Estimating Daily Reference Crop Evapotranspiration in Northeast China Using Optimized Empirical Models Based on Heuristic Intelligence Algorithms

Accurately estimating reference crop evapotranspiration (ETo) improves agricultural water use efficiency. However, the accuracy of ETo estimation needs to be further improved in the Northeast region of China, the country’s main grain production area. In this research, meteorological data from 30 sites in Northeast China over the past 59 years (1961–2019) were selected to evaluate the simulation accuracy of 11 ETo estimation models. By using the least square method (LSM) and three population heuristic intelligent algorithms—a genetic algorithm (GA), a particle swarm optimization algorithm (PSO), and a differential evolution algorithm (DE)—the parameters of eleven kinds of models were optimized, respectively, and the ETo estimation model suitable for northeast China was selected. The results showed that the radiation-based Jensen and Haise (JH) model had the best simulation accuracy for ETo in Northeast China among the 11 empirical models, with R2 of 0.92. The Hamon model had an acceptable estimation accuracy, while the combination model had low simulation accuracy in Northeast China, with R2 ranges of 0.74–0.88. After LSM optimization, the simulation accuracy of all models had been significantly improved by 0.58–12.1%. The results of heuristic intelligent algorithms showed that Hamon and Door models optimized by GA and DE algorithms had higher simulation accuracy, with R2 of 0.92. Although the JH model requires more meteorological factors than the Hamon and Door model, it shows better stability. Regardless of the original empirical formula or the optimization of various algorithms, JH has higher simulation accuracy, and R2 is greater than 0.91. Therefore, when only temperature or radiation factors were available, it was recommended to use the Hamon or Door model optimized by GA to estimate ETo, respectively; both models underestimated ETo with an absolute error range of 0.01–0.02 mm d−1 compared to the reference Penman–Monteith (P–M) equation. When more meteorological factors were available, the JH model optimized by LSM or GA could be used to estimate ETo in Northeast China, with an absolute error of less than 0.01 mm d−1. This study provided a more accurate ETo estimation method within the regional scope with incomplete meteorological data.