Browsing by Author "Menares, Camilo"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Publication Current Status, Trends, and Future Directions in Chilean Air Quality: A Data-Driven Perspective(2025) Basoa, Kevin; Fleming, Zoë; Leiva, Manuel A.; Concha, Carolina; Menares, CamiloAir pollution is one of the main problems facing humanity today. Megacities and large urban areas are pollution hotspots. Measuring pollutants and recording these measurements is key to developing effective strategies to reduce the pollution levels to which people are exposed. However, air quality monitoring presents significant challenges (e.g., investment costs, maintenance), which can lead to limited monitoring equipment. Despite this, Chile has an extensive air quality monitoring network, known as the National Air Quality Information System (SINCA in Spanish). This network has more than 200 monitoring stations that measure, record, and display information on pollution levels in different locations in Chile. In this study, all the information available from the SINCA network was systematized to evaluate the completeness of the records and the current trends of several pollutants in Chile. The main results show that most measurements focus on particulate matter and sulfur dioxide concentrations, and many of the measurement stations are located in the central part of the country (32° S–38° S). However, by splitting the data into five macrozones, one can see the regional air quality characteristics and changes. Furthermore, there are significant data gaps at some monitoring stations, which makes it difficult to elaborate a robust analysis. Regarding pollution levels, a significant decrease is observed for the peak Particulate Matter (PM2.5) concentrations, with decreases of nearly 40% compared to concentrations at the beginning of the 2000s. This is consistent with the concentration trends, which show negative trends in most cases.Item Forecasting PM2.5 levels in Santiago de Chile using deep learning neural networks(2021) Menares, Camilo; Pérez, Patricio; Parraguez, Santiago; Fleming, ZoëAir pollution has been shown to have a direct effect on human health. In particular, PM2.5 has been proven to be related to cardiovascular and respiratory problems. Therefore, it is important to have accurate models to predict high pollution events for this and other pollutants. We present different models that forecast PM2.5 maximum concentrations using a Long Short-Term Memory (LSTM) based neural network and a Deep Feedforward Neural Network (DFFNN). Ten years of air pollution and meteorological measurements from the network of monitoring stations in the city of Santiago, Chile were used, focusing on the behaviour of three zones of the city. All missing values were rebuilt using a method based on discrete cosine transforms and photochemical predictors selected through unsupervised clustering. Deep learning techniques provide significant improvements compared to a traditional multi-layer neural networks, particularly the LSTM model configured with a 7-day memory window (synoptic scale of pollution patterns) can capture critical pollution events at sites with both primary and secondary air pollution problems. Furthermore, the LSTM model consistently outperform deterministic models currently used in Santiago, Chile.