What we do
TCS Research
TCS Research: Inventing to build sustainable futures
HIGHLIGHTS
- Resolving food waste problem by monitoring and estimating the freshness of food in real time using novel digital twin technology.
- The system is trained to virtually assess food quality by observing physical and chemical degradation properties over time and replicating the patterns in digital twins.
- The platform helps stakeholders to take dynamic decisions relating to modified logistics and changes in environmental conditions.
On this page
On this pageinpage
The smart technology
Over one-third of the food produced in the world gets lost in transit or wasted along the supply chain. TCS Research uses novel digital twin technology to solve the problem by monitoring and estimating the freshness of food in real time.
TCS Research scientists detail the approach to solve the food wastage problem in this video.
Smart technology to reduce food waste
Reducing food waste
Food wastage is at the level of a global crisis. Producers, logistics companies, governments, food health enforcement bodies, sustainability advocates, and concerned citizens are trying multiple options to reduce wastage. Real-time monitoring of food quality has emerged as a viable solution that can benefit all stages of the food supply chain, starting from farmers to end consumers like us. It helps reduce significant economic losses which occur due to food spoilage and wastage while retaining quality and nutritional value. A novel integrated ‘smart digital platform’ is being developed to estimate and predict the food quality. This will enable all the stakeholders of the food supply chain to make dynamic decisions regarding altering supply chain logistics and storage conditions, to repurpose and minimize food spoilage and wastage.
Roughly one-third of the food produced in the world for human consumption every year—approximately 1.3 billion tonnes—gets lost or wasted. A large amount of food produced gets wasted in different parts of the supply chain such as farms, storehouses, logistics, and processing units (Figure 1). Along with this, a significant amount of food wastage is also experienced at the consumer end. Of the total global food wastage, 40–45% is fruits, vegetables, and root crops.
Food wastage and spoilage within the food supply chain can be attributed to uncertainties in demand and supply, time delay, and changes in environmental conditions at different stages of the food supply chain. This is equivalent to an annual economic loss of USD 1.2 trillion. It also causes a significant environmental footprint amounting to about 8% of greenhouse gas emissions worldwide.
A platform that can gather data from multiple types of sensors, with data processing capabilities, can provide much value in reducing wastage.
Fact File
TCS Research: Physical sciences
Outcomes: Novel platform for estimation of food freshness and shelf life, development of sustainable food supply chains, decision-making system for food retail, consumer guidance system on quality and nutritional value of food
Principal investigator: Dr. Beena Rai
Techniques used: Chemical lab experiments, physics-based models, artificial intelligence, data analytics, sensing and IoT, cloud computing
Industries benefited: Food supply chain, food processing, and healthcare/wellness
As a result, food and drink manufacturers, supply chain managers, retailers, governments, health authorities, consumer forums, sustainability-focused NGOs, and responsible citizens are all keen on reducing food wastage.
A farm to plate view
Concerned groups are looking at multiple ways of reducing waste in storage and along the supply chain. Some leading carriers are already equipping their containers with sensors and connecting them to a platform.
A platform that can gather data from multiple types of sensors, with data processing capabilities, can provide much value in reducing wastage. In order to optimize supply chain logistics, it is necessary to equip all stakeholders—from farmers to end-consumers—with dynamic decision-making capabilities and real-time monitoring of various parameters.
Framework for real-time food quality monitoring in supply chain.
Such a system enables quick decisions on early offloading, rerouting, ramping-up storage, and even food repurposing, to extend shelf life. The continuous monitoring and prediction of food quality at all stages of the food supply chain can create direct savings for stakeholders and result in many indirect benefits for the larger community–stable food prices and reduced environmental impact.
TCS’ smart food freshness monitoring platform
TCS’ platform (Figure 2) for predicting food quality is built using a collection of internet of things (IoT)-enabled sensors which senses galvanic skin resistance (GSR), near infrared (NIR) imaging, ultrasound, pH, air quality, gas composition (CO2, NH3, C2H4, O2, etc.), weight, volatile organic compound (VOC) content, camera feeds, and chemically analyzed food parameters. This is coupled with data analytics, image processing, and cloud computing.
This platform allows provision for variation of environmental conditions such as temperature, humidity light intensity, etc. thus simulating the conditions like those experienced by food in the field, during storage and in transit. The platform incorporates a modular framework. It consists of a custom designed enclosure where different supply chain scenarios can be simulated.
A platform to monitor food quality
The enclosure consists of a multimodal sensor suite with a modular framework and is inclusive of multiple IoT-enabled sensors. The sensors and offline data are interfaced with digital media via a Bluetooth Low Energy (BLE) module or a WiFi module.
The data is further sent to the cloud to allow real-time monitoring of the sensed parameters across the globe.
The platform incorporates hybrid models (AI/ML/physics-based) built on non-invasive sensory and offline lab data simulating all possible supply chain scenarios. These act as soft sensors in the real-time prediction of food quality.
Multivariate, multimodal, synchronized, time series, online and offline lab data collected at predefined intervals have been used to train these models to accurately predict food quality.
These hybrid models provide a standardized digital signature of the food and enable prediction of its quality, freshness index, and remaining shelf life. The predictions enable development of a feedback system, which allows alteration of the environmental conditions to increase shelf life or repurpose the food (such as ship it to a nearby location or take other appropriate alternatives), in turn reducing food wastage.
This platform, once deployed in a real-world scenario, will assist stakeholders to take dynamic decisions relating to modified logistics and changes in environmental conditions. Thus, this platform will help in building sustainable supply chains and reducing impact of global food wastage on hunger, the economy, and the environment.
Predicting ripening time
The TCS smart food monitoring platform is used to predict ripening duration of climacteric fruits (banana, mango, papaya, etc.) and predicting shelf life of potatoes for different customers.
Climacteric fruits need a lot of flexibility in a supply chain. Overripe fruits become soft and must be handled with much more care; the act of ripening releases ethylene which may affect the ripening of other fruits close by.
The TCS platform is used to study the natural ripening process of climacteric fruits, both for a farmer and a leading metro retailer. It helped prevent over ripening, by prompting variation of environmental conditions. This platform monitors the quantitative variation in the quality of “Cavendish—a highly produced banana cultivar” w.r.t. ripening index (RI). Combined quantitative sensing of O2, CO2, sugar content, and images during ripening stages of banana were used to calculate the respiration rate (RR) and establish correlation between RR and banana ripening index (RI) to find an optimal ripening schedule. Further, the platform is used to predict the ideal ripening duration and factors affecting the natural ripening process at different environmental conditions.
For the retailer, real-time information on changing quality and remaining time for ideal ripening is provided so that the store could introduce dynamic price against quality grading. For example, if there are three stacks of bananas with different ripening durations, they can be priced differently to ensure economic benefits and waste reduction.
The platform is also used to predict shelf life of potatoes for different supply chain scenarios. Potatoes have different uses such as the production of chips and fries, potato starch for domestic consumption. The supply chain for potatoes includes harvesting, curing, storage, processing, and logistics etc. Our platform predicts the shelf life of different varieties of potatoes at different environmental conditions for different applications in terms of weight loss, sprouting, fungal growth, change in sugar content and dry matter.
Our platform with soft sensor technology coupled with precision modeling and digital imaging can revolutionize existing food supply chains.
