“In the vertical farm, the main operating costs are attributable to energy use, with artificial lighting being one of the key components. Reducing this cost is critical if controlled ecological farming is to become a more profitable method of production, and this is a key component,” says Dr. Rakibel Islam, Researcher In Biomedical Sciences at Photosynthetic, a subsidiary of Rift Labs, “The problem we’re trying to solve with our technology.”
He explains that the Photovoltaic R&D Laboratory provides a platform for scientific testing by comparing environmental variables side-by-side while monitoring plant growth. It provides valuable insight into reducing resource waste by adjusting, for example, photoperiod, wavelength, temperature, etc., for optimum plant growth. It provides the vertical farmer with a recipe for energy-saving plant growth, which can be implemented in the production environment.
As a researcher, Rakibul has always had a keen interest in artificial intelligence. He has been working in a leading AI research group, developing and evaluating the application of AI in cancer diagnosis and disease prognosis. Though, at Photosynthetic, Rakibul’s role is to create AI solutions for farmers.
“It was very rewarding to see the great potential of using my knowledge of AI to help CEA become more efficient by creating smart processes and workflows. Working on this project satisfies both my hobby of growing plants and my intellectual curiosity.”
Grow together with the farms
PhotoSynthetic’s expertise lies within data generation and precise control of plant growth inputs using its proprietary software and patented technology for mixing light of different wavelengths. For example, with a stand-alone R&D lab, farmers can better understand the environmental needs of a candidate crop, allowing experiments to be conducted for efficiency without compromising plant physiology.
By controlling the environmental conditions in this R&D lab, one can recreate a “problem state” for farmers to generate highly relevant data necessary for training machine learning models. The stored data for optimal growth can be used to simulate growth and to predict computational harvest time.
“We don’t just make a product for farmers, we do it with them. Through “photosynthesis” technology, our goal is to establish ourselves as a research partner and technology resource for farmers around the world. We have a data-centric approach where we want to leverage our expertise in photobiology and provide solutions Smart helps our customers to continually improve the production process.”
Since artificial intelligence is a large field; It is usually used interchangeably for machine learning (ML), deep learning (DL), and so on. It consists of a set of tools that allow computers to learn without being explicitly programmed, explains Rakibull.
“Traditional programs are based on rules, where exact instructions are given to a computer to solve a problem, which means we need input and rules to provide an output. In machine learning, we need previous input and output to train a model so that it can predict the output when it gets new inputs. Machine learning applications are all around us today; most importantly, they are useful,” says Rakibull.
For example, a machine learning model works behind the screen when you unlock your phone using the face recognition system. Spam filters in your email, search engine results, and movie recommendation system on Netflix; They are also models for machine learning. There are applications for AI in drones and talking robots, so it’s not entirely wrong to imagine them when you think of AI.
“We must keep in mind when designing technology to help productivity so that it not only looks good, but adds value to users by reducing unnecessary work and complexity. The best AI products and services are often invisible and seamlessly integrated into workflows.”
The current role of AI in CEA
According to Rakibull, CEA is one of the ideal candidates for harnessing the power of artificial intelligence. This is because CEA is designed to control and monitor growing conditions to improve the sustainability of agricultural production. Farmers make their decisions according to the controlled variables to improve resource use, productivity, quality, profitability, and sustainability.
AI may play a role in these areas; For example, it can improve electricity consumption, which is one of the biggest cost drivers in CEA; automation of processes to increase productivity; improve plant growth and predict productivity to reduce uncertainty; Detection of inferior products to ensure quality.
“The technological capacity is there. However, the thing is that there are no off-the-shelf solutions. These solutions are data-driven and, therefore, have to be built in collaboration with farmers, based on what kind of improvement they need,” he notes.
Optimizing production with artificial intelligence
Indeed, AI solutions in indoor plant production require a remarkably diverse range of expertise. Coding a machine learning model is, of course, an important part but not the only part of it and not even the biggest challenge. AI development includes many different aspects of the complex infrastructure surrounding model development such as data collection, feature extraction, infrastructure servicing, monitoring, etc.
“However, I consider AI to be one of the many interesting tools that we can use to increase yield and reduce production costs in indoor plant production. In my opinion, it has huge potential, which has not yet been fully explored. We work with AI through our multiple team Specializations, which consists of plant scientists, AI product managers, mechatronics, electronics, and software engineers, to support our customers by helping to scope and frame their challenges as machine learning issues to be solved, support decision making, and ultimately improve the production process.”