Research in Vertical Farming

Aquaponics, one of the vertical farming methods, is a combination of aquaculture and hydroponics. To enhance the production capabilities of the aquaponics system and maximize crop yield on a commercial level, integration of Industry 4.0 technologies is needed. Industry 4.0 is a strategic initiative characterized by the fusion of emerging technologies such as big data and analytics, internet of things, robotics, cloud computing, and artificial intelligence. Modern vertical farms can leverage disruptive digital technologies such as the internet of things (IoT), cyber-physical systems (CPS), artificial intelligence (AI), wireless sensor networks (WSN), big data and analytics (BDA), an autonomous robot systems. Aquaponics 4.0 system at AllFactory, provides complete digital and physical platforms based on a smart farming concept that uses all these technologies to improve systems’ design and operation by ensuring autonomous monitoring and control and intelligent data-driven decisions in the fast-processing pervasive environment.

Featured Research Projects

Some of the featured projects are presented below:

1) Digital Twin and Cyber-Physical System in Aquaponics:

This research project aims to adopt the digital twin method in the growing beds of an aquaponics system for monitoring real-time parameters, namely pH, electroconductivity, water temperature, relative humidity, air temperature, and light intensity. It supports the use of artificial intelligence techniques to, for example, predicts the growth rate and fresh weight of the growing crops. The digital twin model developed and presented is based on IoT technology, databases, centralized control of the system, and a virtual interface that permits users to have full control and visualizes the state of the aquaponic system in real time.

2) Quality control and computer vision applications in vertical farming

The lack of intelligent real-time approaches to monitor and track plant growth is hindering the transition of aquaponic systems towards automation and commercialization. Computer vision can promote further contributions to smart applications in aquaponics; therefore, a methodology is proposed to measure the growth rate and fresh weight of crops in multi-instance setups in real-time. The proposed system uses image-processing techniques, deep learning, and regression analysis to estimate the size of the crops as they grow using image segmentation. Then, a correlation between the size of the crops and their fresh weight is modelled. For common little gem romaine lettuce, the size of crops and fresh weight is estimated with an overall error of 30 mm (18.7%) and 0.5 g (8.3%), respectively.

3) Robotics in Agriculture:

Today’s advancements in Robotics, Computational Intelligence, Information Technologies and Hydroponics allow for very advanced and automated agriculture. This project aims to leverage all these advancements to bring about the next generation of farming and other agricultural equipment. We envision tomorrow’s companies using our framework like John Deere or New Holland, which built their empire on top of the Internal Combustion Engine.
As humanity ventures forward, agriculture will advance along with it. We are setting the stage for the second agricultural revolution, where food production is highly automated and requires little to no human supervision.

4) Artificial Intelligence and data modeling applications in aquaponics:

The realization of aquaponics 4.0 requires an efficient flow and data integration due to complex biological processes. A key challenge in this essence is to deal with the semantic heterogeneity of multiple data resources. An ontology that is regarded as one of the normative tools solves the semantic interoperation problem by describing, extracting, and sharing the domains’ knowledge. In the field of agriculture, several ontologies are developed for the soil-based farming methods, but so far, no attempt has been made to represent the knowledge of the aquaponics 4.0 system in the form of an ontology model. Therefore, this study proposes a unified ontology model, AquaONT, to represent and store the essential knowledge of an aquaponics 4.0 system. This ontology provides a mechanism for sharing and reusing the aquaponics 4.0 system’s knowledge to solve the semantic interoperation problem. AquaONT is built from indoor vertical farming terminologies and is validated and implemented by considering experimental test cases related to environmental parameters, design configuration, and product quality. The proposed ontology model will help vertical farm practitioners with more transparent decision-making regarding crop production, product quality, and facility layout of the aquaponics farm. For future work, a decision support system will be developed using this ontology model and artificial intelligence techniques for autonomous data-driven decisions. This study also gives practitioners the capacity to visualize the impact of the desired crop selection on the aquaponic system design, as well as supporting clearer decision-making regarding production facility layout and system design in aquaponic farms.