In the heart of Qatar, where the sun blazes and water is a precious commodity, researchers are pioneering a new approach to sustainable agriculture that could reshape the future of farming in arid regions. Ikhlas Ghiat, a researcher at the College of Science and Engineering, Hamad Bin Khalifa University, has developed a data-driven model predictive control (MPC) system that optimizes irrigation in agricultural greenhouses, even under the challenging conditions of CO2 enrichment.
The quest for food security in hyper-arid regions is more pressing than ever, driven by geopolitical uncertainties, population growth, and climate change. Ghiat’s research, published in the journal *Smart Agricultural Technology* (translated as “الزراعة الذكية”), addresses these challenges head-on. By integrating advanced predictive modeling and data analytics, her work offers a promising solution for enhancing resource efficiency and promoting plant growth in closed greenhouse systems.
At the core of Ghiat’s innovation is the use of the extreme gradient boosting (XGBoost) model to predict dynamic transpiration rates. This model considers a complex interplay of microclimate conditions, including solar radiation, inside temperature, relative humidity, and CO2 concentration, along with vegetation indices derived from hyperspectral imaging measurements. “The XGBoost model demonstrated a high predictive accuracy, achieving an R2 of 97.1% and an RMSE of 0.417 mmol/m2/s for transpiration estimation,” Ghiat explains. This high level of accuracy is crucial for optimizing irrigation scheduling and ensuring that plants receive the right amount of water at the right time.
The integration of the XGBoost model into the MPC framework allows for precise control of irrigation while maintaining optimal soil moisture levels. Ghiat’s research highlights that the MPC-based irrigation control results in significant water savings. Over the course of one week of projections, the system achieved a 42.2% reduction in water usage compared to existing irrigation schedules under varying CO2 concentrations. Moreover, when applying the MPC model under different CO2 enrichment regimes, results revealed a 34% reduction in water consumption with CO2 enrichment at 1000 ppm relative to 400 ppm.
The implications of this research are far-reaching, particularly for the energy sector. As the world grapples with the challenges of climate change and water scarcity, the need for sustainable agricultural practices becomes increasingly urgent. Ghiat’s work offers a blueprint for achieving optimal irrigation control in closed greenhouse environments, emphasizing the advantages of advanced predictive modeling, data integration, and continuous rolling optimization.
“This research underscores the potential of MPC in closed greenhouse environments, highlighting the capacity of CO2 enrichment in closed agricultural greenhouses, particularly in regions under conditions of high solar radiation, as an effective practice for reducing water consumption,” Ghiat notes. By reducing water usage, the system not only conserves a precious resource but also lowers the energy required for irrigation, contributing to a more sustainable and efficient agricultural sector.
As the world looks towards a future where food security and environmental sustainability are paramount, Ghiat’s innovative approach to irrigation management offers a beacon of hope. Her work demonstrates the power of data-driven strategies in addressing the complex challenges of modern agriculture, paving the way for a more resilient and efficient food production system. With further research and development, this technology could revolutionize farming practices in arid regions, ensuring food security and sustainability for generations to come.