- We have no prior data related to the variety grown on the block
- We have no prior data related to THIS block, but we do know about similar blocks
- We have a reasonable set of data about the variety and the region.
- A statistical modelling approach
Samples are considered “as a whole”, and each sample is decorated with likely influential factors (e.g. variety and region). Using specialist statistical software, it is then possible to analyse the effect of each factor on ripening speed.
This is an unsupervised machine learning method CSIRO has perfected.
- A physics/chemistry approach
Samples are considered as time series, each vintage being a period of a block ripening signal. Each period is considered independent from the previous periods.
Samples are then analysed to test candidate ripening equations. This is a supervised machine learning method Thoughtpool has developed.
- extend and stabilise predictions in typical weather conditions:
The planning benefits are important as good samples in an easy vintage will result in transient/unreliable dates using OPW (as a result of the linear bias), whereas it will result in stable dates with non linear models.
As a result, less time is spent adapting a plan when there is no need to.
- actually model the effects of atypical weather:
The planning benefits are also important as good samples in a difficult vintage MUST result in fleeting dates to reflect the changing conditions. This additional level of modelling is impossible to conduct over a biased ripening model.
Better maturity prediction
More accurate predictions of grape maturity with a longer planning horizon
Register now to improve your vintage planning
Latest updates from the blog …
Last weekend was the annual weekend away with a bunch of friends - a couple of nights away in some salubrious location for a break from the everyday, and usually a fair bit of wine and food. We hit up the Barossa Valley, one of South Australia's prime winegrowing...read more
While it might seem that not much has been happening around here, in fact the quiet is because of work getting done. Not so much by me, I should add - but my colleague Marc has been hard at work on our prediction model, with help from a sizeable winery who have kindly...read more
David Bowley of Vinteloper Wines isn't afraid of a new idea. Witness his experiment with a “fold-up” winery in the depths of his home city, Adelaide. In an effort worthy of Renew Adelaide, DB has taken over the courtyard of a retail premise that has been empty for...read more