The electricity market in Spain holds significant importance in the nation’s economy and sustainability efforts due to its diverse energy mix that encompasses renewables, fossil fuels, and nuclear power. Accurate energy price prediction is crucial in Spain, influencing the country’s ability to meet its climate goals and ensure energy security and affecting economic stakeholders. We have explored how leveraging advanced GPT tools like OpenAI’s ChatGPT to analyze energy news and expert reports can extract valuable insights and generate additional variables for electricity price trend prediction in the Spanish market. Our research proposes two different training and modelling approaches of generative pre-trained transformers (GPT) with specialized news feeds specific to the Spanish market: in-context example prompts and fine-tuned GPT models. We aim to shed light on the capabilities of GPT solutions and demonstrate how they can augment prediction models by introducing additional variables. Our findings suggest that insights derived from GPT analysis of electricity news and specialized reports align closely with price fluctuations post-publication, indicating their potential to improve predictions and offer deeper insights into market dynamics. This endeavor can support informed decision-making for stakeholders in the Spanish electricity market and companies reliant on electricity costs and price volatility for their margins.

The use, production, and disposal of engineering nanomaterials (ENMs), including graphene-related materials (GRMs), raise concerns and questions about possible adverse effects on human health and the environment, considering the lack of harmonized toxicological data on ENMs and the ability of these materials to be released into the air, soil, or water during common industrial processes and/or accidental events. Within this context, the potential release of graphene particles, their agglomerates, and aggregates (NOAA) as a result of sanding of a battery of graphene-based polyester resin composite samples intended to be used in a building was examined. The analyzed samples were exposed to different weathering conditions to evaluate the influence of the weathering process on the morphology and size distribution of the particles released. Sanding studies were conducted in a tailored designed sanding bench connected to time and size resolving measurement devices. Particle size distributions and particle number concentration were assessed using an optical particle counter (OPC) and a condensation particle counter (CPC), respectively, during the sanding operation. A scanning electron microscope/energy dispersive X-ray (SEM/EDX) analysis was performed to adequately characterize the morphology, size, and chemical composition of the released particles. A toxicity screening study of pristine and graphene-based nanocomposites released using the aquatic macroinvertebrate Daphnia magna and relevant human cell lines was conducted to support risk assessment and decision making. The results show a significant release of nanoscale materials during machining operations, including differences attributed to the % of graphene and weathering conditions. The cell line tests demonstrated a higher effect in the human colon carcinoma cell line Caco2 than in the human fibroblasts (A549 cell line), which means that composites released to the environment could have an impact on human health and biota.

During the last decade, the use of nanomaterials, due to their multiple utilities, has exponentially increased. Nanomaterials have unique properties such as a larger specific surface area and surface activity, which may result in health and environmental hazards different from those demonstrated by the same materials in bulk form. Besides, due to their small size, they can easily penetrate through the environmental and biological barriers. In terms of exposure potential, the vast majority of studies are focused on workplace areas, where inhalation is the most common route of exposure. The main route of entry into the environment is due to indirect emissions of nanomaterials from industrial settings, as well as uncontrollable releases into the environment during the use, recycling and disposal of nano-enabled products. Accidental spills during production or later transport of nanomaterials and release from wear and tear of materials containing nanomaterials may lead to potential exposure. In this sense, a proper understanding of all significant risks due to the exposure to nanomaterials that might result in a liability claim has been proved to be necessary. In this paper, the utility of an application for smartphones developed for the insurance sector has been validated as a solution for the analysis and evaluation of the emerging risk of the application of nanotechnology in the market. Different exposure scenarios for nanomaterials have been simulated with this application. The results obtained have been compared with real scenarios, corroborating that the use of novel tools can be used by companies that offer risk management in the form of insurance contracts.

Our research proposes two different training and modelling approaches of Generative Pre-trained Transformers (GPT) with specialized news feeds specific to the Spanish market: in-context example prompts and fine-tuned GPT models. Our findings indicate that integrating GPT insights into electricity price trend forecasting can result in more precise predictions and a deeper understanding of market dynamics. Through our research, we aim to provide insights to understand the capabilities of GPT solutions, and how those can be used to enhance prediction accuracy, ultimately supporting informed decision-making for stakeholders across the Spanish electricity market and companies whose margins heavily depend on electricity costs and price volatility.

The development of large language models (LMMs) with generative artificial intelligence has enabled the automated development of a new generation of knowledge based systems that can interact through natural language with users. In this paper, we study how to exploit the potential of LLMs, specifically of the new OpenAI GPT models, to extract information on the causes and possible solutions of manufacturing defects from the analysis of the knowledge contained in a sample of specialized bibliographic sources. For this purpose, an advanced Retrieval-Augmented Generation (RAG) system has been designed, developed and applied to ceramic tile manufacturing. The documents of the knowledge base have been selected among those in the literature dealing with defects in ceramic tile manufacturing and their possible causes and solutions. In addition to the functions of a basic RAG for query and retrieval, the developed RAG system incorporates functions for specific preprocessing of documents and user queries, postprocessing of the retrieved information, and performance evaluation processes for both retrieval and generation. We show how an advanced RAG system can be an effective tool in the troubleshooting and failure analysis stages of quality control management procedures. Companies can use this application to quickly identify nonconformities in products or processes and their causes and generate solutions to quality problems.