Olumuyiwa Akintola

Accurate prediction of air pollutant concentrations is essential for environmental policy, public health protection, and early warning systems. In recent years, artificial intelligence (AI) techniques, including machine learning (ML), deep learning (DL), and hybrid models, have significantly improved the forecasting of particulate matter, gaseous pollutants, and real-time Air Quality Index (AQI). This study presents a systematic review of AI applications for predicting air pollutant concentrations, with emphasis on comparing global and Nigeria-specific studies. To ensure methodological consistency and avoid inappropriate comparisons, the analysis was structured according to modelling task: station-level particulate-matter forecasting, satellite-based particulate-matter mapping, and AQI prediction. Results were interpreted descriptively within each category because of differences in datasets, validation strategies, and prediction objectives. Findings show that data availability and monitoring infrastructure strongly influenced model selection and reported performance. Global studies commonly apply more complex ML, DL, and hybrid models using long-term multi-station and multi-source datasets, whereas Nigeria-specific studies rely more on simpler ML approaches because of limited data availability and sparse monitoring networks. Differences in reported performances are therefore linked mainly to data conditions and validation methodology rather than the inherent superiority of any specific algorithm. The study highlights the importance of aligning modelling approaches with available data, improving validation practices, and expanding monitoring infrastructure in data-limited regions. It emphasizes the value of context-specific modelling frameworks and multi-source data integration for evidence-based environmental decision-making. Beyond synthesis of existing literature, the study further contributes to a context-aware analytical framework for interpreting and applying AI models for air-quality prediction.

Anthocyanins are naturally occurring polyphenolic pigments with valuable chromatic, antioxidant, and analytical properties. This study optimized the extraction of anthocyanins from Hibiscus sabdariffa L. calyces and characterized them using low-cost chromatographic and spectroscopic techniques. Methanol proved superior to ethanol as an extraction solvent, yielding 12.4 ± 0.6% crude extract by dry calyx weight, with excellent pigment stability over 72 hours at 4 °C. Total anthocyanin content, determined via the pH differential method, was 185.6 ± 4.2 mg cyanidin -3-glucoside equivalents per 100 g dry calyces. Thin-layer chromatography (TLC) revealed a predominant band with Rf = 0.93 ± 0.02 in the crude extract, with systematic pH-dependent shifts from 0.55 ± 0.06 at pH 1 –3 to 0.38 ± 0.04 at pH 12 – 14, corresponding to flavylium, carbinol, chalcone, and quinoidal forms. Colorimetric evaluation demonstrated reproducible transitions from pink (pH 1 – 3) to faint pink/light color (pH 4 – 7) and green hues (pH 8 – 14), confirming the potential of these pigments as natural pH indicators. UV – visible spectroscopy revealed a characteristic absorption maximum around 520 nm under acidic conditions, with absorbance values ranging from 0.451 ± 0.012 (pH 1) to 0.734 ± 0.015 (pH 2), decreasing at neutral pH and partially recovering under alkaline conditions. These results demonstrate that simple solvent extraction combined with TLC and UV – visible spectroscopy provides an effective framework for the quantitative and qualitative analysis of roselle anthocyanins, supporting their application in food, sensor, and educational settings.

Fuel produced by artisanal refiners using indigenous technology continues to find its way into the Nigerian oil market despite the proscription of such refining activities in the Niger Delta, owing largely to the illegal means by which the artisans procure crude oil and also related to doubt about the quality of products coming from their covertly operated facilities. Therefore, in this study, gasoline samples were collected across 30 artisanal refiner camps, and their properties were examined to ascertain their conformity with the minimum requirements of the Standard Organisation of Nigeria (SON) and the American Society for Testing and Materials (ASTM) on fuel quality. Standard test protocols on fuel characterisation published by ASTM were utilised for the analysis. The specific gravity of the samples determined at 15℃ ranged from 0.796 – 0.807 g/cm3. The Antiknock Index ranged between 78.75% and 82.45% for the fuel, and the initial and final boiling points of the samples were about 32 – 39.1℃ and 226.3 – 238.7℃, respectively. The distillation profiles of most of the fuel samples were satisfactory. Experimental data gathered from this study indicate that notwithstanding the artisanal refiners’ shortcomings, they are still able to produce fuels that meet some minimum local and international requirements

This study developed mathematical modeling equations for the interactions between outdoor electric power generator air emissions and indoor receptors location. It also describes a numerical solution for the transportation of air pollutants in a simple rectangular box domain. The mathematical model of indoor pollution from electric power generators operated near buildings using one-dimension advection and one-dimension diffusion was solved numerically. The finite difference method was used in solving the model with respect to advection term only, diffusion term only and both advection and diffusion terms. The numerical solution of this equation were obtained using the Crank-Nicolson scheme and by implementing the numerical scheme via developing computer programming codes of Crank-Nicolson scheme for advection and/or diffusion equation. The results from the concentration profiles of advection term only and diffusion term only show that the concentrations of air pollutants decrease with time and remains constant at a point, this differs when both terms are considered together. Finally, governing equations with solution of concentrations varying with time and space can be established for air emissions from outdoor electric power generators operated near buildings with their associated effects on indoor air quality.