Nurmalitasari et al. (2025) Artificial intelligence-driven solar smart irrigation for sustainable agriculture: Trends, challenges, and SDG implications – A systematic review

Identification

• Journal: Smart Agricultural Technology
• Year: 2025
• Date: 2025-11-25
• Authors: Nurmalitasari Nurmalitasari, Nurchim Nurchim, Retna Dewi Lestari
• DOI: 10.1016/j.atech.2025.101665

Research Groups

• Faculty of Computer Science, Universitas Duta Bangsa Surakarta, Surakarta, Indonesia
• Faculty of Science and Technology, Universitas Duta Bangsa Surakarta, Surakarta, Indonesia

Short Summary

This systematic literature review synthesizes 29 articles to examine the technological innovations, efficiency outcomes, adoption barriers, and sustainability impacts of AI-driven, solar-powered smart irrigation systems. It finds that these systems significantly improve water-use efficiency (up to 70 %), increase crop yields (15–40 %), and reduce energy consumption and greenhouse gas emissions, directly contributing to several Sustainable Development Goals despite persistent implementation challenges.

Objective

• To map the current approaches and technologies used in AI-based solar smart irrigation systems.
• To assess how the integration of solar energy and AI contributes to water-use efficiency in irrigation systems.
• To identify the major technical, economic, and social challenges in implementing AI-based solar irrigation systems, particularly in developing countries.
• To evaluate the extent to which AI and solar-powered smart irrigation models support food security and sustainable agriculture.

Study Configuration

• Spatial Scale: Global, covering diverse agroecological contexts, ranging from field-level applications to large-scale agricultural regions, with a focus on developing countries.
• Temporal Scale: Articles published between 2016 and 2025.

Methodology and Data

• Models used: (Models identified in the reviewed literature)
  • AI/Machine Learning: Fuzzy Logic Systems, Artificial Neural Networks (ANNs), bio-inspired algorithms, Radial Basis Function Network – Enhanced Smart Algorithm (RBFN-ESA), Deep Convolutional Neural Networks (DCNN), XGBoost, CART, LSTM, SVR, Deep NARMAX.
  • Control Systems: Model Predictive Control (MPC), Stochastic Programming, Chaotic Harris Hawks Optimization with Maximum Power Point Tracking (CHHO-MPPT).
• Data sources: (Sources used by the reviewed literature)
  • Review Data Sources: Scopus, Web of Science (WOS), Google Scholar.
  • Reviewed Literature Data Sources: Satellite imagery (Earth Observation, Remote Sensing), IoT sensors (soil moisture, air temperature, humidity, sunlight intensity, CO₂ concentration, water level), weather forecasts, historical agronomic data, unmanned aerial vehicles (UAVs).

Main Results

• Technological Landscape: Eight key technological clusters were identified: Sensors and IoT, AI/ML, Solar PV, Real-Time Monitoring and Autonomous Control, Model Predictive Control and Decision Support Systems, Cloud Platforms and Remote Access, Weather and Satellite Integration, and Big Data Fusion and Decision Engines.
• Efficiency Outcomes:
  • Water consumption reduction: Ranged from 28.1 % to 71.8 %.
  • Crop yield increases: Ranged from 15 % to 40 %.
  • Energy consumption and greenhouse gas emissions: Significant reductions, with one system reporting a carbon emission reduction of 0.252 kg CO₂/m²/year and energy savings from 200 kWh to 50 kWh.
  • Operational efficiency: Pump operating time reduced by 16.5 % in one system, and operational efficiency improved by up to 34 % in another.
• Adoption Barriers:
  • Technical: Inadequate infrastructure (lack of internet/electrical grids), system complexity and calibration demands, limited local data for AI model accuracy, and device maintenance challenges due to environmental stressors (dust, humidity, extreme temperatures).
  • Economic: High initial investment costs for hardware and software, limited access to financing mechanisms (loans, subsidies), and recurring maintenance and operational costs (sensor replacement, software licensing).
  • Social: Low technological literacy among farmers, resistance to change (distrust of automation, preference for manual control), limited training and technical support, and cultural barriers (incompatibility with traditional practices, generational divides).
• Sustainability Impact:
  • Direct contributions to Sustainable Development Goals (SDGs): SDG 2 (Zero Hunger), SDG 6 (Clean Water and Sanitation), SDG 7 (Affordable and Clean Energy), and SDG 13 (Climate Action).
  • Optimization of water resources through precise scheduling and reduced waste.
  • Enhancement of crop productivity and uniformity.
  • Improved environmental sustainability and climate resilience by reducing fossil fuel dependency and carbon footprint.

Contributions

• Provides a comprehensive mapping of AI–IoT–PV-based smart irrigation technologies reported between 2016 and 2025.
• Introduces an analytical synthesis framework explaining interdependencies among technological components in autonomous irrigation.
• Develops a multidimensional taxonomy of adoption barriers derived from diverse agroecological contexts.
• Proposes a sustainability framework linking AI–IoT–PV technologies with SDG 2, SDG 6, SDG 7, and SDG 13, offering a conceptual foundation for policy formulation and evidence-based technology development.

Funding

• The Ministry of Higher Education, Science, and Technology under the Fundamental Research Programme in 2025 (Grant number: 127/C3/DT.05.00/PL/2025, 043/LL6/PL/AL.04/2025, and 061/UDB.LPPM/A.34-HKN/2025).

Citation

@article{Nurmalitasari2025Artificial,
  author = {Nurmalitasari, Nurmalitasari and Nurchim, Nurchim and Lestari, Retna Dewi},
  title = {Artificial intelligence-driven solar smart irrigation for sustainable agriculture: Trends, challenges, and SDG implications – A systematic review},
  journal = {Smart Agricultural Technology},
  year = {2025},
  doi = {10.1016/j.atech.2025.101665},
  url = {https://doi.org/10.1016/j.atech.2025.101665}
}