التبخر هو أحد العناصر الأساسية للدورة الهيدرولوجية و ضروري للعديد من الدراسات مثل الموازنة المائية, تصميم أنظمة الري و إدارة الموارد المائية, و يتطلب تقديره معرفة العديد من العناصر المناخية. على الرغم من أن هناك صيغاً تجريبيَّةً متوفرةً لتقدير التبخر, و لكن 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 و سرعة 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. و تم تقييم شبكات مختلفة بعدد مختلف من العصبونات و بتغيير دوال التفعيل المستخدمة في كل طبقة. و استُخدم جذر متوسط مربع الخطأ (RMSE) لتقييم دقة النموذج المُقترح. و قد 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) و قيمة R2 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 R2 (0.97).
This study suggests using other types of neural networks for estimation of
evaporation
References used
DALKILIC, Y.; OKKAN, U. and BAYKAN, N. Comparison of Different Ann Approaches in Daily Pan Evaporation Prediction. Journal of Water Resource and Protection, Vol. 6, 2014, 319-326
ESLAMIAN, S. S.; GOHARI, S. A.; BIABANAKI, M. and MALEKIAN, R. Estimation of Monthly Pan Evaporation Using Artificial Neural Networks and Support Vector Machines. Journal of Applied Sciences, Vol. 8, 2008, 3497-3502
GOAL, A. ANN Based Modeling for Prediction of Evaporation in Reservoirs. Vol. 22, No. 4, November, 2009, 351-358
Evaporation forms one of the hydrology cycle elements that it's hard to measure its actual amounts in the field conditions, so it’s estimated by calculations of experimental relations, which depend on climatic elements data. So the research goal is t
This study includes the possibility of using Artificial neural
networks (ANNs) with back-propagation algorithm in a short-term
prediction of water level in Qattinah Lake. The data used are the
water level data in the lake and rainfall data for the period from
1/5/2007 to 28/2/2005. 2009).
Accurate estimating and predicting of hydrological phenomena plays an influential role in the development and management of water resources, preparing of future plans according to different scenarios of climate changes. Evapotranspiration is one of t
To transcribe spoken language to written medium, most alphabets enable an unambiguous sound-to-letter rule. However, some writing systems have distanced themselves from this simple concept and little work exists in Natural Language Processing (NLP) o
Evapotranspiration forms one of the hydrology cycle elements that it's hard to
measure its actual amounts in the field conditions, so it’s estimated by calculations of
experimental relations that depend on climatic elements data. These estimations