Prediction of Nitrogen Dioxide Level using Machine Learning Models

As we release more pollution into the atmosphere as factory and vehicle byproducts, acid rains are formed and are constantly damaging the environment and harming wildlives under and above the ocean. If the occurrence of acid rains can't be limited, the phenomenon of this man-made disaster will threaten the health and safety of billions. By predicting the potential development of acid rain with nitrogen dioxide (NO2) levels, one of the major components of acid rain, we could prevent it by limiting the number of specific gasses produced.

Air pollution has been a lingering problem to many developing countries. Overpopulated cities and unregulated industrial and vehicle emissions constantly destroy the natural environment and harm human health. Being one of the most common air pollutants, nitrogen dioxide, also known as NO2, damages our respiratory system, destroys aquatic food chains, and contributes to the formation of acid rains. In this paper, linear regression, random forest regressor and decision tree regressor from scikit learn are used to predict NO2 level in parts per million (ppm) by analyzing its correlation with other air pollutants in a specific city. The model achieved an accuracy of 69,1 percent using random forest and a 66 percent accuracy using decision tree. The accuracy of the model can increase with a more detailed dataset, but further scientific research and discovery are required to actually predict acid rain based on just NO2, since the amount of NO2 that will cause acid rain is uncountable and many more variables go into the formation of acid rain.

Explore More!

Plant Toxicity Classification by Image

Since differentiating between dangerous and safe plants is a complex task for a human brain, this study approaches the issue through machine learning models starting with a convolutional neural network (CNN) and discovering that a logistic regression model—trained on a dataset with manually designed features—has the best performance with the particular dataset used.

Eera B.

Mentored by Clayton Greenberg

PlastiGuard: ML/Molecular Descriptor based Biodegradability Analyzer of Persistent Chemical Carcinogens in Plastics

This study uses machine learning models and molecular descriptor data to evaluate the biodegradability of harmful plastic carcinogens and identify safer structural alternatives. The research shows that neural networks perform the best at predicting biodegradability, and it highlights several naturally produced substitutes that could reduce the environmental and health risks linked to persistent toxins in plastics.