ANALISIS EFEKTIVITAS KERAPATAN JARINGAN POS STASIUN HUJAN DI DAS KEDUNGSOKO DENGAN MENGGUNAKAN JARINGAN SARAF TIRUAN (ARTIFICIAL NEURAL NETWORK)
Abstract
Abstrak: Kualitas data curah hujan sangat bergantung pada kemampuan pos hidrologi dalam memantau karakteristik hidrologi dalam suatu Daerah Aliran Sungai. Oleh karena itu, diperlukan suatu kajian, agar memperoleh jaringan pos stasiun hujan yang efektif dalam hal perletakan stasiun pos stasiun hujan yang optimum dan mampu menggambarkan varibilitas ruang DAS yang teramati dengan baik. Lokasi penelitian terletak di DAS Kedungsoko yang luasnya adalah 416,54 km2, dan terdiri atas 8 pos stasiun hujan. Analisis dilakukan dengan membandingkan debit AWLR tahun 2001 s.d. 2010 dengan debit hasil model Jaringan Saraf Tiruan (JST). Model JST ini digunakan untuk mendapatkan debit dengan variabel masukan terdiri atas curah hujan maksimum tahunan pos stasiun hujan dengan satuan mm (X1), jarak pos stasiun hujan dengan pos AWLR dalam satuan km (X2), beda tinggi pos stasiun hujan dengan pos AWLR dalam satuan m (X3), dan koefisien thiessen (X4). Berdasarkan perbandingan debit hasil JST dengan debit AWLR, maka kerapatan jaringan pos stasiun hujan yang paling efektif adalah kombinasi pos stasiun hujan yang terdiri atas 4 (empat) pos stasiun hujan yang terdiri atas Pos Stasiun Hujan Pace, Pos Stasiun Hujan Banaran, Pos Stasiun Hujan Prambon, dan Pos Stasiun Hujan Badong dengan rerata Kesalahan Relatif debitnya adalah 3,763%.
Kata Kunci: Jaringan Saraf Tiruan, Stasiun Hujan, Kerapatan Stasiun Hujan, Efektivitas, Kesalahan Relatif
Â
Abstract: Quality of rainfall data is highly depend on the ability of hydrologic station in monitoring hydrological characteristics in the Watershed. Therefore it is necessary to get the accurate that is able to describe variability of the watershed. This study located in Kedungsoko Watershed with area is 416,54 km2, which there are 8 Rainfall Station. This analysis used to compare between AWLR flows with Artificial Neural Network (ANN) on years of 2001 to 2010. ANN used to obtain flows by input variables that are maximum rainfall on mm (X1), distance of rainfall station with AWLR station on km (X2), height difference betweenrainfall station with AWLR station on m (X3), and thiessen coefficient (X4). Based on comparison of ANN flows and AWLR flows, The most effective density of Rainfall Station is rainfall station combined with 4 rainfall station that are Pace Rainfall Station, Banaran Rainfall Station, Prambon Rainfall Station, and Badong Rainfall Station within the relative error is 3,763%. Â
Keywords: Artificial Neural Network, Rainfall Station, Density of Rainfall Station, Effectivity, Relative Error
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial 4.0 International License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
2.png)
