Scalable agritech growbox architecture

Introduction: Urban farming has gained prominence in Singapore, offering opportunities for automation to enhance its efficiency and scalability. This study, conducted in collaboration with a leading Singaporean urban farming company, introduces an IoT-based automated farming system. This system incorporates an agnostic growbox and a web application dashboard for intelligent monitoring of crop growth. The presented approach provides an open-source and cost-effective solution for a scalable urban farming architecture. The agnostic growbox system offers both accessibility and scalability, utilizing cost-effective and modular hardware components with open-source software, thereby increasing customizability and accessibility compared to commercial growbox products. The authors anticipate that this approach will find diverse applications within the realm of urban farming, streamlining, and improving the efficiency of urban farming through automation. Methods: The study employs an integrated solution that incorporates an image analytics approach for the proficient and accurate classification of crop disease phenotypes, specifically targeting chlorosis and tip burn in lettuce crops. This approach is designed to be hardware- and software-efficient, obviating the necessity for extensive image datasets for model training. The image analytics approach is compared favourably with a machine learning approach, evaluating the accuracy of categorization using the same dataset. Additionally, the approach is assessed in terms of time and cost efficiency in comparison to machine learning techniques. Results: The image analytics approach demonstrated notable scalability, time efficiency, and accuracy in the detection of crop diseases within urban farming. Early detection, particularly of chlorosis and tip burn, proves critical in mitigating crop wastage. The results indicate that the integrated solution provided a reliable and effective means of disease classification, with significant advantages over traditional machine learning approaches in terms of time and cost efficiency. Discussion: The presented IoT-based automated farming system, incorporating the agnostic growbox and image analytics approach, holds promise for revolutionizing urban farming practices. Its open-source nature, coupled with cost-effectiveness and scalability, positions it as a practical solution for urban farming architecture. The system's ability to efficiently detect and classify crop diseases, particularly chlorosis and tip burn, offers a substantial contribution to reducing wastage and enhancing crop yield. Overall, this approach paves the way for a more efficient and sustainable future for urban farming through the integration of automation and advanced analytics. Further exploration and implementation of this technology in diverse urban farming settings is warranted.