Artificial intelligence based approaches to evaluate actual evapotranspiration in wetlands Francesco Granata ⁎, Rudy Gargano, Giovanni de Marinis University of Cassino and Southern Lazio, Department of Civil and Mechanical Engineering, Cassino, Italy HIGHLIGHTS • Estimation of evapotranspiration in wet- lands is essential for their preservation • AI methods are a promising alternative to the most common estimation techniques • RF, ARDS, MLP and k-NN algorithms have been used to develop several prediction models • The accuracy of the models remains good even if the number of input variables is reduced • RF and k-NN provide slightly better per- formance than ARDS and MLP GRAPHICAL ABSTRACT abstract article info Article history: Received 29 October 2019 Received in revised form 18 November 2019 Accepted 18 November 2019 Available online xxxx Editor: José Virgílío Cruz Keywords: Evapotranspiration Wetlands Artificial intelligence Prediction models Wetlands are extraordinary ecosystems and important climate regulators that also contribute to reduce natural disaster risk. Unfortunately, wetlands are declining much faster than forests. The safeguarding of the wetlands also needs knowledge of the dynamics that control the water balance of these environments. Therefore, an accu- rate estimation of evapotranspiration in wetlands is an essential task. When adequate experimental data are available, some algorithms deriving from Artificial Intelligence research represent a promising alternative to the most common estimation techniques. In this study, starting from daily measurements of climatic variables such as net solar radiation, depth to water, wind speed, mean relative humidity, maximum temperature, minimum temperature, and mean temperature, using the Random Forest, Additive Regression of Decision Stump, Multilayer Perceptron and k-Nearest Neighbors algorithms, 24 estimation models, different in input variables, have been developed and compared. The data have been provided by USGS. They have been obtained from a measuring site in wetlands of Indian River County, Flor- ida using the eddy-covariance technique. The accuracy of these models based on AI algorithms remains good even if the number of input variables is re- duced from 7 to 3. Net solar radiation, mean temperature and mean relative humidity or wind speed measure- ments allow obtaining a sufficiently accurate estimation model. Random Forest and k-Nearest Neighbors provide slightly better performance than Additive Regression of Decision Stump and Multilayer Perceptron. The analyzed models show in most cases the lowest accuracy in the range 2–4 mm/day, while the highest Science of the Total Environment xxx (xxxx) xxx ⁎ Corresponding author. E-mail address: f.granata@unicas.it (F. Granata). STOTEN-135653; No of Pages 15 https://doi.org/10.1016/j.scitotenv.2019.135653 0048-9697/© 2019 Elsevier B.V. All rights reserved. Contents lists available at ScienceDirect Science of the Total Environment journal homepage: www.elsevier.com/locate/scitotenv Please cite this article as: F. Granata, R. Gargano and G. de Marinis, Artificial intelligence based approaches to evaluate actual evapotranspiration in wetlands, Science of the Total Environment, https://doi.org/10.1016/j.scitotenv.2019.135653