Sugarcane is a particularly suitable crop for the application of data science, due to the continuous year-round growing season, multiple harvests per planting, the common application of ripeners several weeks before harvest time, and the high fraction of usable biomass visible through remote sensing.
Change Occurs at the Field Level
Our Predictive Yield Estimates are built by creating digital bio-physical models unique to C4 photosynthetic crops, using robust machine-learning prediction methods that allow us to understand the impact of various agronomic factors, such as sugar content and tonnage.
Accurate short-term estimates can alleviate uncertainty in yield and tonnage, and long-term estimates can be used to optimize plant timing and rotation plans.
The growers we’ve worked with have sought to lower the error in their yield estimates through quantitative analysis at the field level. Digital Harvest develops a customized plan for each customer to have an operational yield estimation with a 5-8% field error and 1-3% error at the production zone level several months prior to harvest.
Receiving predictive yield estimates months in advance for individual fields within a total production area gives mill management an invaluable look into the future, enabling them to make more accurate, proactive decisions.
Add - Meaningful change and improvements occur with decisions made at the field level. As such, all of Digital Harvest’s predictive models start at the field level and aggregate up to the mill, regional and national levels as needed.
Accurate short-term estimates can alleviate uncertainty in TCH and TSH, and long term estimates can be used to optimize plant and harvest timing, crop rotation plans, and irrigation schedules.
Visible Harvest™ also now offers
6 Month Weather Forecasting.
This is a New Premium Feature!
This powerful resource is being offered for FREE to this season's customers.
ACT NOW See Your Tomorrow, Today.
Optimization Solution for 4,507 Fields
Yield-Optimized Harvest Schedule
With the ability to better quantify the impact of controllable variables such as harvest date, we’ve been able to optimize multi-year harvest schedules to maximize yield within logistics constraints.
For example, during the 2016/17 season, the customer realized an additional 200,000 extra tons of sugarcane (1 ton=$32), simply by rearranging its yield optimized harvesting schedule delivered by Digital Harvest (without deploying new hardware or learning to use new software).