Artificial Intelligence in Post-Harvest Drying Technologies: A Comprehensive Review on Optimization, Quality Enhancement, and Energy Efficiency

Azmirul Hoque

Abstract: Post-harvest drying is an important procedure for preserving agricultural products, since it prolongs shelf life, reduces post-harvest losses, and maintains food quality. Conventional drying techniques can result in inconsistency in product quality and inefficiencies in energy use. The integration of artificial intelligence (AI) with novel drying technologies, such as refractance window drying, microwave drying, freeze-drying, and hot air drying, presents viable solutions to these difficulties. This research examines the utilization of AI methodologies, such as machine learning, deep learning, and predictive modeling, to optimize drying parameters, improve product quality, and minimize energy usage. This study analyzes the improved functionality of real-time monitoring and flexible oversight with AI-driven models predicting ideal temperature, humidity, airflow, and drying duration depending on product attributes. Moreover, AI applications in quality prediction provide accurate regulation of moisture content, color, texture, and nutritional characteristics, leading to excellent dried products. Challenges including data quality, model interpretability, scalability, and adaption to various drying systems are also addressed. This analysis emphasizes potential possibilities for enhancing AI in post-harvest drying, focusing on AI's potential to promote sustainable and efficient drying methodologies within the agricultural sector.

Keywords: Artificial intelligence, Post-harvest drying, Quality optimization, Energy efficiency, Machine learning, Refractance window drying

How to Cite?: Azmirul Hoque, "Artificial Intelligence in Post-Harvest Drying Technologies: A Comprehensive Review on Optimization, Quality Enhancement, and Energy Efficiency", Volume 13 Issue 11, November 2024, International Journal of Science and Research (IJSR), Pages: 493-502, https://www.ijsr.net/getabstract.php?paperid=SR241107163717, DOI: https://dx.doi.org/10.21275/SR241107163717