The findings are particularly relevant as agriculture remains the world's largest consumer of freshwater. In tropical regions, unpredictable rainfall, fluctuating temperatures, and varying humidity levels often make conventional irrigation inefficient, leading to excessive water use, higher energy consumption, and lower production efficiency.
To address these challenges, the researchers evaluated an intelligent irrigation system capable of continuously monitoring environmental conditions and automatically determining the optimal irrigation schedule. Rather than relying on fixed watering routines, the AI-driven system supplies water only when crops actually need it, helping farmers conserve resources without compromising yields.
The experiment employed a quantitative design over a 60-day period using 24 horticultural plots under tropical conditions. Twelve plots were managed using conventional irrigation methods, while the remaining twelve were equipped with an AI-IoT precision irrigation system.
Multiple IoT sensors continuously monitored soil moisture, air temperature, humidity, water flow, and electricity consumption. The collected data were transmitted to a cloud-based platform, where a machine learning model analyzed real-time environmental information and automatically determined the timing and volume of irrigation required for each plot.
Because the system continuously adapts to changing field conditions, irrigation pumps operate only when necessary. This intelligent decision-making process minimizes unnecessary watering while maintaining optimal soil moisture for crop growth.
The study reported substantial improvements compared with conventional irrigation methods.
The major findings include:
- Water consumption decreased by 31.4% compared with conventional irrigation.
- Energy consumption was reduced by 22.7% due to more efficient pump operation.
- Soil moisture became significantly more stable, creating better growing conditions for crops.
- Crop productivity increased by 14.2%, demonstrating that greater efficiency can also improve agricultural output.
Statistical analysis using the Independent Samples t-test confirmed that all improvements were statistically significant, indicating that the observed differences resulted directly from the implementation of AI-IoT technology rather than random variation.
According to the researchers, the system's success lies in its ability to combine continuous environmental monitoring with automated decision-making. Unlike traditional irrigation systems that operate on predetermined schedules, the AI model evaluates real-time sensor data and adjusts irrigation based on the actual needs of crops and soil conditions.
Beyond water conservation, the study also highlights significant energy savings. Since irrigation pumps are activated only when necessary, electricity consumption decreases substantially, reducing operational costs for farmers who rely on electrically powered irrigation systems.
Another important outcome is improved soil moisture stability. Maintaining consistent moisture levels allows crops to develop healthier root systems, absorb nutrients more efficiently, and sustain better photosynthetic activity, all of which contribute to higher agricultural productivity.
Hermantoro and his colleagues emphasize that integrating AI and IoT enables irrigation systems to respond dynamically to changing environmental conditions. This adaptive capability makes the technology particularly suitable for tropical agriculture, where weather patterns and water requirements can vary considerably throughout the growing season.
From a practical perspective, the research demonstrates that digital agriculture extends beyond technological innovation. By reducing water use and electricity consumption while simultaneously increasing crop yields, AI-based precision irrigation offers farmers an opportunity to lower production costs and improve long-term sustainability.
The findings also provide valuable insights for governments and policymakers seeking to modernize agricultural systems. Investment in digital infrastructure, smart sensors, communication networks, and farmer training programs could accelerate the adoption of intelligent irrigation technologies and strengthen food security in tropical countries.
The researchers recommend that future studies involve larger agricultural areas, different crop varieties, and longer observation periods. They also suggest incorporating additional variables, such as weather forecasting, solar radiation, and nutrient management, to further improve the accuracy and performance of AI-driven irrigation systems.
Author Profile
Hermantoro is a researcher and academic at INSTIPER Yogyakarta specializing in precision agriculture, digital farming technologies, and the application of Artificial Intelligence and the Internet of Things in sustainable agricultural management.
Rengga Arnalis Renjani is a researcher at INSTIPER Yogyakarta whose research focuses on smart agriculture, agricultural sensor systems, and digital technologies for improving farming efficiency.
Gani Supriyanto is a researcher at INSTIPER Yogyakarta with expertise in agricultural technology innovation, energy-efficient farming systems, and sustainable agriculture.
Research Source
Hermantoro, Rengga Arnalis Renjani, & Gani Supriyanto. (2026). Artificial Intelligence and IoT-Based Precision Irrigation for Energy-Efficient Tropical Agriculture. International Journal of Management and Business Intelligence (IJBMI), Volume 4, Issue 3, pp. 685–698.
0 Komentar