Geospatial and Artificial Neural Network Applications for Prioritization of Watershed Prediction
Surya Budi Lesmana1, Ery Suhartanto2, Agus Suharyanto3, Very. Dermawan4

1S.B Lesmana*, Department of Civil Engineering, Muhammadiyah University, Yogyakarta, Indonesia.
2E. Suhartanto, Professor, Brawijaya University, Malang, Indonesia.
3A. Suharyanto, Professor , Brawijaya University, Malang, Indonesia.
4V. Darmawan, Professor, Brawijaya University, Malang, Indonesia.
Manuscript received on January 13, 2020. | Revised Manuscript received on January 21, 2020. | Manuscript published on February 10, 2020. | PP: 231-236 | Volume-9 Issue-4, February 2020. | Retrieval Number: D1142029420/2020©BEIESP | DOI: 10.35940/ijitee.D1142.029420
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Characteristics of the river basin formed by natural factors and non-natural factors that makes up an ecosystem. One of the characters that create the river basin of the physical element is morphometry. Morphometry has three parameters such as linear, relief, and areal. The linear aspect consist of stream order (U), stream length (Lu), bifurcation ratio (Rb ), stream length ratio (Rl ), bifurcation ratio (Rb ). Relief aspect consists of basin relief (Bh), relief ratio (Rh), ruggedness number (Rn). Areal elements comprise drainage density (Dd ), stream frequency (Fs ), texture ratio (T), form factor (Rf ), circularity ratio (Rc ), elongation ratio (Re ), length of overland flow (Lg ), constant channel maintenance (C). This study aims to analyze the characteristics of watershed morphometry and implement Geographical Information System (GIS) and Artificial Neural Network (ANN) to get watershed priority predictions. After analyze, the prioritization based on morphometry that is six sub-watershed with very high priority, two sub-watershed with high priority, four sub-watershed with medium priority and five sub-watershed have low priorities. From the test results by measuring method using a neural network based, it is known that neural network algorithms yield accuracy values 90.00%, and class precision 90.82 %. The model produced satisfactory results and showed a very good agreement between the predicted and observed data. 
Keywords: ANN, Geographic Information Systems (GIS), Morphometry Watershed.
Scope of the Article:  Energy Harvesting and Transfer for Wireless Sensor Networks