PEMODELAN KONDISI UDARA ATAS DENGAN BACK-PROPAGATION NEURAL NETWORK DAN PEMANFAATANNYA UNTUK PENENTUAN HARI SEMAI
Article Sidebar
Main Article Content
Abstract
hari semai. Data rawinsonde dari periode 1995-1999 dari Semarang dan Bandung
dipakai untuk melatih jaringan. Jaringan terdiri dari 10 buah simpul pada layer input, 40
simpul pada layer tersembunyi dan 2 buah simpul pada layer output. Jumlah simpul yang optimal pada layer tersembunyi untuk memodelkan 10 parameter udara atas adalah 40 buah. Banyaknya iterasi yang optimal untuk mencapai konvergensi dengan kesalahan rata-rata kuadrat 0.05 adalah 700 kali. Jaringan yang dihasilkan dapat menghasilkan prakiraan kelayakan hari semai atau tidak dengan tingkat ketelitian yang lebih besar dari 75%.
A back -propagation artificial neural network was used to model the relationship between upper-air parameters obtained by rawinsonde and the seeding day favorability. A series of data obtained from rawinsonde launched at Semarang and Bandung from 1995-1999 period was used as input or training data. The network comprised of 10, 40 and 2 simpuls located at the input, hidden and output layers respectively. The optimum number of hidden units of this network was 40. The training iteration required to reach convergence with RMS error of 0.05 was 700. The network resulted can predict the seeding favorability greater than 75% accuracy.
Article Details
Authors who publish with this journal agree to the following terms:
a). Authors retain copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
b). 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 acknowledgment of its initial publication in this journal.
c). 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).
d). Each author must sign the copyright transfer statement. The article will not be published unless this form has been signed and received.
OPEN ACCESS POLICY
Jurnal Sains & Teknologi Modifikasi Cuaca provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
JSTMC by BBTMC-BPPT is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Permissions beyond the scope of this license may be available at http://ejurnal.bppt.go.id/index.php/JSTMC