Work

Field-scale evaluation of low-elevation and mobile drip irrigation systems

Year: 2025
Type: article
Abstract: Available water in arid watersheds is scarce and is projected to decline in the future. Therefore, optimizing water use in all sectors, especially the agricultural sector with the highest consumptive use, is critical. One common option for optimizing water use is improving irrigation system efficiency. In this on-farm study, three irrigation technologies for center pivots at different irrigation levels were investigated over space and time. Satellite imagery was used to examine the performance of each treatment at a field scale for different crops during 2016–2020. Relative yield change among various crops was calculated to compare treatments spatially and temporally. Finally, relative yield changes were simulated using the most accurate machine learning models for each irrigation technology. The sensitivity of feature importance was evaluated using sensitivity analysis and SHAP (SHapley Additive exPlanations), an interpretable machine learning method based on game theory. The results showed that the performance of irrigation systems was influenced by climate conditions such as temperature and precipitation, as well as field features. For example, in drought years, soil electrical conductivity (EC) had the highest influence for some irrigation technologies, while in years with more normal precipitation, elevation had the greatest impact. The method proposed in this paper can be applied in other fields to evaluate irrigation technologies and support better decision-making aimed at enhancing agricultural productivity. • New methodology using imagery and machine learning for field-scale irrigation evaluation. • Climate significantly impacts yield; irrigation technologies vary, requiring site-specific optimization. • Elevation and soil EC are key yield influencers, with interpretive machine learning (SHAP) revealing their importance .
Language: English
Subfield: Soil Science
Open Access status: gold
Estimated APC paid: $3,070
OpenAlex ID: W4409873978
FWCI: 1.51
Cites: 69
Cited by: 3
Related to: 10