Big Data Analytics Using Swarm-Based Long Short-Term Memory for Temperature Forecasting

In the past few decades, climatic changes led by environmental pollution, emittance of greenhouse gases, and emergence brown energy utilization have to global warming. Global warming increases Earth's temperature, thereby causing severe effects on human conditions threatening livelihoods millions people. issues are increase in temperatures that lead heat strokes high-temperature-related diseases during summer, untimely death thousands To forecast weather conditions, researchers utilized machine learning algorithms, such as autoregressive integrated moving average, ensemble learning, long short-term memory network. These techniques been widely used for prediction temperature. this paper, we present a swarm-based approach called Cauchy particle swarm optimization (CPSO) find hyperparameters (LSTM) The were determined minimizing LSTM validation mean square error rate. optimized temperature Chennai City. proposed CPSO-LSTM model was tested openly available 25-year dataset. experimental evaluation MATLABR2020a analyzed root rate absolute evaluate forecasted output. outperforms traditional algorithm reducing its computational time 25 min under 200 epochs 150 hidden neurons training. hyperparameter-based can predict accurately having (RMSE) value 0.250 compared with 0.35 RMSE.