Comparison of machine learning and dynamic models for predicting actual vapour pressure when psychrometric data are unavailable

Abstract

• Machine learning models for predicting e a without psychrometric data were developed. • Machine learning models were compared with recently proposed dynamic empirical model. • The machine learning models using T mean and T min as inputs were superior to those using only T mean or T min . • The XGBoost model using T mean and T min offered the best accuracy in various climate zones. • We recommend global XGBoost model when there are no historical data except for hyper-arid regions. Information of actual vapour pressure ( e a ) is frequently required in many disciplines. However, psychrometric data required to calculate e a are often not readily available. Hence, it is of great importance to develop models to estimate e a when psychrometric data are unavailable. Here, five machine learning models were developed for estimating e a , viz. extreme gradient boosting (XGBoost), extreme learning machine (ELM), kernel-based nonlinear extension of Arps decline (KNEA), multiple adaptive regression splines (MARS), and support vector machine (SVM) models. Their performance was also compared to a dynamic model proposed recently, which estimates e a by adjusting dew point temperature from minimum temperature ( T min ) with dynamic correction factor. Three input combinations using only temperature data (i.e. T min and mean temperature ( T mean )) were considered in the machine learning models. The meteorological data collected from 1,188 stations across six climate zones were used to develop and assess the models. The overall results revealed that the dynamic and machine learning models offered satisfactory e a estimates spanning from hyper arid to humid climates. However, the accuracy of the dynamic model was lower than all machine learning algorithms using either only T min or combinations of T mean and T min in all climate zones. The machine learning models using T mean and T min were superior to those using only T mean or T min . There were comparable performances among the ELM, KNEA, MARS, and SVM models with various input variables; however, the XGBoost model incorporating T mean and T min produced the best accuracy. The computational demand was least for the ELM model, followed by the XGBoost model. Considering the accuracy and computational demand, the XGBoost model is recommended for predicting daily and monthly e a from hyper arid to humid climates when historical data are prior known. When there are no historical data, we recommend using the global XGBoost model incorporating T mean , T min , and aridity index for estimating daily and monthly e a from arid to humid regions, and using the dynamic model in hyper-arid regions.