Air pollution remains one of the most serious threats to environmental sustainability and public health, with particulate matter $PM_{2.5}$ and $PM_{10}$ among the most hazardous pollutants. High levels of these particles are closely linked to respiratory and cardiovascular disorders, which greatly increase mortality rates worldwide. With population, $PM_{2.5}, PM_{10}$, and mortality due to particulate matter as important variables, a mathematical model is created in this study to examine the dynamics of air pollution and its effects on human health. To better represent the intricate and unpredictable nature of air pollution dynamics, the suggested model is examined under deterministic, fractional-order, and stochastic formulations. The Caputo derivative is used to add memory effects into the fractional-order model, while stochastic differential equations are used to account for environmental variability. The model's well-posedness is proven, and the fractional-order system's boundedness and stability are investigated. Asymptotic behavior and isoclines are used to examine the viability of equilibrium states. The Milstein scheme for the stochastic system and the Adams–Bashforth–Moulton (ABM) approach for the fractional model are used in numerical simulations. Sensitivity analysis is carried out to assess the impact of model parameters. To improve predictive power, machine learning and time-series forecasting methods are combined, such as the Random Forest regressor and ARIMA model. Particulate matter concentrations show varying but consistent trends over time, while population and pollution-related mortality continue to rise, according to the forecasted data. Both short-term fluctuations and the long-term dynamics of the system are successfully captured by the hybrid forecasting framework, which also increases prediction accuracy. All things considered, the suggested method offers a thorough analytical and computational framework for comprehending the relationship between particulate matter, air pollution, and health effects, providing insights that can help legislators create efficient pollution mitigation plans.
This study explores the interconnection between the variables of ChatGPT usage, energy consumption, water consumption, and carbon dioxide CO2 emissions. A new integer and fractional order model using the Caputo derivative is proposed to comprehend the long-term dependencies of these variables. Boundedness, and global and local stability are examined for the fractional order model. The equilibrium points of these variables are shown to determine the stability of the model. The Runge–Kutta 7 numerical method is employed for the integer order model, whereas the semi-implicit linear interpolation (L1) method is used for the fractional order model. The parameter sensitivity is conducted on the system’s parameters to understand the variables’ impact by varying the relevant parameters for the system. To increase the efficacy of our analysis, we used machine learning approaches to model and predict the dynamics of CO2 emissions, energy and water consumption, and ChatGPT usage. The Prophet ML model stood out among the other methods because it is adept at identifying long-term growth trends, seasonal changes, and the impact of outside variables in intricate time-series data. It is extremely beneficial for research centered on sustainability, where accurate projections are essential for wellinformed decision-making, because it can produce robust, interpretable forecasts against missing values and outliers. Using the Prophet ML model, our research guarantees precise and expandable predictions and provides valuable information that can direct tactics to balance environmental sustainability and technological progress.