The increasing concentration of atmospheric CO2 since the Industrial Revolution has driven research into subsurface storage as a viable solution. This study focuses on developing machine learning models to estimate net present value and carbon footprint in a combined gas production and CO2 sequestration scenario in shales. The dataset comprised a large set of numerical simulation scenarios, which were run using PSU SHALECOMP, a 3-dimensional, compositional and multiphase simulator, which incorporates an equation of state to capture the effects of pressure and temperature variations. A horizontal production/injection well with multiple hydraulic fractures was modeled using the stimulated reservoir volume approach which represents the volume impacted by hydraulic fractures as well as the induced fractures through the natural fracture network in the reservoir. The results of these scenarios were used to calculate net present value and carbon footprint associated with each scenario. Exploratory data analysis and feature engineering revealed that the net present value is primarily governed by stimulated reservoir volume’s fracture permeability, original gas in place within the stimulated reservoir volume, and injection constraints, whereas the carbon footprint is predominantly controlled by total production duration and injected CO2 volume. Machine learning models were trained to build robust forecasting tools for net present value and carbon footprint. These models revealed that the selected neural network model outperformed multiple linear regression and random forests models in predicting both net present value and carbon footprint, with R2 values of 0.99 and 0.96, respectively, for the testing sets. To further refine these estimates and improve the robustness of predictions, future research should focus on improving the certainty in deterministic and probabilistic estimations of net present value and carbon footprint by gathering more comprehensive data, and conducting detailed analyses of carbon emissions and operational costs. This research represents a significant step toward understanding the economic and environmental implications of CO2 sequestration in shale reservoirs, contributing valuable insights for future developments in this field.
This study presents a machine-learning-guided hydrothermal strategy for optimizing Cobalt-modified ZnFe2O4 (ZF–Co) photocatalysts. Moreover, a novel scalable porous inorganic coating platform compatible with retrofit implementation on existing urban infrastructures was developed for visible-light-driven atmospheric pollutant mitigation. A hydrothermal synthesis database containing 320 experimentally synthesized ZF–Co samples was generated using temperature (120–250 °C), duration (4–24 h), cobalt concentration (0–20 wt%), and urea-to-metal molar ratio (1.8–9) as input variables, while BET specific surface area (SBET) was selected as the optimization target. Linear regression, random forest, and XGBoost models were implemented for prediction and optimization. The optimized ZF–Co photocatalyst was subsequently characterized using BET, XRD, FESEM/EDS, TEM/HRTEM, FTIR, and UV–Vis analyses and incorporated into a porous lithium-silicate-based coating containing dispersant and foaming agents. The coating was deposited onto cementitious substrates and evaluated by continuous-flow photocatalytic degradation of NOx, formaldehyde, and toluene under UV-A and visible-light irradiation, along with wettability, compressive strength, and pull-off adhesion tests. XGBoost achieved the highest predictive accuracy with R2 = 0.947 and RMSE = 4.49 m2 g−1, identifying an optimum synthesis condition of ∼198 °C, ∼6.8 h, ∼12.2 wt% Co, and ∼2.7 urea-to-metal ratio. Experimental validation yielded a maximum SBET of 126.4 m2 g−1 with only ∼3.0% deviation from the predicted value. The optimized coating achieved ∼58% NO conversion and ∼42% total NOx removal under UV irradiation, while visible light still provided ∼37% and ∼28% removal, respectively. Formaldehyde degradation reached ∼94% under UV and ∼79% under visible light, whereas toluene degradation reached ∼61% and ∼37%, respectively. The coating additionally exhibited a hydrophobic transition from ∼31.6°–33.1° to ∼128.4°–129.3°, preserved compressive strength at ∼40 MPa, and achieved pull-off adhesion strengths of ∼2.1–2.65 MPa. Overall, the results establish a foundation for ML-assisted optimization of ferrite photocatalysts and scalable durable photocatalytic coatings for existing urban infrastructures and diverse construction materials without compromising their intrinsic mechanical functionality or durability. All Python codes and the experimental dataset are provided in the Appendix to ensure reproducibility.
Fishing, especially within industrial sectors, is widely recognized as one of the most dangerous occupations in the world, as fishers are exposed to adverse physical and environmental risks. While legal frameworks in Nigeria provide occupational safety and labor protections for industrial fishers, inconsistencies in enforcement and compliance persist. Voluntary sustainability standards (VSS) have been promoted as market-based mechanisms to reduce risks, increase safety compliance, and improve working conditions. Despite their relevance, evidence of their impacts on industrial fisheries remains unclear. This study examines the effects of the Friend of the Sea (FOS) certification program on the occupational safety and working conditions of industrial fishers in Nigeria's Gulf of Guinea, Atlantic Ocean. A mixed methods approach was employed, integrating quantitative surveys with semi-structured interviews with key informant to facilitate triangulation among participants recruited from FOScertified and Business as Usual (BAU) fishing companies. Bivariate analyses revealed that FOS-certified fishers were significantly more likely to have adequate safety equipment (98.0% vs. 74.8%), access to health personnel and emergency services (100% vs. 17.4%), and training opportunities (98.5% vs. 46.8%). Multivariate logistic regression confirmed these associations such that absence of safety equipment was associated with a 0.364 decrease in the probability of FOS certification; no injury history with a 0.291 increase; no exposure to unsafe conditions with a 0.400 increase; and lack of training access with a 0.535 decrease (all p < 0.001). These findings suggest that, despite statutory legal protections in Nigeria, participation of fishing companies in the FOS certification programme may enhance the implementation of safety standards and improve occupational health outcomes among industrial fishers.
Generative artificial intelligence (GenAI) is fundamentally reshaping the planning, development, and execution of advertising campaigns. Despite the growing application of GenAI in advertising and scholarly interest, research findings on the effects of AI-generated ads on consumer-related outcomes are mixed and rapidly evolving. In particular, the extant literature does not provide sufficient insight into how consumers process cognitive (informativeness and credibility) and affective (creativity and entertainment) values delivered by AI-generated advertisements compared with human-generated advertisements. To fill this gap, the present research used two scenario-based experiments to collect data from 405 (study 1) and 602 (study 2) tourists by randomly exposing them to human and AI-generated advertisements. Data was analyzed in two stages. First, tourists' perceptions of advertising values were compared using multivariate analysis of variance (MANOVA), and then the impact of advertising values on outcome variables was measured using structural equation modeling (SEM). The findings indicate that tourists perceive human-generated advertisements as slightly more informative, credible, creative, and entertaining than AI-generated advertisements. However, the SEM results indicate that the effects of advertising values on tourists' self-expression, attitudes toward the destination, and destination evangelism do not differ significantly between the two advertising formats. These findings are particularly noteworthy, as they suggest that advertising values that emerge from AI-generated advertisements positively influence tourists' attitudes and self-expressive responses. Consequently, the results support tourism marketing professionals in strategically leveraging emerging GenAI tools to develop advertising content that fosters favorable destination attitudes, enhances tourists’ self-expression, and ultimately stimulates destination evangelism.
The Khosrow Abad Fe-skarn deposit lies within the Sonqor igneous–sedimentary series of the northern Sanandaj–Sirjan Zone (N-SaSZ), western Iran, where Late Jurassic quartz monzonite–quartz monzodiorite intrusions cut meta-basaltic andesite and dolomitic limestone. Field relationships and petrography are integrated with LA–ICP–MS zircon UPb geochronology, whole-rock geochemistry, and mineral chemistry to constrain magmatism, skarn evolution, and magnetite deposition. To our knowledge, the zircon ages provide the first deposit-specific UPb constraints for the skarn-related intrusions. Weighted mean ages of 148.50 ± 0.48 Ma, 147.91 ± 0.72 Ma, and 146.97 ± 2.49 Ma overlap within analytical uncertainty and define an intrusive episode at ca. 148–149 Ma; they date crystallization rather than mineralization directly. The intrusions are predominantly calc-alkaline and I-type, although hydrothermal alteration locally modified alkali-element distributions. Contact metamorphism and restricted garnet-bearing prograde skarn were followed by widespread hydrous retrograde alteration. The principal magnetite stage accompanied albite–actinolite and epidote–chlorite alteration and was subsequently overprinted by sulfides and oxidation. Ore localization reflects fluid–rock interaction, reactive lithological contacts, and structurally enhanced permeability. Mineral chemistry is evaluated with the observed assemblages and ore textures rather than used as an independent genetic test. The resulting deposit-scale model identifies the wider retrograde alteration footprint and permeable contacts within carbonate–metavolcanic successions as complementary exploration criteria for comparable intrusion-related calcic Fe-skarn systems.
