This bulletin aims to introduce Artificial Intelligence and Machine Learning, and provide examples of how these new technologies can be used in vertical farming systems.
Artificial Intelligence (AI) is a term used to describe how machines are used to imitate human skills and emulate human intelligence. The added value created by AI is projected to reach $13 trillion across all industrial sectors by 2030, and $164 billion in the agriculture sector (Source: McKinsey Global Institute).
There are two main categories of AI:
- Artificial intelligence (Artificial narrow intelligence – ANI); AI that does one thing, e.g. smart speaker, self-driving car, web search, AI in agriculture and manufacturing.
- Artificial intelligence (AGI), which does anything that a human can do. The biggest progress made in ANI and to a lesser extent in AGI, which – while exciting to new researchers – is some time away.
AI solves problems differently from traditional computing, which takes rules and data as input and output results. AI solves problems with no pre-programmed rules.
Machine Learning (ML), the driving force for AI, takes data and results as the collective rules of inputs and outputs. A process of training leads to AI finding patterns and relationships between data and results and creating its own rules for how they relate to each other. AI solves problems that we do not know how to solve ourselves. Machine learning systems are built with artificial neural networks (ANNs), also known as neural networks. Artificial neural networks are inspired by the biological neural networks that make up a biological brain. Artificial neural networks learn to perform tasks by considering examples, but not programmed with any task-specific rules.
Artificial Intelligence and Vertical Farming
In vertical farming, artificial intelligence can be used to produce greater yields and improved efficiencies, by making the best use of nutrients and water. It can also be used to improve crop quality in terms of taste and nutrition.
A start-up Tech Agriculture company, Plenty www.plenty.ag from San Francisco uses AI and robotics to continuously improve the quality of crop growth, using 95% less water and 99% less hand. This is achieved through Controlled Environment Agriculture (CEA) technology that uses AI to control the temperature, humidity and gases in the atmosphere.
AI enables continuous optimisation of these variables through self-learning with Machine Learning about how to grow larger, faster and better quality crops. Plenty uses robots to carry large racks of growing vegetables, moving them to where they are needed. LED panels are used in place of sunlight, resulting in food grown 24/7 inside vertical farms. AI also helps regulate the combination of blue, red and white light to maximise plant growth as they respond to different wavelengths of light. By partnering with Cambridge-based AI company Agxio, Tech Tyfu aims to trial new remote sensing and AI technologies in the Innovation Hub to identify pests before crop damage can occur, and create new avenues for AI development.