Using shiny and Bayesian network to estimate the Biochar effects

Hello all,

It's been a while that researchers within the agronomy field of study try to understand how a new soil amendment called Biochar affect the crop growth. In the past ten years, huge amount of lab and field experiments have been carried out all around the world and tons of studies and specifically meta-analysis papers have been published.

For one of the chapters of my PhD project, I was supposed to come up with a model that could estimate the Biochar effect using some basic soil and Biochar properties as a set of predictors.

At first, I spent a lot of time trying to come up with a multiple regression type of model, because I wanted to have a simple model that people could use it and interact with it. But huge collinearity between my predictors and having too many missing data made me to quit on that and take a different path.

So instead, I built a Bayesian network in R using a Java based library at the end and then created a shiny app to let the people to interact with it.

If you wanna use the app all you need to do is just click on the "Build the network" button and starting entering your soil or Biochar properties.

---