Chaining Hash Map
这是一篇来自美国的关于在LTC预测中应用的机器学习代写
- What is the problem you plant to work? why are you interested in the problem or how is it important?
Machine Learning in the prediction of LTC (lattice thermal conductivity) of materials
Heat transfer in two-dimensional (2D) materials due to their application in nanoelectronics and batteries is a determining factor in their design and optimal performance. Therefore thermal conductivity is the most important thermal property in 2D semiconductor materials.
- Describe the type of problem (regression, classification, active learning etc). What are the input and output?
Random forest Input: compounds’ chemical formula
Output: LTC (lattice thermal conductivity)
- Any similar work has been done before? Why do you need ML instead of other approaches?
Yes. As machine learning algorithm gain experience, they keep improving in accuracy and efficiency. This lets them make better decisions. In recent years, machine learning has been extensively used to accelerate the recognition of the physical properties of various materials
- What database or data source will you use? Describe characteristics of data (image, numerical, categorical data so on). How much data can you expect to get from the data source?
Citrination Numerical data More than 500 data cells
- Do you plan to use an online platform or write own program (Scikit-learn, Pytorch etc) for your project?
Not sure, we will try if necessary.