Employing Agtech and AI at each stage of the crop production lifecycle

Employing Agtech and AI at each stage of the crop production lifecycle, the benefits are clear but how best we store and are able use the data and outputs for analysis?

Jon Mann

Executive Chairman and Financial Sector Advisor

Technical Level: Intermidiate


The agriculture industry has changed enormously over the past few years. Advances in machinery have expanded the scale, speed, and productivity of farm equipment, leading to more efficient cultivation of more land. Seed, irrigation, and fertilisers also have vastly improved, helping farmers increase yields. Agriculture is going through yet another gyration, at the heart of which lie data, connectivity and analysis. Artificial intelligence, analytics, smart contracts, connected sensors, and other emerging technologies is increasing yields.

Without a solid and robust platform to store, map and analyse the data, much of the momentum is lost.

The world’s population is on track to reach 9 billion by 2050. Add to that continuing challenges around energy, input and labour costs, water supply and arable land shortages, ever changing weather patterns and increased ethical behaviour; the onus of reaping the advancements in agtech and AI has never been more immediate.  

This paper will look at the various crop production cycle stages, the relevant agtech, AI applications and benefits, and a solution of how and where to store, analyse and use such data.

A crop’s lifecycle goes through the following stages.

Crop Lifecycle Agtech

Preparation of soil: The initial stage of farming preparing the soil for sowing seeds.

AI systems can conduct chemical soil analyses and provide accurate estimates of missing nutrients as well as the moisture content of the soil. More use of robotics.

More confidence from farmers around the heath of the soil pre planting and faith that the farmer has found an area of soil giving the best chance of the crop to grow. Automated machinery means more efficiency and less reliance on manual labour.

Sowing of seeds: The distance between two seeds, is important here. At this stage climatic conditions such as temperature, humidity, and rainfall are relevant.

Gene edited seeds, machine learning

Results in seeds being less dependent on water and fertiliser. Data from machine learning models educate farmers in knowing what type of seed to plant for success

Fertilisers: Farmers use fertilisers because these substances contain plant nutrients. This stage determines the quality of the crop

The use of soil sensors and use of AI extracted

These sensors confirm existing nitrogen levels in the soil helping to reduce the overuse of fertilisers and pesticides and their negative effects

Irrigation: Underwatering or overwatering hinders the growth of crops and if not done properly it can lead to a poor crop

Water sensors and information around plant behaviour

Water sensors help detect leaks in irrigation systems. Information and data gleaned from plant behaviour inform us as to whether or not a plant is in need of water or not

Weed protection: Weeds are unwelcome plants and decrease yields, increase production costs and lower crop grading

Smarter, automated machines

Such machines can detect the difference between a plant/crop and a weed in real time. Consequently, any fertiliser or pesticide is only targeted on the weed, helping the issue of overfertilisation. Automated weeding is on the increase

Harvesting: This is a labour-intensive task, including the cleaning, sorting, packing, and cooling of the produce

Drones, driverless tractors

Harvesting becomes more automated; drones help predict best time to harvest

Storage: Crops need to be kept in such a way as to procure quality and food after harvesting.

High tech greenhouses, warehouses

Real time information around air pressure, humidity and temperature helps increase the chance of maintaining a good crop during the storage/warehousing phase. More secure warehouses help with issues around food security and theft. Improvements in AI around traceability helps locate the whereabouts of the produce

How best we store and analyse the data and outputs from these various stages of a crop’s lifecycle?

In order to leverage off the data and intelligence picked up by the AI and advances in agtech mentioned above, there is a need for a state of the art robust ledger or asset registry platform on which one can store all the data. This applies as to whether one is involved in only one, several or all of the stages of a crop’s production cycle.

About EyA Global

At EyA we have built that which we consider to be one of the world’s most powerful enterprise grade distributed ledgers (DLT) as a full, easy to integrate stack of technologies. The aim is simple, to better enable users to store and manage their data. EyA’s platform is fast, inexpensive (as compared to other ledgers), more secure, easily scalable and energy efficient. The various elements and components of all assets and components within the ledger, if required, can be broken down to the nth degree (e.g., each individual component of a soil sensor or driverless combine harvester).

In addition, EyA’s platform can communicate and be plugged into any other existing (legacy) systems. Only permissioned users will have access to the platform, but the industry can also expose public data including traceability, lifecycle data and allergens to the end consumer.

So, imagine that as a farmer or somebody involved in crop production, all of your data is available on one easy to use platform, At the click of a finger, courtesy of EyA’s ground-breaking technology, every single particle/component of each and every asset on the platform/ledger is able to communicate with each other in a non-linear manner. In other words, in the above crop production lifecycle example, data of any and every component, from any stage, can be seamlessly linked together. Not only that, EyA have managed to inject a relational database function into their distributed ledger. So, in short asset data points on the ledger are inter related and the scope for analysis of the assets is boundless.

Thinking upon this, it means that everything from the soil, to the machinery, to the supply chain has a unique digital twin, streaming use and lifecycle data into the ledger. Combine this with data streaming from ecological and environmental organisations and forward planning, economics and even consumer demands are predictable and obtainable when joined into a true cross-pollinated ecosystem of intra-organisational and intra-industry rich data.

Are you visiting from outside the UK? Visit your regional site for more relevant promotions and events.