Citation

Al Qwaid, Marran and Sarker, Md Tanjil and Hossen, Md Sabbir and Shawon, Sarowar Morshed and Abdul Karim, Hezerul (2026) A hybrid ANN–RF and IoT-enabled framework for water energy optimization in arid smart farming: Evidence from Saudi Arabia. Smart Agricultural Technology, 14. p. 102098. ISSN 2772-3755

Text 1.pdf - Published Version Restricted to Repository staff only Download (5MB)

Abstract

Saudi Arabia faces persistent agricultural sustainability challenges due to extreme water scarcity, harsh climatic conditions, and increasing food demand driven by population growth. This study proposes a Hybrid Artificial Neural Network–Random Forest (ANN–RF) and Internet of Things (IoT)-enabled smart farming framework to optimize water, energy, and nutrient use in arid agricultural systems. The framework integrates real-time IoT sensing, hybrid AI-based prediction, and renewable-energy-powered irrigation actuation within a closed-loop architecture suitable for desert environments. A one-hectare wheat and date-palm field in the Al-Qassim region was modeled using MATLAB/Simulink and Python analytics to simulate realistic arid-environment operating conditions. The hybrid ANN–RF model was trained on twelve months of soil and climate data and evaluated using cross-validation. Results demonstrate substantial improvements in resource efficiency, including a 38.5% reduction in irrigation water usage, 22.6% energy savings, and a 26.7% increase in crop yield compared with conventional irrigation. The hybrid predictor achieved strong performance (R2 = 0.93; RMSE = 0.15 m3/ha). Renewable-energy integration further reduced carbon emissions by 24.4%, while the sustainability efficiency index improved from 0.56 to 0.81. These findings confirm that hybrid AI-driven IoT systems offer a scalable, climate-resilient, and economically viable solution for transforming agriculture in line with Saudi Vision 2030 and the Saudi Green Initiative. The proposed framework demonstrates strong potential for scalable deployment in arid agricultural environments, subject to further validation across multiple farms and seasonal conditions.

Item Type:	Article
Uncontrolled Keywords:	Smart farming, Internet of things (IoT), artificial intelligence (AI
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science S Agriculture > S Agriculture (General)
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	04 May 2026 00:57
Last Modified:	07 May 2026 04:42
URII:	http://shdl.mmu.edu.my/id/eprint/15801

Downloads

Edit (login required)