The meteorological variability generated by climate change causes uncertainty in the evolution of crops that entails added difficulty in planning harvests, and particularly in fruit growing. On the other hand, the increase in the variability of the volume and quality of peach and cherry production means that the investment of resources and dedication of the technical teams to plan the harvests is increasingly higher and not more accurate. The technical teams use different techniques (sampling, ripening controls, gauging, etc.) to determine in advance the aforementioned variables of volume and optimal harvest time, but the reliability of the results that these systems provide has a lot of potential for improvement. The large number of variables that affect both the quality and quantity of production (meteorology, characteristics of the plots, productive areas, etc.) makes it very complex to obtain reliable predictions with traditional approaches, and therefore, That today there is still no successful methodology to be able to know in advance the two main variables that affect harvest planning in peach and cherry cultivation: volume and harvest maturation.
Therefore, improving the reliability of harvest planning becomes a critical factor for the competitiveness of fruit producing companies. Obtaining reliable harvest planning allows you to gain a strategic position when it comes to:
Make strategic business decisions
Negotiate sales contracts (prices, delivery dates and volumes) with clients
Reduce production costs thanks to better efficiency in resource management
Optimize the cold and logistics capacity of the plants
The project is based on the use of data and Big Data technologies to develop prediction models that anticipate information on the evolution of quality parameters and harvest volumes for the peach and cherry sector. It is understood that these models are scalable to other fruit species later.
Technology linked to Big Data currently makes it possible to integrate multiple sources of information to develop prediction models to reduce uncertainty in harvest planning. The data sources that will be used in this project are divided into 4 main blocks:
a) Ripening controls, using fruit quality parameters such as the degradation of chlorophyll.la in peaches (measured with the DA-meter device) and the sugar content in cherries (measured with a refectrometre). b) History of production volumes by plot (the origin is the central ERP) c) Capacity (the origin is the company records)
a) Maps/type of soils
b) Planting details (surface area, age of trees, variety, rootstock, training system...etc)