lnwzaa001

Inspiration

    Nowadays, the amount of CO2 is getting higher and higher and our world is getting hotter and hotter, so our team realize this problem and try to fix it.  

    In recent years, metal-organic frameworks have gathered and attracted everyone's attention from various fields including us. This is because of its amazing function which is the extraordinarily large internal surface area. Then, we found one of the very interesting applications of MOF which is the capability to absorb CO2. Therefore, we had an idea for predicting the capability of MOF in capturing CO2 to find the best MOF structure and reduce the MOF synthesis time.

What it does

    MOFs or Metal-Organic Frameworks are a class of compounds that consist of metal ions with organic compounds acting as binders. MOFs are the coordinate polymers, which have the special feature of being porous. Due to such properties, MOFs are used to absorb gases such as carbon dioxide and hydrogen gas as they are one of the best-used porous materials in carbon capture technologies.

How we built it

Firstly, we explore the data that is given, finding the correlation between the columns. Then, the data was cleaned, numerical data were normalized, and the functional groups were changed into categorical data. After that, we build the prediction by using the different models: neural network, XG Boost, LightGBM, CatBoost.

Challenges we ran into

We think that the toughest in this competition is to process the data because many data are missing, especially in the surface area column. From the paper that we review, we found that mostly the VSA and GSA are commonly used in predicting CO2 capturing capacity, so we decided to use them. However, calculating the VSA is quite hard and takes time.

Accomplishments that we're proud of

The model is successfully predicting the CO2 capturing capacity.

What we learned

From this competition, as the topic which is predicting the CO2 capturing capacity, it requires both knowledges from chemistry and programming, so it is a good opportunity to learn in another field that we didn’t specialize in.