Projects

SowStain: Digital Twins for Precision Agriculture

A Digital Twin to improve agriculture

Funding: ICSC Innovation Funds

Enabling technology: Digital Twin, Geographic Information Systems (GIS), Image recognition

Sustainable Development Goals

A Digital Twin will be developed to study and optimize processes in precision agriculture (PA). The objectives are:

optimizing precision agriculture systems by learning from data;
efficiently managing water and effectively adapting to extreme events;
collecting data across all phenological phases, focusing on: product quality, attention to the entire supply chain, and the ability to optimize seasonal forecasts based on crops, soil, water availability, and pathogen risks;
reducing issues through information sharing.

National Centre for HPC, Big Data and Quantum Computing (ICSC), a project funded by the European Union – NextGenerationEU – and by Italy’s National Recovery and Resilience Plan (PNRR) – Mission 4, Component 2.

Objectives

The project’s strengths lie in product quality, attention to the entire supply chain, and the ability to optimize seasonal forecasts and make predictions based on crops, water availability, and pathogen risks.

The ultimate goal is to solve industry challenges by sharing the information gathered by the Digital Twin.

Initial challenge

The main challenge is the need to develop a system capable of efficiently managing water and adapting management to extreme events for successful agricultural processes.

This need is compounded by the impossibility of conducting field trials.

Solution

Implementation of a Digital Twin environment to analyze and optimize processes in PA.
Use of data collected from sensors, satellites, and drones.
What-if simulations to manage extreme events and improve crop resilience.

Benefits

Improved crop resilience.
Reduced resource waste and emissions.
Increased production on existing agricultural land.
Support for decision-makers with advanced analysis tools.
Contribution to sustainable agriculture and climate-resilient water management.

IFAB’s role

IFAB acted as a technical partner in the project’s development. The team’s work began with the data engineering phase, collecting and harmonizing data from the different phenological phases of crops to build a structured, interoperable information base. Building on this foundation, the Digital Twin was designed and implemented — a dynamic digital representation of agricultural processes capable of learning from real data and simulating scenarios to support operational decisions.

In parallel, predictive models were developed for seasonal and crop forecasting, capable of estimating water availability, anticipating pathogen risks, and guiding agronomic planning. The work concluded with the definition of data-driven methods for optimizing water management and adapting to extreme events, making the most of the information gathered throughout the entire crop cycle.

For Fondazione IFAB, the project offered an opportunity to deepen the application of digital twin technologies and predictive modeling in the agricultural sector, building experience in a domain where the ability to integrate environmental, agronomic, and climate data is set to become an increasingly relevant competitive factor.