BibTex Citation Data :
@article{YPJ8055, author = {Siti Yuniar Pangestu and Rahmat Gernowo}, title = {EVALUASI MODEL JARINGAN SYARAF TIRUAN METODE BACKPROPAGATION UNTUK PREDIKSI IKLIM EKSTRIM DENGAN KORELASI CURAH HUJAN DAN TINGGI MUKA LAUT DI SEMARANG}, journal = {Youngster Physics Journal}, volume = {4}, number = {1}, year = {2015}, keywords = {Artifical Neural Network, Backpropagation, extreme climate, rainfall, sea level rise}, abstract = { Global warming is an event average temperature rise of the atmosphere, ocean, and land. Atmosphere temperature changes cause the physical conditions of the atmosphere becomes unstable, causing anomalies weather parameters that cause climate change. The impact of climate changes is increasing frequency of natural disasters or extreme weather, changes in rainfall patterns, and rising sea level rise. To minimize disaster prediction is carried out by making modeling with artificial neural network method, algorithm of backpropagation models. The research was conducted in Semarang, using data from rainfall, precipitation, temperature, cloud cover, and sea level rise in 2002 until 2012.Artificial neural network modeling was used Matlab R2010a. Network training by using one unit of input layer, two hidden layer units, and one unit of output layer. The first hidden layer with 10 neurons and the second hidden layer used 5 neurons. The best results on the training and testing of the network by using the parameter learning rate 0.3 and a momentum 0.6. The results obtained in the training get a percentage value of correlation is 79.0% and in the testing process to get the percentage correlation is 77.5%. Keywords: Artifical Neural Network, Backpropagation, extreme climate, rainfall, sea level rise }, issn = {2302-7371}, pages = {67--72} url = {https://ejournal3.undip.ac.id/index.php/bfd/article/view/8055} }
Refworks Citation Data :
Global warming is an event average temperature rise of the atmosphere, ocean, and land. Atmosphere temperature changes cause the physical conditions of the atmosphere becomes unstable, causing anomalies weather parameters that cause climate change. The impact of climate changes is increasing frequency of natural disasters or extreme weather, changes in rainfall patterns, and rising sea level rise. To minimize disaster prediction is carried out by making modeling with artificial neural network method, algorithm of backpropagation models.
The research was conducted in Semarang, using data from rainfall, precipitation, temperature, cloud cover, and sea level rise in 2002 until 2012.Artificial neural network modeling was used Matlab R2010a. Network training by using one unit of input layer, two hidden layer units, and one unit of output layer. The first hidden layer with 10 neurons and the second hidden layer used 5 neurons.
The best results on the training and testing of the network by using the parameter learning rate 0.3 and a momentum 0.6. The results obtained in the training get a percentage value of correlation is 79.0% and in the testing process to get the percentage correlation is 77.5%.
Keywords: Artifical Neural Network, Backpropagation, extreme climate, rainfall, sea level rise
Last update:
