[Paper Review] Artificial Intelligence in Sustainable Vertical Farming

Hribhu Chowdhury, Debo Brata Paul Argha+1 more|arXiv (Cornell University)|Nov 17, 2023

Smart Agriculture and AI9 citations

TL;DR

The paper reviews how AI technologies such as machine learning, computer vision, IoT, and robotics can enhance sustainable vertical farming, discusses current applications, challenges, and future research directions.

ABSTRACT

As global challenges of population growth, climate change, and resource scarcity intensify, the agricultural landscape is at a critical juncture. Sustainable vertical farming emerges as a transformative solution to address these challenges by maximizing crop yields in controlled environments. This paradigm shift necessitates the integration of cutting-edge technologies, with Artificial Intelligence (AI) at the forefront. The paper provides a comprehensive exploration of the role of AI in sustainable vertical farming, investigating its potential, challenges, and opportunities. The review synthesizes the current state of AI applications, encompassing machine learning, computer vision, the Internet of Things (IoT), and robotics, in optimizing resource usage, automating tasks, and enhancing decision-making. It identifies gaps in research, emphasizing the need for optimized AI models, interdisciplinary collaboration, and the development of explainable AI in agriculture. The implications extend beyond efficiency gains, considering economic viability, reduced environmental impact, and increased food security. The paper concludes by offering insights for stakeholders and suggesting avenues for future research, aiming to guide the integration of AI technologies in sustainable vertical farming for a resilient and sustainable future in agriculture.

Motivation & Objective

• Motivate the adoption of sustainable vertical farming amid population growth, climate change, and resource scarcity.
• Explore how AI can maximize crop yields in controlled environments.
• Synthesize current AI applications and identify gaps, challenges, and opportunities.
• Assess economic viability and environmental impact to support resilient agricultural systems.
• Suggest avenues for interdisciplinary collaboration and explainable AI in agriculture.

Proposed method

• Review of existing literature on AI in sustainable vertical farming across AI subfields (ML, computer vision, IoT, robotics).
• Synthesis of how AI enables resource optimization, automation, and data-driven decision making.
• Critical analysis of gaps such as model optimization, interdisciplinary collaboration, and explainable AI.
• Discussion of implications for economic viability, environmental impact, and food security.
• Provision of stakeholder-oriented insights and future research directions.

Experimental results

Research questions

• RQ1 What is the current state of AI applications in sustainable vertical farming?
• RQ2 What are the main challenges and gaps hindering widespread adoption?
• RQ3 How can AI models be optimized and made explainable for agricultural use?
• RQ4 What are the economic and environmental implications of AI-enabled vertical farming?
• RQ5 What future research directions and collaborations are most promising for sustainable adoption?

Key findings

• AI applications span machine learning, computer vision, IoT, and robotics in vertical farming.
• AI can optimize resource usage, automate tasks, and improve decision-making in controlled environments.
• There are gaps in optimized AI models, interdisciplinary collaboration, and the development of explainable AI for agriculture.
• Economic viability and environmental impact considerations are central to broader adoption.
• The paper provides stakeholder-oriented insights and future research directions to guide AI integration in sustainable vertical farming.