About this Research Topic
The relationship between air quality and biosphere-atmosphere interactions (BAI) is complex and bidirectional. Air quality is a broad, overarching topic, which relates to BAI in particular through the formation of particulate matter, its impact on clouds, and the interactions between chemicals and pollutants (originating from both anthropogenic and natural sources). In this sense, BAI modulates air quality, and vice versa. For example, air pollution caused by human activities can have adverse impacts on the biosphere and affect BAI.
Machine learning and neural network approaches in BAI are still in development. At the current time, methods that are being explored include: regression systems for gap-filling, pattern matching, predictive modeling, time-series predictions, and ANN techniques.
The goal of this Research Topic is to provide an integrated understanding of the link between air quality and BAI, current machine learning and neural network approaches to investigate these dynamics, as well as aiming to initiate further research and discussion on the topic. For instance, the future of deep learning methods is a pertinent question that could be addressed, considering their advantages (high prediction accuracy) and limitations (low interpretability). More generally, this Research Topic should contribute to clarifying the use of linear vs non-linear algorithms according to the situation and the research goals. These themes are of great importance for furthering scientific knowledge in multiple domains, such as climate change research, weather predictions, and impacts on human health.
Authors are welcome to submit Original Research articles, Reviews, Methods, Perspectives, Data Reports, Brief Research Reports, and Opinion articles. Specific topics of interest, include, but are not limited to:
● Data collection and integration of data from different sources on air quality and BAI - for example, satellite imagery, weather stations, air quality sensors, and biological monitoring systems.
● Linear (Regression systems) and non-linear (advanced ML algorithms) methods for gap-filling.
● Pattern matching and pattern recognition - machine learning models trained to recognize patterns in the collected data that may help in identifying interactions.
● Predictive modeling, time series forecasting using historical data to predict future trends.
● Artificial neural network and deep neural network models - for forecasting and air quality assessment.
● New machine learning and artificial intelligence methods for air quality and BAI.
Machine learning and neural network approaches in BAI are still in development. At the current time, methods that are being explored include: regression systems for gap-filling, pattern matching, predictive modeling, time-series predictions, and ANN techniques.
The goal of this Research Topic is to provide an integrated understanding of the link between air quality and BAI, current machine learning and neural network approaches to investigate these dynamics, as well as aiming to initiate further research and discussion on the topic. For instance, the future of deep learning methods is a pertinent question that could be addressed, considering their advantages (high prediction accuracy) and limitations (low interpretability). More generally, this Research Topic should contribute to clarifying the use of linear vs non-linear algorithms according to the situation and the research goals. These themes are of great importance for furthering scientific knowledge in multiple domains, such as climate change research, weather predictions, and impacts on human health.
Authors are welcome to submit Original Research articles, Reviews, Methods, Perspectives, Data Reports, Brief Research Reports, and Opinion articles. Specific topics of interest, include, but are not limited to:
● Data collection and integration of data from different sources on air quality and BAI - for example, satellite imagery, weather stations, air quality sensors, and biological monitoring systems.
● Linear (Regression systems) and non-linear (advanced ML algorithms) methods for gap-filling.
● Pattern matching and pattern recognition - machine learning models trained to recognize patterns in the collected data that may help in identifying interactions.
● Predictive modeling, time series forecasting using historical data to predict future trends.
● Artificial neural network and deep neural network models - for forecasting and air quality assessment.
● New machine learning and artificial intelligence methods for air quality and BAI.
Keywords: air quality, biosphere-atmosphere interactions, machine learning, artificial neural networks, forecasting, predictive modeling
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
