Science seeks strategies to mitigate global warming and reduce the negative impacts of the long-term use of fossil fuels for power generation. In this sense, implementing and promoting renewable energy in different ways becomes one of the most effective solutions. The inaccuracy in the prediction of power generation from photovoltaic (PV) systems is a significant concern for the planning and operational stages of interconnected electric networks and the promotion of large-scale PV installations. This study proposes the use of Machine Learning techniques to model the photovoltaic power production for a system in Medellín, Colombia. Four forecasting models were generated from techniques compatible with Machine Learning and Artificial Intelligence methods: K-Nearest Neighbors (KNN), Linear Regression (LR), Artificial Neural Networks (ANN) and Support Vector Machines (SVM). The results obtained indicate that the four methods produced adequate estimations of photovoltaic energy generation. However, the best estimate according to RMSE and MAE is the ANN forecasting model. The proposed Machine Learning-based models were demonstrated to be practical and effective solutions to forecast PV power generation in Medellin.

Air pollution caused by fine particles known as PM2.5 is a significant health concern worldwide, contributing to illnesses like asthma, heart disease, and lung cancer. To address this issue, this study focused on improving air purification systems using negative ions, which can attach to these harmful particles and help remove them from the air. This paper developed a novel mathematical model based on linear differential equations to study how PM2.5 particles interact with negative ions, making it easier to design more effective purification systems. The proposed model was validated in a small, controlled space, using common urban pollutants such as cigarette smoke, incense, coal, and gasoline. These tests were conducted at different temperatures and under two levels of ion generation. The results showed that the system could remove over $99\%$ of PM2.5 particles in five minutes when temperatures were low or moderate. However, at higher temperatures, the system’s performance dropped significantly. This research goes beyond earlier studies by examining how temperature affects the process, which had not been fully explored before. Furthermore, this approach aligns with global sustainability goals by promoting public health, reducing healthcare costs, and providing scalable solutions for sustainable urban living.

Cities globally must make urgent decisions to ensure a sustainable future as rising pollution, particularly PM2.5, poses severe health risks like respiratory and heart diseases. PM2.5’s harmful composition also impacts vegetation and the environment. Immediate government intervention is necessary to mitigate these effects. This study tackles the urgent problem of reducing PM2.5 levels in Medellín’s urban and indoor environments, where pollution presents serious health risks. To explore effective solutions, this research provides new data on the interaction between particulate matter from various pollutants and negative ions under different temperature conditions, offering valuable insights into air quality improvement strategies. Using a high-voltage system, ions bind to pollutants, accelerating their removal. Experiments measured temperature, humidity, formaldehyde, volatile organic compounds, negative ions, and PM2.5 in a 40 cm³ chamber across various conditions. Pollutants tested included cigarette smoke, incense, charcoal, and gasoline at two voltage levels and three temperature ranges. The data, available in CSV format, were based on 36,000 samples and repeated tests for reliability. This resource is designed to support studies investigating particulate matter control in urban and indoor environments, as well as to improve our understanding of negative ion-based air purification processes. The data are publicly available and structured in formats compatible with leading data analysis platforms.