Abstract
Several sectors, such as agriculture and renewable energy systems, rely heavily on weather variables that are characterized by intermittent patterns. Many studies use regression and deep learning methods for weather forecasting to deal with this variability. This research employs regression models to estimate missing historical data and three different time horizons, incorporating long short-term memory (LSTM) to forecast short- to medium-term weather conditions at Quinta de Santa B & aacute;rbara in the Douro region. Additionally, a genetic algorithm (GA) is used to optimize the LSTM hyperparameters. The results obtained show that the proposed optimized LSTM effectively reduced the evaluation metrics across different time horizons. The obtained results underscore the importance of accurate weather forecasting in making important decisions in various sectors.

Abstract
Socioeconomic growth and population increase are driving a constant global demand for energy. Renewable energy is emerging as a leading solution to minimise the use of fossil fuels. However, renewable resources are characterised by significant intermittency and unpredictability, which impact their energy production and integration into the power grid. Forecasting models are increasingly being developed to address these challenges and have become crucial as renewable energy sources are integrated in energy systems. In this paper, a comparative analysis of forecasting methods for renewable energy production is developed, focusing on photovoltaic and wind power. A review of state-of-the-art techniques is conducted to synthesise and categorise different forecasting models, taking into account climatic variables, optimisation algorithms, pre-processing techniques, and various forecasting horizons. By integrating diverse techniques such as optimisation algorithms and pre-processing methods and carefully selecting the forecast horizon, it is possible to highlight the accuracy and stability of forecasts. Overall, the ongoing development and refinement of forecasting methods are crucial to achieve a sustainable and reliable energy future.

Abstract
Motivated by the imperative of sustainable practices, the wine industry is increasingly adopting renewable energy technologies to address environmental concerns and ensure its long-term viability amidst rising fossil fuel costs and greenhouse gas emissions. Hybrid renewable energy systems (HRES) have emerged as a solution to improve energy efficiency and mitigate the variability of renewable resources, allowing for better system load factors, greater stability of power supply, and optimized use of infrastructure. Therefore, this study aims to design a HRES that integrates solar and wind energy to sustainably fed an irrigation system in a favorable technical-economic context. This research presents a Mixed Integer Linear Programming (MILP) model that optimizes the profit generated by a grid-connected HRES over 20 years and obtains the optimal system sizing. The study focuses on the farm Quinta do Vallado, Portugal, and examines two distinct Cases. Over 20 years, the implementation of the hybrid system has resulted in savings of approximately 61%.

Abstract
The objective of achieving carbon neutrality by 2050 requires the various sectors of the economy to actively participate in the decarbonisation of all their activities, from production to consumption and product distribution. The vineyard and wine production sector is no exception to this goal. This paper aims to evaluate the feasibility and efficiency that hybrid energy systems based on renewable energy sources, solar photovoltaic (PV) and wind, can contribute to energy efficiency in certain activities related to wine production. In this sense, this study presents results based on linear programming optimisation models, which show how effective they are in minimising the use of energy from the power grid. The results show that renewable hybrid energy systems based on PV and wind are an effective solution for achieving carbon neutrality in some agricultural sectors, particularly winemaking sector. Besides being able to minimise the energy bought from the grid, the hybrid renewable energy system (HRES) is almost self-sufficient, being able to produce 340,232 kWh over 25 years.

Abstract
The sustainability of forest species is directly related to the success of stand regeneration. Assuring success is particularly critical in stands where perpetuity relies on natural regeneration, as is often the case with cork oak forests. However, 59% of the stand in Portugal have no natural regeneration, and climate change could further worsen the sustainability of the system. The study summarizes the factors that affect the natural regeneration of cork oak (Quercus suber L.) based on current knowledge and presents a case study on a forest in Northeast Portugal, where the natural regeneration of Quercus suber under the effect of climate change have been monitored and analyzed. The present work focuses on the effect of stand density, i.e., tree cover, on the production of acorns, the establishment and survival of seedlings, and the impact of the summer season on seedling mortality. The monitoring was carried out in February, June, September 2022, and January 2023 in two stands with distinct stand canopy cover, when the region was under extreme drought. Data analysis was performed using the analysis of variance for repeated measures and the Mann-Whitney-Wilcoxon test. The study showed that cork oak regeneration is influenced by stand density, which promoted the establishment success and survival of natural regeneration in a period of reduced precipitation, despite possible competition for water resources. The mean number of seedlings differed significantly between the two stands. However, there were no significant differences in the mean number of seedlings throughout the field measurements. Additionally, the percentage of dead seedlings was low even after the summer season (9.5% of the total seedlings) in the denser stand. These results indicate that high canopy cover can have a protective effect for extreme climatic events and should be considered in forestry management to promote regeneration of the cork oak forests.

Abstract
This chapter aims to contribute to the understanding of how artificial intelligence (AI) technologies can promote increased business revenues, cost reductions, and enhanced customer experience, as well as society's well-being in a sustainable way. However, these AI benefits also come with risks and challenges concerning organizations, the environment, customers, and society, which need further investigation. This chapter also examines and discusses how AI can either enable or inhibit the delivery of the goals recognized in the UN 2030 Agenda for Sustainable Business Models Development. In this chapter, the authors conduct a bibliometric review of the emerging literature on artificial intelligence (AI) technolo¬gies implications on sustainable business models (SBM), in the perspective of Sustainable Development Goals (SDGs) and investigate research spanning the areas of AI, and SDGs within the economic group. The authors examine an effective sample of 69 publications from 49 different journals, 225 different institutions, and 47 different countries. On the basis of the bibliometric analysis, this study selected the most significant published sources and examined the changes that have occurred in the conceptual framework of AI and SBM in light of SDGs research. This chapter makes some significant contributions to the literature by presenting a detailed bibliometric analysis of the research on the impacts of AI on SBM, enhancing the understanding of the knowledge structure of this research topic and helping to identify key knowledge gaps and future challenges. © 2024, IGI Global. All rights reserved.