Sign up for our daily Newsletter and stay up to date with all the latest news!

Subscribe I am already a subscriber

You are using software which is blocking our advertisements (adblocker).

As we provide the news for free, we are relying on revenues from our banners. So please disable your adblocker and reload the page to continue using this site.
Thanks!

Click here for a guide on disabling your adblocker.

Sign up for our daily Newsletter and stay up to date with all the latest news!

Subscribe I am already a subscriber

How AI is aiding growers in vertical farming

AI-driven automation in soilless farming systems significantly enhances crop yields, optimizes resource use, and boosts sustainability, reveals a new study published in Sustainability. The findings emerge from a systematic literature review "Optimization of Vegetable Production in Hydroculture Environments Using Artificial Intelligence: A Literature Review," conducted by researchers from Universidad Nacional Mayor de San Marcos (UNMSM).

Hydroculture - an umbrella term for soilless cultivation techniques such as hydroponics, aeroponics, and aquaponics - has become increasingly vital amid global food insecurity, shrinking arable land, and accelerating climate change. The study notes that hydroponics remains the most widely adopted method, owing to its effectiveness in managing plant nutrition via water-based delivery systems. Among the techniques examined were the Nutrient Film Technique (NFT), Deep Water Culture, Wick System, and newer digital-twin-based smart systems.

The study assessed 72 peer-reviewed articles published between 2020 and 2024. It found that integrating AI with Internet of Things (IoT) sensors and Big Data analytics in hydroponics, aquaponics, and aeroponics has led to major improvements in nutrient management, water efficiency, energy use, and disease detection.

Key performance gains were attributed to a suite of AI models including Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), Fuzzy Logic (FL), Random Forest (RF), Support Vector Machines (SVMs), and Recurrent Neural Networks (RNNs). DNNs were particularly effective, achieving up to 97.5% accuracy in predicting crop growth and enabling real-time automated nutrient adjustment. CNNs demonstrated over 99% precision in pest and disease detection, allowing for early intervention and reducing pesticide dependency.

Read more at Dev Discourse