Estimation of reference evapotranspiration using machine learning models with limited data

Reference Evapotranspiration (ET0) is a complex hydrological variable defined by various climatic variables affecting water and energy balances and critical factors for crop water requirements and irrigation scheduling. Conventionally ET0 is calculated by various empirical methods based on rigorous climatic data. However, there are many places where various climatic data may not available for ET0 estimation. The objective of this study is to evaluate different machine learning (ML) techniques to estimate ET0 with minimal climatic inputs. In this study, FAO 56 Penman-Monteith model was considered as the standard model and different ML models based on A Long short-term memory neural networks (LSTM), Gradient Boosting Regressor (GBR), Random Forest (RF) and Support Vector Regression (SVR) were developed to estimate ET0 with climatic variables as input parameters. These models were evaluated in two different climatic regions, Hyderabad in India and Waipara in New Zealand. The results indicated that 99 % accuracy could be achieved with all climatic input, whereas accuracy drops to 86% with fewer data. LSTM model performed better than other ML models with all input combinations at both the stations, followed by SVR and RF. Both LSTM and SVR models have been noted as the most robust ML models for estimating ET0 with minimal climate data. Even though the excellent performance can be achievable when all input variables are used, the study, however, found that even a three-parameter combination (Temperature, Wind Speed and Relative Humidity values) or two-parameter combination (Temperature and Relative Humidity, Temperature and Wind Speed) can also be promising in ET0 estimation. The presented study will help to estimate ET0 for data scare regions, which is vital for agricultural water management in semi-arid climates.

Automated summary

This study evaluated different machine learning techniques for estimating reference evapotranspiration (ET0), with LSTM model performing the best among all input combinations. Even with fewer data inputs, high accuracy can still be achieved, making it promising for agricultural water management in data scarce regions.