Time Series based Air Temperature forecasting based on the Outlier Robust Extreme Learning Machine

One of humanity's greatest and most significant challenges facing humanity is climate change mitigation. Despite the existing challenges in forecasting climate change effects on Earth, there is scientific agreement on its detrimental consequences. The climate change effects have been identified as adversely affecting ecosystems, soil erosion, reducing biodiversity, rising sea levels, extreme temperature changes, and global warming. Additionally, a significant impact is expected on food security, human health, energy consumption, and the economy. Forecasting air temperatures, in particular, has become an increasingly crucial climatic aspect in many fields, including tourism, energy, agriculture, industry, tourism and so on. There are several applications for air temperature forecasting, including forecasting cooling and energy consumption for residential buildings, controlling greenhouse temperatures adaptively, and predicting natural hazards. As a result, there is a need to reliably anticipate air temperature since they would assist in a planning horizon for constructing a business development, an energy policy, an insurance policy, and infrastructure upgrades when combined with the stud analysis of additional elements in the topic of interest. This research aims to develop a novel technique and explore the potential of new data intelligent models based on the optimally pruned extreme learning machine (OPELM) to predict the hourly air temperature in Quebec City, Canada. OPELM is a new development of the Extreme Learning Machine (ELM). It is a new non-tuned rapid algorithm for single-layer feed-forward neural networks. Different lags are selected as the input parameters, and various models are defined based on the time series concept. The performance of the OPELM is also compared with the ELM.