According to the Food and Agriculture Organization (FAO), nearly one-third of food produced for human consumption is wasted annually, resulting in global economic losses nearing $1 trillion. The proposed framework leverages IoT-enabled, real-time sensor data combined with Machine Learning (ML) models for crop yield prediction, demand forecasting, and shelf-life monitoring. Experimental results demonstrate that the proposed models outperform state-of-the-art solutions in accuracy and efficiency, further enhancing waste reduction across the Food Supply Chain (FSC). This Artificial Intelligence (AI) driven FSC framework demonstrates a scalable approach to reduce food waste, optimize resource use, and improve sustainability across the FSC. The proposed solution not only enhances operational sustainability but also provides a data-driven foundation for future advancements.

The rapid urbanization and industrialization has accelerated the energy consumption globally. This releases a large amount of polluting gases, causing damage to the environment and seriously affecting people's lives. The transportation industry is one of the major contributors towards global carbon emission. This paper focuses on the use of heuristic algorithms (Particle Swarm Optimization - PSO) to predict and optimize the energy consumption value and carbon emission by the fossil fuel-based transportation systems versus green and electric modes of transportation. Results showed that the PSO model has the highest degree of fit between the predicted value and the true value. The use of PSO-based strategies for route and energy efficiency optimization specifically, after adopting and implementing electric vehicles in India showed that there was a 71% decrease in CO₂ emissions. This remarkable reduction highlights the potential of combining intelligent computational techniques with clean technologies to address the pressing issue of climate change and transition toward a sustainable transportation future.

The increasing demand of energy and the limited supply of fossil hydrocarbons are driving the research towards uncovering alternative renewable and sustainable energy sources. The use of plant biomass has emerged as an attractive and promising platform to replace the conventional, non-renewable, environmentally unfriendly and scarce energy sources. This study explains about the use of lignocellulosic plant biomass (rice straw) for the production of bioethanol by employing fungal enzyme (cellulase) conjugated chitosan nanoparticles. These nanoparticles were effective in the hydrolysis of complex structures of lignocellulosic material to reducing sugars in less time, thereby increasing ethanol yield to 3-folds. The environmentally friendly and low-cost substrate, biodegradability and reduced toxicity of bioethanol offers added advantages over fossil hydrocarbons.

Climate change has significant and far-reaching effects on agriculture, a cornerstone of the Indian economy, which supports nearly 60% of the population and contributes substantially to national GDP. This study focuses on understanding the effects of average rainfall and temperature on Indian crop yields such as oilseeds, rice, pulses, maize and wheat over a five year (2020-2025) timeframe through tree-based AI models like XGBoost. Results indicated that the optimal rainfall threshold and climate sensitivity vary markedly across Indian states. The average rainfall (mm) and average temperature (°C) for the maize, oilseeds, pulses, rice and wheat was found to be in the range of 1080-1142 mm and 26.96-27.14 °C, with average yield between 33.73-36.34 q/ha. The data patterns showed that climatic disturbances have led to reduced yields of staple crops thereby affecting food security, rural livelihoods, and income stability.

Metalloids especially arsenic (As) is potentially toxic and is considered as a carcinogen. The prolonged exposure of arsenic may cause severe health problems. This makes it very important to understand the removal strategies of this toxic metal from the soil and water bodies to make them fit for the survival of living organisms. The study demonstrates the effective removal and accumulation of arsenic by a soil bacterium called Bacillus subtilis, which was found to be highly resistant to arsenic with the Minimum Inhibitory Concentration value of 500 mg/ml. Results reflected that the bacteria was quite active in quickly adsorbing the arsenic without any significant damage caused to the cells. Such arsenic resistant bacterium can be effectively applied for the bioremediation of contaminated soil and water.