Welcome to Thoughtpool – a site associated with the Thoughtpool business to be a window on what we’re doing and why.
Thoughtpool itself is (as the name implies) a “pool” of data and models based on that data that can be commercialised via web services. Our first project is related to the wine industry, building on CSIRO research [PDF] into planning a grape harvest based on prediction of the date the grapes will reach a desired ripeness, or maturity (cautionary note: the CSIRO document covers a lot of ground, and we’re not looking to provide all of those ideas – yet). We’ve called it Harvest-Plan, and set up a customer interface site.
So what is Harvest-Plan? It is a tool for wine grape harvest planning, that aggregates individual block maturity predictions into a harvest calendar that takes firmer shape as more samples are incorporated into the predictions. It is subscription- and web-based, and is available for large and small organisations growing wine grapes and/or making the wine from them. If you have an interest in or responsibility for planning a wine vintage, then check out the Harvest-Plan site, or get in touch with us.
Protecting Value
Collaborative planning
Better maturity prediction
Interested?
Register now to improve your vintage planning
Thoughts on pricing – what is a “block”?
We've been spending some time thinking about how we price the Harvest Plan service, and the discussion usually comes down to a relationship to what we call, here in Australia at least, a “block”. What does that mean? What is a block? How do we define it so we can use...
The Prediction Widget
In closing the last post, we introduced our prediction widget, which is a playground to get a feel for how predictions work. It is a graphing tool that shows how different prediction models behave on a set of real samples. It shows two linear models: One Baume per...
Harvest-plan: how we predict (pt2)
In the last post, we considered the situations where we had little or no historical data for the vineyard of interest. In this post, we consider our preferred situation: we have data. When we have historical data In this case, we can model ripening rates with a view...
