پیش‌بینی مقادیر تبخیر-تعرق روزانه با استفاده از راهبرد ترکیب مدل‌های درختی با روش تجربی هارگریوز

نیاز دائمی به افزایش تولیدات کشاورزی، همراه با رویدادهای خشکسالی بیشتر و مکرر در کشور، مستلزم ارزیابی دقیق تری از نیازهای آبیاری و در نتیجه برآورد دقیق تر تبخیر و تعرق واقعی است. در سال‌های اخیر، چندین موضوع مدیریت آب با استفاده از مدل‌های به دست آمده از تحقیقات هوش مصنوعی مورد توجه قرار گرفته است. هنگام استفاده از این مدل‌ها، جنبه‌های چالش‌برانگیز اصلی با انتخاب بهترین الگوریتم ممکن، انتخاب متغیرهای معرف مناسب و در دسترس بودن مجموعه داده‌های مناسب نشان داده می‌شوند. بنابراین، در این مطالعه توانایی مدل های درختی (m5p و rf) با مدل هارگریوز (hs) در برآورد تبخیر-تعرق روزانه در ایستگاه های ارومیه و یزد، طی دوره 2021-2000 با استفاده از چهار معیار آماری مورد ارزیابی قرار گرفت. در تمام مدل های بکار گرفته شده، سناریوی برتر مدلی بود که ورودی آن شامل پارامترهای حداقل دما، حداکثر دما، رطوبت نسبی​​، سرعت باد و ساعات آفتابی بود. نتایج به دست آمده در ایستگاه  یزد نشان داد  که سناریو پنجم مدل  m5p-hs و سپس سناریو پنجم مدل rf-hs به ترتیب با داشتن خطای (mm day-1) 0.24 و (mm day-1) 0.26 بالاترین دقت را داشتند. در ایستگاه ارومیه نیز سناریو پنجم مدل rf-hs با داشتن خطای (mm day-1) 0.27 بهترین عملکرد را داشته و پس از آن سناریو پنجم مدل rf-hs با داشتن خطای (mm day-1) 0.33 دقت مناسبی را ارائه داد. نتایج حاصل از این پژوهش نشان داد که پارامتر سرعت باد از مهم ترین پارامترهای هواشناسی مورد نیاز در برآورد تبخیر-تعرق روزانه می باشد، به طوریکه افزودن این پارامتر سبب کاهش خطا و بهبود دقت پیش بینی مدل ها گردید.

prediction of daily evapotranspiration using the strategy of combining tree models with empirical hargreaves method

background and objectivesthe constant need to increase agricultural production, along with more and more frequent drought events in our country, requires a more accurate assessment of irrigation consumption and thus a more accurate estimate of actual evapotranspiration. prediction of water consumption over agricultural areas is important for agricultural water resources planning, management, and regulation. it leads to the establishment of a sustainable water balance, mitigates the impacts of water scarcity, as well as prevents the overusing and wasting of precious water resources. as evapotranspiration is a major consumptive use of irrigation water and rainwater on agricultural lands, improvements of water use efficiency and sustainable water management in agriculture must be based on the accurate estimation of et. irrigated agriculture is expected to produce more crops with less water consumption in the future. therefore, accurate forecasting of water demand along with sustainable management and more efficient methods to meet the growing demand under scarce water resources is necessary. the models used to predict evapotranspiration should be used in different regions with different climates to evaluate their performance. therefore, in this research, tree models and hargreaves were used in yazd and west azerbaijan provinces, which have different climates, in order to evaluate the performance of the models used.methodology in recent years, water management issues have been addressed using models derived from artificial intelligence research. the use of combined models has made significant progress in recent years. combined models are able to perform processing in a short period of time and at the same time with high accuracy. using these models, the main challenging aspects are represented by the selection of the best possible algorithm, the selection of suitable representative variables and the availability of suitable data sets. therefore, in this study, the ability of tree models (m5p and rf) with hargreaves model (hs) for estimating the daily evapotranspiration of urmia and yazd stations was investigated during the period of 2000-2021. the noteworthy point is that in the combined tree-hargreaves model, the used tree models were used as input to the hargreaves model. the combined model has been used for the first time in this research and the use of this model can predict daily evapotranspiration with appropriate accuracy. also, the model's results have been evaluated using 5 evaluation criteria: coefficient of determination, root mean square error, nash-sutcliffe coefficient, and wilmot's agreement index. findingsthe best scenario in all the models used was the model whose input included the parameters of minimum temperature, maximum temperature, relative humidity, wind speed, and sunshine hours. the results obtained at the yazd station showed that the fifth scenario of the m5p-hs model and then the fifth scenario of the rf-hs model, respectively with an error of (mm day-1) 0.24 and (mm day-1) 0.26 had the highest accuracy. in the urmia station, the fifth scenario of the rf-hs model with an error of (mm day-1) of 0.27 had the best performance, and after that, the fifth scenario of the rf-hs model with an error of (mm day-1) of 0.33 had good accuracy. the comparison between the results of the urmia and yazd stations shows that the coefficient of determination and the root mean square error for the urmia station was higher than the yazd station in all scenarios. on the other hand, with the increase of the data range, the coefficient of determination index will have a higher value and the root mean square error index will have a lower value. therefore, the reason for thedecreasing of determination coefficient and the error rate in yazd station can be attributed to the limited range of parameters used. finally, tree models have increased the accuracy of the hargreaves model in this research.conclusionfinally, the rf, m5p, rf-hs and m5p-hs models were able to predict daily evapotranspiration values ​​in the shortest time and with the highest accuracy. however, the results showed that the lower the model inputs, the weaker the model prediction. the results of this research showed that the combination of tree models with hargreaves model is able to predict daily evapotranspiration values ​​with high accuracy compared to individual models. the results of this research showed that the wind speed parameter is one of the most important meteorological parameters needed in estimating daily evapotranspiration, so adding this parameter results in the highest accuracy in all models. also, due to the important role of wind speed in predicting daily evapotranspiration values ​​and the unavailability of the maximum wind speed parameter in this research, it is recommended to use the maximum wind speed parameter as one of the model inputs for further studies.