An AI-Integrated Renewable-Powered Cold Storage System with Advanced Environmental Sensing for Smallholder Farmers
Engineering, Technology & Applied Science Research · 08.12.2025 · 15 (6) · 29391-29396
DOI: 10.48084/etasr.13983 ↗Kurz gefasst
Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 08.12.2025. Verfasst von Sahana D. Gowda und 1 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 14 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Smallholder farmers often face significant post-harvest losses due to the lack of affordable and efficient cold storage infrastructure, which limits their ability to maintain production quality and capitalize on favorable market conditions. Conventional storage systems are energy-intensive, rely on grid power, and lack real-time monitoring or predictive spoilage management. To address these challenges, this study presents an AI-integrated renewable-powered cold storage system equipped with advanced environmental sensing and an edge-based Long Short-Term Memory (LSTM) model for spoilage prediction and freshness assessment. The proposed method combines solar Photovoltaic (PV) energy, Phase Change Material (PCM)-assisted hybrid cooling, multi-sensor environmental monitoring (temperature, humidity, CO2, ethylene, and NIR spectral sensing), and edge AI-powered freshness indexing to enable proactive quality control and informed market dispatch decisions. Experimental validation demonstrated a 28% reduction in grid energy use, shelf life extension of up to 4×, high spoilage prediction accuracy (RMSE: 0.47 days, MAE: 0.31 days), and a 22% increase in farmer income with a 2.1× RoI over three years. These findings establish the proposed system as a scalable, energy-efficient, and intelligent solution for reducing post-harvest losses and enhancing socio-economic outcomes for smallholder farmers. Future work will focus on scalable AI model enhancements, blockchain-based traceability, and dynamic pricing intelligence to further strengthen system performance and impact.
Zitieren
APA
Gowda, S. D., & Raj, K. T. (2025). An AI-Integrated Renewable-Powered Cold Storage System with Advanced Environmental Sensing for Smallholder Farmers. Engineering, Technology & Applied Science Research, 15(6), 29391-29396. https://doi.org/10.48084/etasr.13983
Vancouver
Gowda SD, Raj KT. An AI-Integrated Renewable-Powered Cold Storage System with Advanced Environmental Sensing for Smallholder Farmers. Engineering, Technology & Applied Science Research. 2025;15(6):29391-29396. doi:10.48084/etasr.13983
BibTeX
@article{Gowda2025,
author = {Gowda, Sahana D. and Raj, Kamal T.},
title = {An AI-Integrated Renewable-Powered Cold Storage System with Advanced Environmental Sensing for Smallholder Farmers},
journal = {Engineering, Technology & Applied Science Research},
year = {2025},
volume = {15},
number = {6},
pages = {29391--29396},
doi = {10.48084/etasr.13983}
}
EUVIMED