نموذج شبكة عصبية صنعيَّة للتنبؤ بالتبخر الشهري في منطقة حماه
Abstract
التبخر هو أحد العناصر الأساسية للدورة الهيدرولوجية وضروري للعديد من الدراسات مثل الموازنة المائية, تصميم أنظمة الري وإدارة الموارد المائية, ويتطلب تقديره معرفة العديد من العناصر المناخية. على الرغم من أن هناك صيغاً تجريبيَّةً متوفرةً لتقدير التبخر, ولكن أداء هذه الصيغ غير دقيق بسبب الطبيعة المعقدة لعملية التبخر. لذلك فإن هذا البحث يهدف لوضع نموذج شبكة عصبية صنعيَّة للتنبؤ بالتبخر الشهري في منطقة حماه باستخدام ثلاثة عناصر مناخية هي درجة الحرارة, الرطوبة النسبية وسرعة الرياح. من أجل ذلك فقد بُني النموذج باستخدام مكتبة nntool-box إحدى أدوات الـ MATLAB. استُخدمت الشبكة العصبية الصنعيَّة ذات التغذية الأمامية و الانتشار العكسي للخطأ بطبقة خفية واحدة لبناء النموذج. وتم تقييم شبكات مختلفة بعدد مختلف من العصبونات وبتغيير دوال التفعيل المستخدمة في كل طبقة. واستُخدم جذر متوسط مربع الخطأ (RMSE) لتقييم دقة النموذج المُقترح. وقد بينت الدراسة أن الشبكة العصبية الصنعيَّة ذات الهيكلية (3-14-1) هي الأفضل للتنبؤ بالتبخر في منطقة حماه حيث كانت قيمة RMSE تساوي (21.5mm/month) وقيمة 12R2"> مساوية (0.97).
توصي الدراسة باستخدام أنواع أخرى من الشبكات العصبية لتقدير التبخر.
The evaporation is one of the basic components of the hydrologic cycle and it is essential for studies such as water balance, irrigation system design and water resource management, and it requires knowledge of many climatic variables. Although, there are many empirical formulas available for evaporation estimate, but their performances are not all satisfactory due to the complicated nature of the evaporation process. Accordingly, this paper is an attempt to assess the potential and usefulness of ANN based modeling for evaporation prediction from HAMA by using temperature, relative humidity and wind velocity. The mathematical model was built by the (nntool-box), which is one of the MATLAB tools. The feed forward back propagation network with one hidden layer has been utilised to construct the model. Different networks with different number of neurons were evaluated. Root Mean Squared Error (RMSE) was employed to evaluate the accuracy of the proposed model. The study shows that ANN (3-14-1) was the best model with RMSE (21.5mm/month) and 12R2"> (0.97).
This study suggests using other types of neural networks for estimation of evaporation
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2018 ttps://creativecommons.org/licenses/by-nc-sa/4.0/
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
The authors retain the copyright and grant the right to publish in the magazine for the first time with the transfer of the commercial right to Tishreen University Journal for Research and Scientific Studies - Engineering Sciences Series
Under a CC BY- NC-SA 04 license that allows others to share the work with of the work's authorship and initial publication in this journal. Authors can use a copy of their articles in their scientific activity, and on their scientific websites, provided that the place of publication is indicted in Tishreen University Journal for Research and Scientific Studies - Engineering Sciences Series . The Readers have the right to send, print and subscribe to the initial version of the article, and the title of Tishreen University Journal for Research and Scientific Studies - Engineering Sciences Series Publisher
journal uses a CC BY-NC-SA license which mean
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material
- The licensor cannot revoke these freedoms as long as you follow the license terms.
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- NonCommercial — You may not use the material for commercial purposes.
- ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.