Prediction Of Water Distribution Uniformity Of Sprinkler Irrigation System Based On Machine Learning Algorithms /
Khadiga Tawfiek Elhussiny Badr,
Prediction Of Water Distribution Uniformity Of Sprinkler Irrigation System Based On Machine Learning Algorithms / / التنبؤ بانتظامية توزيع المياه لنظام الري بالرش اعتمادا علي خوارزميات التعلم الآلي By Khadiga Tawfiek Elhussiny Badr; Supervision Committee Dr. Ahmed Mahrous Hassan, Dr. Ali Mokhtar Mohammed, Dr. Ahmed Reda Abo Habsa, Dr. Mohamed Hanafy Hassan - 103 pages : illustrations ; 25 cm. + CD.
Thesis (M.Sc.) -Cairo University, 2024.
Bibliography: pages 78-96.
The water shortage is one of the main challenges for future water policy. The coefficients of uniformity (Christiansen's uniformity coefficient (CU) and distribution uniformity (DU)) are an important parameter for designing irrigation systems, and these are accurate indicator for water loss. In this study, three machine learning algorithms (RF: Random Forest, XGB: Extreme Gradient Boosting and XGB-RF: Random Forest-Extreme Gradient Boosting), after training the different algorithms and testing it, the best result was as following: using XGB-RF to predict CU and DU with the first scenario. Were developed to predict the water distribution uniformity based on operating pressure, heights of sprinkler, nozzle diameter (discharge), wind speed, relative humidity, maximum and minimum temperature for three different impact sprinklers (KA-4, FOX and 2520) for square and triangular system layout. The main findings were; the highest CU values for (2520 sprinkler) under 200 kPa, 0.5m height, Nozzle 2.5mm was 86.7% in the square system and the discharge was 0.855 m3/h, Meanwhile, in the triangular system, it was 87.3% under the same pressure and discharge but at 1m height. Through the simulation work, the highest values of coefficient of determination (R2) were 0.796, 0.825 and 0.929 in RF, XGB and XGB-RF respectively in the first scenario for CU. Moreover, for the DU, the highest values of R2 were 0.701, 0.479 and 0.826 in RF, XGB and XGB-RF respectively in the first scenario. The obtained results revealed that the machine learning models is promising and can be as a rapid tool for decision-makers to manage the water scarcity. في هذه الرسالة، تم تطوير ثلاث خوارزميات للتعلم الآلي (, XGB ,RF و (XGB - RF للتنبؤ بتوحيد توزيع المياه بناءً على ضغط التشغيل وارتفاعات الرشاش وقطر الفوهة (التصرف) وسرعة الرياح والرطوبة النسبية ودرجة الحرارة العظمي والصغري لثلاث رشاشات (FOX ,KA-4 و (2520 لتخطيط النظام المربع والمثلث. وكانت النتائج الرئيسية هي أعلى قيمة CU كانت 87.3٪ في النظام المثلث للرشاش 2520 تحت ضغط تشغيل 200 كيلو باسكال، وارتفاع 1 متر وتصرف 0,855 متر مكعب/ساعة (قطر الفوهة 2,5 ملم). من خلال أعمال المحاكاة كانت أعلي قيم معامل التحديد (R2) هي 0.796 و 0.825 و 0.929 في RF ، XGB و XGB-RF على الترتيب في السيناريو الأول لـ CU.
Text in English and abstract in Arabic & English.
Irrigation
Water distribution uniformity sprinkler irrigation water shortage machine learning algorithms
631.587
Prediction Of Water Distribution Uniformity Of Sprinkler Irrigation System Based On Machine Learning Algorithms / / التنبؤ بانتظامية توزيع المياه لنظام الري بالرش اعتمادا علي خوارزميات التعلم الآلي By Khadiga Tawfiek Elhussiny Badr; Supervision Committee Dr. Ahmed Mahrous Hassan, Dr. Ali Mokhtar Mohammed, Dr. Ahmed Reda Abo Habsa, Dr. Mohamed Hanafy Hassan - 103 pages : illustrations ; 25 cm. + CD.
Thesis (M.Sc.) -Cairo University, 2024.
Bibliography: pages 78-96.
The water shortage is one of the main challenges for future water policy. The coefficients of uniformity (Christiansen's uniformity coefficient (CU) and distribution uniformity (DU)) are an important parameter for designing irrigation systems, and these are accurate indicator for water loss. In this study, three machine learning algorithms (RF: Random Forest, XGB: Extreme Gradient Boosting and XGB-RF: Random Forest-Extreme Gradient Boosting), after training the different algorithms and testing it, the best result was as following: using XGB-RF to predict CU and DU with the first scenario. Were developed to predict the water distribution uniformity based on operating pressure, heights of sprinkler, nozzle diameter (discharge), wind speed, relative humidity, maximum and minimum temperature for three different impact sprinklers (KA-4, FOX and 2520) for square and triangular system layout. The main findings were; the highest CU values for (2520 sprinkler) under 200 kPa, 0.5m height, Nozzle 2.5mm was 86.7% in the square system and the discharge was 0.855 m3/h, Meanwhile, in the triangular system, it was 87.3% under the same pressure and discharge but at 1m height. Through the simulation work, the highest values of coefficient of determination (R2) were 0.796, 0.825 and 0.929 in RF, XGB and XGB-RF respectively in the first scenario for CU. Moreover, for the DU, the highest values of R2 were 0.701, 0.479 and 0.826 in RF, XGB and XGB-RF respectively in the first scenario. The obtained results revealed that the machine learning models is promising and can be as a rapid tool for decision-makers to manage the water scarcity. في هذه الرسالة، تم تطوير ثلاث خوارزميات للتعلم الآلي (, XGB ,RF و (XGB - RF للتنبؤ بتوحيد توزيع المياه بناءً على ضغط التشغيل وارتفاعات الرشاش وقطر الفوهة (التصرف) وسرعة الرياح والرطوبة النسبية ودرجة الحرارة العظمي والصغري لثلاث رشاشات (FOX ,KA-4 و (2520 لتخطيط النظام المربع والمثلث. وكانت النتائج الرئيسية هي أعلى قيمة CU كانت 87.3٪ في النظام المثلث للرشاش 2520 تحت ضغط تشغيل 200 كيلو باسكال، وارتفاع 1 متر وتصرف 0,855 متر مكعب/ساعة (قطر الفوهة 2,5 ملم). من خلال أعمال المحاكاة كانت أعلي قيم معامل التحديد (R2) هي 0.796 و 0.825 و 0.929 في RF ، XGB و XGB-RF على الترتيب في السيناريو الأول لـ CU.
Text in English and abstract in Arabic & English.
Irrigation
Water distribution uniformity sprinkler irrigation water shortage machine learning algorithms
631.587