بررسی کارایی روشهای داده کاوی در پیش بینی تبخیر - تعرق مرجع روزانه (مطالعه موردی ایستگاههای نوار ساحلی جنوب ایران).

Investigating the effectiveness of data mining methods in predicting daily reference evapotranspiration (Case study: Coastal strip stations in southern Iran).

Reference evapotranspiration is one of the important hydrological parameters in agricultural research and water and soil protection. For this reason, its estimation and modeling are of special importance. Non-linear relationships, inherent uncertainty, and the need for a lot of climate information in estimating evapotranspiration have made researchers use data-mining methods to estimate evapotranspiration in recent decades. The purpose of this research is to investigate the efficiency of data mining methods included in support vector machine, decision tree, random forest and Gaussian process regression in forecasting the daily reference evapotranspiration of coastal strip stations in the south of the country (Chabahar, Bandar Abbas, Bushehr and Abadan).To do the work, daily reference evapotranspiration was calculated using 20-year climatic data (2001-2021) using the FAO-Penman-Monteith method. Then, using these data as output data, 6 combined scenarios were evaluated based on the correlation between meteorological variables and reference evapotranspiration using data mining methods (Support vector machine, Decision tree, Random forest and Gaussian regression process). The results of the investigations showed that all four data mining methods were able to estimate the reference evapotranspiration values in the studied areas.In all four stations, the Gaussian process regression method with the highest R2 value and the lowest RMSE and MAE values had a better estimate of the reference evapotranspiration values, and random forest, decision tree, and support vector machine methods were in the next ranks respectively. Among the examined patterns, in Chabahar pattern 6 with the combination of minimum temperature, maximum temperature, average temperature, relative humidity, solar radiation and wind speed variables, in Bandar Abbas and Bushehr pattern 4 with the combination of minimum temperature, maximum temperature, average temperature and relative humidity and in Abadan pattern 3 with the combination of minimum temperature, maximum temperature and average temperature parameters had the best estimate. Considering the high accuracy of the Gaussian process regression model in estimating reference evapotranspiration, this method is recommended for estimating reference evapotranspiration in coastal stations of southern Iran. [ABSTRACT FROM AUTHOR]

Copyright of Iranian Journal of Eco Hydrology is the property of University of Tehran and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)