Skip to content

AI for sustainable value chains

AI for sustainable value chains

The pandemic has both reinforced and highlighted the underlying trends that preceded it. Not only did 45% of consumers claim that they want to purchase more sustainable products during this period, Accenture reports, they also intend to continue in this dynamic in the future (Keeble, 2020).

Faced with the rise of these new expectations, companies have higher demands from their suppliers and are improving the sustainability of their value chains. However, the required transformation does not stop there, it is now necessary to ensure the quality of the information that circulates in the supply chains and empower each actor with suitable technological tools to manage it. To take full advantage of artificial intelligence (AI) and its capabilities, large amounts of data are necessary. As value chain data is too often scattered, a system integrating supply chain data collection and consolidation is needed.

The first big challenge for agribusiness value chain actors is data collection and consolidation.

phy2app and phy2app pro. Anteja, August 2021.

At Anteja, we’ve developed phy2app, a digital transparency tool, which helps agribusinesses to collect, consolidate and communicate key information about the product’s origin, production processes, certifications, social and environmental impact to their customers. They can communicate this information. to either another business (B2B) or to final consumers (B2C). Transparently, each actor in the value chain can easily access valuable information, all in one place.

As an advanced version of phy2app, we developed phy2app pro, an order management system, that facilitates a transparent exchange of order-related documents and information. Phy2app pro also provides organised filing and shared archiving, so that the trade partners can always access all the relevant information and documents.

Additionally, according to the needs of the specific value chains, Anteja can support phy2app with its own blockchain technology traceability system that ensures the fidelity of the information shared.

Where does AI fall into place?

The information collected by each value chain actor can be used for making informed business decisions, but it needs to be correctly interpreted and analysed. The second biggest challenge in the agribusiness value chains is producing actionable business intelligence by leveraging the collected data. AI and machine learning (ML) can play a major role in identifying new business opportunities, detecting potential quality issues, and predicting supply.

AI use cases in agribusiness value chains

The artificial intelligence applications are broad, ranging from detecting plant diseases to informing national agricultural policies about the prediction of gaps between food production and consumption (Omran, 2010).

Artificial intelligence fosters agriculture that produces more by using fewer resources. QU Dongyu, FAO Director-General, emphasises the importance of a “transparent, inclusive, socially beneficial and accountable AI” (Mayer, 2020).

Also, the current pressure on the agricultural supply chains to produce large quantities of high-quality crops multiplies the risks of being exposed to food safety scandals and contamination (Marjou, 2021). To overcome food safety issues in developing countries, AI should be prioritised in the supply chains that include staple crops (wheat, maize, rice, and soybean) (Tzachor, 2020) and high-nutritional value products.

In this perspective, AI serves as a risk mitigation tool, as potential food safety issues can be detected before they affect the entire value chain. AI and ML can help the agribusiness value chain actors to analyse crop stresses, such as water shortages, soil chemistry, and diseases in real-time (Dugbazah, 2021). In Europe, AI is expected to accelerate the transition towards healthier consumption by reducing the use of fertilisers, pesticides, and irrigation (European Parliament, 2021).

AI platform predicting crop production. Adobe Stock Photo.

Here are some of the most notable AI use cases:

  1. An AI-powered machine helps to conduct a real-time product inspection and ensures food safety at the shipping, processing, and wholesaling stages. However, it requires significant capital expenditures to implement and operate such machinery, capable of analysing products at each step, which reduces the value chain flexibility.
  2. An AI platform that predicts crop production and analyses market behaviour trends to maximise the food supply chain’s efficiency.
  3. An AI tool that automatically scans online communication posts to check their compliance with the company’s code of conduct or sustainability criteria.

Value Chain Generator

The University of Applied Sciences and Art in Western Switzerland has developed an AI and ML-powered solution called the Value Chain Generator (VCG). VCG is a software solution aiming to establish the most suitable trade connections in value chains. It uses AI and ML to connect value chain actors from different sectors and countries to create novel bio-based value chains. The system identifies possible linkages between buyers and suppliers of a variety of products and by-products. By identifying such business opportunities, the system can help suppliers reduce waste and maximise their profits, making value chains more sustainable, efficient, and lucrative.

Value Chain Generator. Courtesy EU Interreg AlpLinkBioEco.

Artificial intelligence and machine learning will play key roles in strengthening value chain sustainability as they can ensure the quality of information that circulates in the supply chains. AI and ML are popular tools in the emerging agricultural technologies (agtech), which can increase yield, reduce food safety factors, improve crop quality and allow quicker go-to-market strategies.

This article was written by Alexis Mallet, Jon Goriup Dermastia and Martina Vilhar.


Table of Contents