article · Cogent Food & Agriculture
Accurately predicting reference evapotranspiration is essential for improving irrigation water management amid changing climatic conditions. This study evaluates several machine learning algorithms to forecast daily reference evapotranspiration, comparing predictions against traditional estimation approaches including the Penman-Monteith, Hargreaves, and Blaney-Criddle methods. Trends in climate variables were analysed using the modified Mann-Kendall test and Theil Sen slope estimator. Tested algorithms included Support Vector Regression, Random Forest, XGBoost, K-Nearest Neighbour, Decision Trees, Linear Regression, and Multiple Linear Regression. The evaluated machine learning models demonstrated strong predictive accuracy, achieving coefficients of determination between 0.97 and 0.99 for the Penman-Monteith method, 0.99 for the Hargreaves method, and 0.91 to 0.92 for the Blaney-Criddle method. High Kling-Gupta efficiency values alongside low error rates confirm that machine learning algorithms can match the reliability of standard equations for evapotranspiration prediction.
Accurate estimation of reference evapotranspiration helps agricultural managers determine optimal crop water requirements. By demonstrating that machine learning can reliably reproduce standard hydrological equations, this research supports more precise irrigation scheduling, which can reduce water waste and help agricultural systems adapt to the challenges posed by climate change.
These predictive algorithms could be integrated into smart irrigation scheduling tools or agricultural water management platforms for irrigation planners and farm operators. Because the study focuses on evaluating algorithmic performance against standard calculation methods on climate data, the technology represents applied and tested research that requires software integration and field validation before reaching market readiness.
AI-generated from the published abstract. Always read the original work before citing.
This study addressed the increasing challenges of climate change by exploring the use of machine learning (ML) algorithms to predict the reference evapotranspiration (ETo). Accurate ETo prediction is crucial for optimizing irrigation water management. This research aimed to assess the reliability and accuracy of ML algorithms in predicting ETo values. Three ETo calculation methods were employed: Penman-Monteith (PM), Hargreaves (HA), and Blaney-Criddle (BC). The study analyzed ETo and other climate variables using the modified Mann-Kendall test (m-MK) and Theil Sen’s slope estimator methods to identify trends. Multiple ML algorithms, including Support Vector Regression (SVR), Random Forest (RF), XGboost, K-Nearest Neighbor (KNN), Decision Trees (DT), Linear Regression (LR), and Multiple Linear Regression (MLR) were utilized for ETo prediction. The ML algorithms exhibited excellent performance, with coefficients of determination (R2) values ranging from 0.97 to 0.99 for PM, 0.99 for HA, and from 0.91 to 0.92 for BC. The models demonstrated a high value of the Kling-Gupta efficiency (KGE) with low Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) values. Strong correlations between the predicted and calculated daily ETo were observed with R2 values of 0.99, 0.99, and 0.92 for PM, HA, and BC methods, respectively. In conclusion, this study affirmed the accuracy and reliability of ML algorithms to match that of standard ETo prediction equations.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1080/23311932.2024.2348697
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
