Resolving data-hungry nature of machine learning reference evapotranspiration estimating models using inter-model ensembles with various data management schemes

Over the past decade, there has been an increasing research on the use of machine learning tools for estimating reference crop evapotranspiration (ETo). However, due to the data-hungry nature of the machine learning models, all of these researches are not suitable for regions with limited data supply. This study aims to provide a breakthrough for the bottleneck through coupling of the inter-model ensemble with various data management schemes. The Bayesian modeling approach and a non-linear neural ensemble based inter-model ensemble (BMA E and NNE-E) were developed locally with data from five different meteorological stations in the Peninsular Malaysia. The NNE-E was found to be highly robust spatially, whereby it can be used to estimate daily ETo accurately at other stations, even though with reduced input meteorological parameters. However, the performances of the locally trained models were found wanting and were fluctuating violently. This was resolved through creating a data pool that include the data from all stations and developing a universal NNE. By following the proposed scheme of things, the daily ETo can be easily estimated across the whole Peninsular Malaysia. This being, without the need for historical data and new models at estimation site.

Automated summary

This study tackles the issue of using machine learning tools for estimating reference crop evapotranspiration (ETo) in regions with limited data supply. Through the integration of models and data management schemes, the locally developed non-linear neural ensemble (NNE-E) proves to be robust and accurate in estimating daily ETo at different stations across the Peninsular Malaysia.