Artificial Intelligence for Improving Agricultural Water-Use Efficiency: A Comparative Descriptive Analysis of Spain and South Korea

Abstract

Agricultural water-use efficiency has become an increasingly important policy and research priority as water scarcity, climate variability, and pressure on agricultural production intensify. Artificial intelligence (AI) may support more responsive irrigation management through crop-water requirement estimation, soil-moisture monitoring, predictive modelling, and data informed irrigation scheduling. However, the adoption of digital technologies does not necessarily demonstrate that AI has been used, nor does improved irrigation performance automatically establish a reduction in water consumption at the wider hydrological scale. This study examines AI-enabled and data-driven irrigation management in Spain and South Korea through a comparative descriptive analysis based on official statistics, institutional publications, documented initiatives, and relevant scientific literature. Spain’s 2023 Farm Structure Survey recorded 2,739,252 hectares of irrigated land, of which 49.0% was irrigated using localised methods. In South Korea, institutional reporting on selected smart-irrigation applications for apple and peach cultivation indicates irrigation-water savings of 10–31% under the reported conditions. These figures describe different types and levels of evidence and are not directly comparable measures of national AI performance. The analysis therefore distinguishes technological development from demonstrated outcomes and examines the implications of differences in measurement, implementation context, and evidence quality. Finally, the study derives policy-relevant lessons for Algeria, emphasising reliable agricultural data, farmer training, technical support, and monitored pilot projects before wider implementation.