Emami et al. (2026) Intelligent irrigation management system for arid and semi-arid regions under climate change

Identification

• Journal: Scientific Reports
• Year: 2026
• Date: 2026-04-06
• Authors: Somayeh Emami, Hossein Dehghanisanij, Hojjat Emami
• DOI: 10.1038/s41598-026-46523-9

Research Groups

• Agricultural Research, Education and Extension Organization, Agricultural Engineering Research Institute, Karaj, Alborz, Iran
• Department of Computer Engineering, University of Bonab, Bonab, Iran

Short Summary

This study developed and validated an intelligent irrigation management system for arid and semi-arid regions by integrating actual and predicted climate data with a physical water–soil–plant model. The system demonstrated significant reductions in water use (up to 41%), increases in crop yield (up to 12.6%), and improvements in water productivity (up to 87%) for wheat, tomato, and apple compared to conventional methods.

Objective

• Development of an intelligent irrigation system by integrating real and predicted climate data with a physical–physiological model.
• Dynamic updating of plant coefficients and simulation of multiple stresses (water, salinity, temperature).
• Validation of the system in real field conditions for three crops: wheat, tomato, and apple.

Study Configuration

• Spatial Scale: Miandoab Plain, located in the south of the Lake Urmia Basin, West Azerbaijan Province, Iran (average elevation 1,290 m). The study involved three monitored farms (0.5 ha replicate plots each) for wheat, tomato, and apple.
• Temporal Scale: Field experiments were conducted during the 2024–2025 cropping season. Wheat was monitored from November 2024 to June 2025, tomato from May to September 2025, and the apple orchard from April to October 2025. Climate data were based on 20 years (2000–2019) from the Miandoab synoptic station, with daily time scale for model operation.

Methodology and Data

• Models used:
  • Intelligent irrigation depth and timing determination system (developed in Python, integrating climate, soil, crop, and irrigation system data).
  • Physical water–soil–plant model (layered soil water balance, crop stress calculation, evapotranspiration estimation).
  • Dynamic simulation of soil moisture, salinity, and water flow in soil layers.
  • Crop stress models for water (Kssto, Srel), temperature (tstrs), and salinity (KSalinity).
  • Calculation of crop evapotranspiration (ETc) with dynamic updating of soil evaporation coefficient (Ke) and crop transpiration coefficient (Kcb) based on leaf area index (LAI) and phenological stages.
  • Growing Degree-Days (GDD) for crop growth physiology.
  • Deficit irrigation module based on FAO yield reduction relationships.
  • Financial optimization using Net Present Worth (NPW).
  • Concepts and equations derived from FAO-56, SWAP, and AquaCrop modeling frameworks.
  • Penman–Monteith method used for comparison of water requirements.
• Data sources:
  • Online meteorological data (minimum/maximum temperature, relative humidity, wind speed, solar radiation, precipitation, air pressure) from Miandoab synoptic station.
  • Soil properties (texture, bulk density, field capacity (FC), permanent wilting point (PWP), soil depth, hydraulic conductivity, permeability, organic matter percentage). Initial soil salinity (ECe) ranged from 2.1 to 6.5 dS/m.
  • Crop characteristics and phenology (crop type, crop coefficients, growth stages, root depth, water stress sensitivity, planting density).
  • Water access conditions (withdrawable flow, available pressure, time limit, water quality, salts, pumping cost/energy).
  • Irrigation system specifications (type: drip/sprinkler/basin, irrigation efficiency, spray intensity, flow rate, timing pattern, pump specifications).
  • Farm water storage information (pond volume, inlet/outlet, fill/empty time, evaporation and infiltration losses).
  • Sensor and performance data (soil moisture measured gravimetrically, soil temperature, current flow rate, system pressure, irrigation history).
  • Field-measured data from monitored farms for water requirements, net irrigation depth, water consumption, and crop yield.

Main Results

• The intelligent system accurately estimated crop water requirements, showing no statistically significant difference (p > 0.05) compared to the Penman–Monteith method (mean difference of 26.42 mm).
• Temporal patterns of temperature and ETc were consistent with semi-arid climates; an increase in temperature during the middle of the growing season led to a significant rise in ETc.
• Highest ETc values were observed in the apple orchard (up to approximately 29 mm/day), while tomato exhibited a peak-decline pattern (up to 12 mm/day) and wheat showed peak ETc during flowering-to-grain-filling (up to 7 mm/day).
• Dynamic analysis of coefficients showed that as leaf area expanded, the contribution of soil surface evaporation (Ke) decreased, and crop transpiration (Kcb) became the dominant component of water consumption.
• Field validation demonstrated that the intelligent system predicted water needs more accurately than conventional methods, leading to:
  • Tomato (drip irrigation): 41.1% reduction in gross irrigation depth, 10.3% increase in crop yield, and 87.3% improvement in water productivity.
  • Apple (basin irrigation): 2.8% reduction in gross irrigation depth, 12.6% increase in crop yield, and 15.9% improvement in water productivity.
  • Wheat (drip irrigation): 25% reduction in gross irrigation depth, 6.5% increase in crop yield, and 35% improvement in water productivity.
• Correlation analysis confirmed a strong relationship between temperature, LAI, and ETc, highlighting the system's capability to represent climatic and physiological factors simultaneously.

Contributions

• Development of an intelligent, web-based irrigation management system that integrates real-time and predicted climate data with a physical–physiological water-soil-plant model.
• Dynamic daily updating of soil evaporation (Ke) and crop transpiration (Kcb) coefficients based on simulated leaf area index (LAI) and phenological stages.
• Simultaneous modeling and simulation of water, salinity, and temperature stresses and their cumulative impact on actual evapotranspiration, crop growth, and final yield.
• Extensive field validation at farm and orchard scales under real water deficit conditions in the semi-arid climate of the Lake Urmia basin, demonstrating practical applicability and bridging the gap between theoretical models and field conditions.
• Enhanced accuracy in estimating crop water requirements compared to conventional methods by simulating soil moisture at different depths, actual crop evapotranspiration, and physiological changes throughout the growing season.
• Optimization of water consumption, improvement of irrigation efficiency, and minimization of irrigation cycles to prevent water stress, over-irrigation, and salinity accumulation in the root zone.
• Incorporation of economic and social indicators to enhance farm management and increase farmers’ income, serving as a generalizable tool for climate-change-adapted agriculture.

Funding

• Iran National Science Foundation (INSF) (project No. 4040570).

Citation

@article{Emami2026Intelligent,
  author = {Emami, Somayeh and Dehghanisanij, Hossein and Emami, Hojjat},
  title = {Intelligent irrigation management system for arid and semi-arid regions under climate change},
  journal = {Scientific Reports},
  year = {2026},
  doi = {10.1038/s41598-026-46523-9},
  url = {https://doi.org/10.1038/s41598-026-46523-9}
}