-mum Mean Absolute Percentage Error (MAPE%) and Root Mean Squared Error (RMSE%).

Agriculture is the primary component of the Indian economy. It is the primary source of food supply and is essential to our livelihoods. The majority of Indians rely on agriculture for their employment. Agriculture production declines as a result of unpredictable weather, wrong selection of crops, unbalanced fertilizer use, and a lack of market awareness. Farmers face numerous challenges in traditional farming, and many times, farmers fail to select the appropriate crop for cultivation. Crop growth is affected by a variety of factors such as weather, soil parameters, and fertilizers. A crop recommendation system is proposed in this paper to assist farmers in selecting the appropriate crop based on the location, weather data, crop sowing season, and soil parameter. Various Machine Learning techniques, such as Decision Tree (DT), Random Forest (RF), Gaussian Naive Bayes, and XGBoost Classifier methods, were used for recommendation.The XGBoost classifier gives the best results with a 97% accuracy, hence the final model was developed using the XGBoost classifier. This system will help farmers in selecting the best crop for their fields while increasing agricultural yield.

With the growth in population, traffic congestion and parking have become a serious problem. There is the explosive growth of the per capita amount of vehicles. In this paper, a Location-Based Shared Smart Parking System is proposed to solve the parking problem. This system is designed for both private and public parking areas. This system helps the user to find the nearest possible parking area and gives the information related to the availability of parking slots in that respective parking area. The main focus of this system is to reduce the time for finding the parking slot and also avoids unnecessary travelling through occupied parking slots in a parking area. The proposed system is designed using IoT technology, WSN(IR sensors), QR code and RFID technology. IR sensors are used to detect the presence of the car in the parking slot and QR code is used to authenticate the user in the public parking area, RFID technology is used to authenticate the user in private parking area. The system is expected to reduce traffic problems, fuel consumption which results in reduces carbon footprints in an atmosphere.