Key points are not available for this paper at this time.
This research looks into how artificial intelligence (AI) and neural networks (NN) can be used to test data for the input and target driven by mathematical models for the amount of CO2 in the air. The analysis is carried out within the framework of the fractal-fractional (FF) operator. The work endeavors to design a mathematical model that accurately replicates the levels of CO2 in response to variables such as human population, forest area, and plantation operations. The paper tries to advance forecasting abilities and establish an enhanced understanding of the intricate dynamics of CO2 by implementing advanced AI techniques and neural networks. The results of this research add toward advancement in the field of climate change studies as they provide important perspectives for the development of effective measures to reduce CO2 emissions, subsequently contributing in the fight against global warming and its related repercussions. The AI portion of the article presents the validation and training process for the population of time series data at 1000 epoch with gradient 5.7782×10−06, μ=0.1 and val fail 0. It shows the model's ability to accurately predict CO2 concentration dynamics described in (1.1).
Khan et al. (Wed,) studied this question.