ChatGPT is a versatile conversational Artificial Intelligence model that responds to user input prompts, with applications in academia and various sectors. However, crafting effective prompts can be challenging, leading to potentially inaccurate or contextually inappropriate responses, emphasizing the importance of prompt engineering in achieving accurate outcomes across different domains. This study aims to address this void by introducing a methodology for optimizing interactions with Artificial Intelligence language models, like ChatGPT, through prompts in the field of engineering. The approach is called GPEI and relies on the latest advancements in this area; and consists of four steps: define the objective, design the prompt, evaluate the response, and iterate. Our proposal involves two key aspects: data inclusion in prompt design for engineering applications and the integration of Explainable Artificial Intelligence principles to assess responses, enhancing transparency. It combines insights from various methodologies to address issues like hallucinations, emphasizing iterative prompt refinement techniques like posing opposing questions and using specific patterns for improvement. This methodology could improve prompt precision and utility in engineering.

DYNA es una publicación científica general del área de las ciencias tecnológicas, fundada en 1933, es el medio de expresión de los trabajos en el área de ingeniería, ciencias y tecnología de la Facultad de Minas de la Universidad Nacional de Colombia.

In the last decade, many artificial intelligence (AI) techniques have been used to solve various problems in sustainable energy (SE). Consequently, an increasing volume of research has been devoted to this topic, making it difficult for researchers to keep abreast of its developments. This paper analyzes 18,715 articles—about AI techniques used for SE—indexed in Scopus and published from 2013 to 2022, which were retrieved and selected following a novel iterative methodology. Besides calculating basic bibliometric indicators, we used clustering techniques and a co-occurrence analysis of author keywords to discover and characterize dominant themes in the literature. As a result, we found eight dominant themes in SE (solar energy, smart grids and microgrids, fuel cells, hydrogen, electric vehicles, biofuels, wind energy, and energy planning) and nine dominant techniques in AI (genetic algorithms, support vector machines, particle swarm optimization, differential evolution, classical neural networks, fuzzy logic controllers, reinforcement learning, deep learning, and multi-objective optimization). Each dominant theme is discussed in detail, highlighting the most relevant work and contributions. Finally, we identified the AI techniques most widely used in each SE area to solve its specific problems.

Risk management in electricity markets is essential for decision making that involve uncertainty. This article researches the dominant themes and research trends in risk management in electricity markets using descriptive analysis, literature mapping, and data mining techniques. The proposed methodology generates the clusters within the dominant themes and provides a comprehensive view of the main authors, journals, and publications, as well as the main lines of research. The results reveal that the academic production of the subject is increasing and the research trends focused on financial risk management, energy resource management, and that climate coverage mechanisms are of great interest to the scientific community.

Objective: The aim of this paper is to analyze the development of new forecasting models based on neural networks. Method: We used the systematic literature review method employing a manual search of papers published on new neural networks models in the time period 2000 to 2010. Results: Only 18 studies meet all the requirements of the inclusion criteria. Of these, only three proposals considered a neural networks model using a process different to the autoregressive. Conclusion: Although studies relating to the application of neural network models were frequently present, we find that the studies proposing new forecasting models based on neural networks with a theoretical support and a systematic procedure for the construction of model, were scarce in the time period 2000-2010.