Air quality prediction by machine learning models: A predictive study on the indian coastal city of Visakhapatnam.

Clean air is critical component for health and survival of human and wildlife, as atmospheric pollution is associated with a number of significant diseases including cancer. However, due to rapid industrialization and population growth, activities such as transportation, household, agricultural, and industrial processes contribute to air pollution. As a result, air pollution has become a significant problem in many cities, especially in emerging countries like India. To maintain ambient air quality, regular monitoring and forecasting of air pollution is necessary. For that purpose, machine learning has emerged as a promising technique for predicting the Air Quality Index (AQI) compared to conventional methods. Here we apply the AQI to the city of Visakhapatnam, Andhra Pradesh, India, focusing on 12 contaminants and 10 meteorological parameters from July 2017 to September 2022. For this purpose, we employed several machine learning models, including LightGBM, Random Forest, Catboost, Adaboost, and XGBoost. The results show that the Catboost model outperformed other models with an R2 correlation coefficient of 0.9998, a mean absolute error (MAE) of 0.60, a mean square error (MSE) of 0.58, and a root mean square error (RMSE) of 0.76. The Adaboost model had the least effective prediction with an R2 correlation coefficient of 0.9753. In summary, machine learning is a promising technique for predicting AQI with Catboost being the best-performing model for AQI prediction. Moreover, by leveraging historical data and machine learning algorithms enables accurate predictions of future urban air quality levels on a global scale.

Artificial intelligence enabled carbon capture: A review.

Carbon capturing is imperative to fight climate change as much carbon emissions are liberated into the atmosphere, leading to adversely negative environmental impacts. Today's world addresses all the issues with the aid of digital technologies like data pooling and artificial intelligence (AI). Accordingly, this study is articulated based on AI-assisted carbon capturing. Techniques including machine learning (ML), deep learning (DL), and hybrid techniques being adopted in carbon capture are discussed. The role of AI tools, frameworks, and mathematical models are also discussed herein. Furthermore, the confluence of AI in carbon capture patent landscape is explored. This study would allow researchers to envision the growth of AI-assisted carbon capture in mitigating climate change and meeting SDG 13 - climate action.

Soft computing-based models and decolorization of Reactive Yellow 81 using Ulva Prolifera biochar.

The present research explores the application of optimization tools namely Response Surface Methodology (RSM), Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) in the decolorization of Reactive Yellow 81 (RY81) from an aqueous solution. The characterization of the biochar was carried out using FTIR, elemental analysis, proximate analysis, BET analysis and Thermogravimetric analysis. Five independent variables namely solution pH, biochar dose, contact time, initial dye concentration and temperature were analyzed using RSM, ANN and ANFIS models. The maximum removal efficiency of 86.4% was obtained and the statistical error analysis was calculated. The correlation coefficient of 0.9665, 0.9998 and 0.9999 was obtained for RSM, ANN and ANFIS models, respectively. Adsorption Isotherm models and kinetic models were used to understand the adsorption mechanism. Maximum monolayer adsorption of 225 mg g-1 was predicted by Hill isotherm model. A partition coefficient of 4.09 L g-1 was obtained at an initial dye concentration of 250 mg L-1. It was revealed from the thermodynamic studies that reactions are endothermic and spontaneous. Further, to check the potential of the biochar, regeneration cycle was studied. The desorption efficiency of 99.5% was achieved at an S/L ratio of 3, regeneration cycles of 2, and sodium hydroxide was found as the best elutant for the desorption.

Towards sustainable biodiesel production by solar intensification of waste cooking oil and engine parameter assessment studies.

Renewable energy sources for harnessing biofuels are the viable solution to substitute fossil fuels and reduce production cost. In this study, waste cooking oil was converted into biodiesel via a customized solar reactor. The solar reactor was customized using copper tubes and black surface to trap solar energy for conversion of waste cooking oil into biodiesel. The main experimental parameters studied are temperature (30 to 50 °C), stirring speed (100 to 500 rpm), catalyst loading (0.25 to 1.25 wt%), flow rate (3 to 15 LPH), and methanol to oil ratio (3:1 to 15:1), respectively. The uppermost conversion of 82% was achieved at catalyst load of 0.75 wt%, stirring speed of 300 rpm, flow rate of 3 LPH and methanol/oil ratio of 12:1. Performance of biodiesel blend (D80 + BD20) in CI engine showed a decrease in ignition delay (10.5 deg. CA) and brake thermal efficiency (32.7%) at maximum load (100%). Smoke emission was also decreased with an increase in biodiesel blend at lower brake power, but an increase in brake power increased the smoke emission.

Environmentally benign solid catalysts for sustainable biodiesel production: A critical review.

Versatile bio-derived catalysts have been under dynamic investigation as potential substitutes to conventional chemical catalysts for sustainable biodiesel production. This is because of their unique, low-cost benefits and production processes that are environmentally and economically acceptable. This critical review aspires to present a viable approach to the synthesis of environmentally benign and cost-effective heterogeneous solid-base catalysts from a wide range of biological and industrial waste materials for sustainable biodiesel production. Most of these waste materials include an abundance of metallic minerals like potassium and calcium. The different approaches proposed by researchers to derive highly active catalysts from large-scale waste materials of a re-usable nature are described briefly. Finally, this report extends to present an overview of techno-economic feasibility of biodiesel production, its environmental impacts, commercial aspects of community-based biodiesel production and potential for large-scale expansion.