Estimation of Rainfall Quantity using Hybrid Ensemble Regression

Rainfall analysis and prediction using ensemble learning for Karnataka State

“…Their study found that due to the non-linear connections in rainfall datasets and ANN model's ability to learn from the past, they provide a superior solution than all existing technologies. Ganesh et al [3] created a composite ensemble regression model by combining bagging regression (BAR), extra tree regression (ETR), random forest regression (RFR), gradient boosting regression (GBR), and extreme gradient boosting regression (XGBoostR). Consequently, these ensemble regression models, in which two or more models are implemented in various combinations, are used to predict precipitation instead of features.…”

“…Figure 13. Model stacking with ensemble layers GBR builds a weak ensemble prediction model similar to other boosting techniques [3]. Chen et al [24] proposed XGBoost based on the gradient boosting paradigm.…”

“…Researchers have proposed many rainfall prediction techniques, most of which use random numbers and resemble climatic data [2]. For predicting rainfall, researchers typically adopt classification or regression techniques [3]. Fuzzy logic, decision tree (DT) algorithm, regression, artificial neural network (ANN) along with data manipulation techniques are some computing methods used for weather forecasting [1].…”

“…Fuzzy logic, decision tree (DT) algorithm, regression, artificial neural network (ANN) along with data manipulation techniques are some computing methods used for weather forecasting [1]. ANN is often used to forecast rainfall [2], [3]. Long shortterm memory (LSTM), a recurrent neural network (RNN) version, is applied for both short-and long-term forecasting.…”