Browse Articles

Using machine learning to predict the risk of algae bloom

Here the authors investigated air quality forecasting in India, comparing traditional time series models like SARIMA with deep learning models like LSTM. The research found that SARIMA models, which capture seasonal variations, outperform LSTM models in predicting Air Quality Index (AQI) levels across multiple Indian cities, supporting the hypothesis that simpler models can be more effective for this specific task.

The water we use must be treated and cleaned before we release it back into the environment. Here, the authors investigate two new techniques for purifying dissolved impurities from waste water. Their findings may give rise to more cheaper and more efficient water treatment and help keep the planet greener.

The authors looked at the ability of Spirulina platensis to reduce contaminants in wastewater in order to develop a more accessible treatment option. They found that S platensis did reduce the concentration of pollutants present within simulated agricultural wastewater.

Algal blooms pose a threat to ecosystems, but the methods used to combat these blooms might harm more than just the algae. Halepete, Graham, and Lowe-Schmahl demonstrate negative effects of anti-algae treatments on a cyanobacterium (Spirulina major), and the water fleas (Daphnia magna) that live alongside these cyanobacteria.

In this study, the authors test ways to increase knowledge of green consumerism amongst high school students. Their knowledge was measured based on the New Ecological Paradigm Scale.

Plastic debris can disrupt marine ecosystems, spread contaminants, and take years to naturally degrade. In this study, Wu et al aim to establish an understanding of the scope of Williamston, Michigan’s microplastics problem, as well as to attempt to find the source of these plastics. Initially, the authors hypothesize that the Williamston Wastewater Treatment Plant was the primary contributor to Williamston’s microplastics pollution. Although they find a general trend of increasing concentrations of microplastics from upstream to downstream, they do not pinpoint the source of Williamston’s microplastics pollution in the present research.

This study hypothesized that a machine learning model could accurately predict the severity of California wildfires and determine the most influential meteorological factors. It utilized a custom dataset with information from the World Weather Online API and a Kaggle dataset of wildfires in California from 2013-2020. The developed algorithms classified fires into seven categories with promising accuracy (around 55 percent). They found that higher temperatures, lower humidity, lower dew point, higher wind gusts, and higher wind speeds are the most significant contributors to the spread of a wildfire. This tool could vastly improve the efficiency and preparedness of firefighters as they deal with wildfires.

While some believe that ride-hailing services offer reduced CO₂ emissions compared to individual driving, studies have found that driving without passengers on ride-hailing trips or "deadheading" prevents this. Here, with a mathematical model, the authors investigated if the use of electric vehicles as ride-hailing vehicles could offer reduced CO₂ emissions. They found that the improved vehicle efficiency and cleaner generation could in fact lower emissions compared to the use of personal gas vehicles.

Based on the success of deep learning, recent works have attempted to develop a waste classification model using deep neural networks. This work presents federated learning (FL) for a solution, as it allows participants to aid in training the model using their own data. Results showed that with less clients, having a higher participation ratio resulted in less accuracy degradation by the data heterogeneity.