Deteksi Banjir Area Perkotaan Berbasis Citra Digital dan Convolutional Neural Network (VGG19)

Habibullah Akbar; Diah Aryani; Muhamad Bahrul Ulum

doi:10.55606/teknik.v2i3.798

Authors

Habibullah Akbar Universitas Esa Unggul
Diah Aryani Universitas Esa Unggul
Muhamad Bahrul Ulum Universitas Esa Unggul

DOI:

https://doi.org/10.55606/teknik.v2i3.798

Keywords:

VGG19, convolutional neural networks, flood detection, urban areas.

Abstract

Geographically and demographically, Indonesia has natural conditions that have the potential for floods disaster. There are at least 16,771 islands and 65,017 rivers that fill the archipelago. Unfortunately, the ever-increasing urban population accompanied by a lack of awareness and preparation for protecting the environment has resulted in a higher risk of flooding in urban areas. This study utilizes digital imagery to detect flood conditions in urban areas. In terms of access, digital images are available in urban CCTV monitoring systems as well as office areas, housing, and from people who have smartphones. The detection method used in this study is the VGG19 model which consists of 16 convolution layers and 3 standard classification layers. All convolution layers are divided into 5 blocks followed by a MaxPooling layer for each block to reduce the resolution of the input image. In the last layer, SoftMax layer is used to estimate the probability between flood labels and normal conditions. There are 4 parameters that were optimized during the VGG19 model training process, namely Batch Size, Learning Rate, Dropout and Epoch (training repetition). To test the proposed model, public datasets are used, namely the Roadway Flooding Image Dataset and Road Vehicle Images Dataset. The best flood detection results (or normal conditions) achieve the accuracy of 98.78%. As for the other three performance metrics, namely precision, recall and F1-score, they reach 99%. These results are generated by the VGG19 model with a Batch Size parameter of 20, a Learning Rate of 1e-5 (0.00001), 50% Dropout and 100 Epoch. The achievement values of the four metrics can be considered quite good, so that the VGG19 model has the opportunity to be developed for flood detection applications in order to monitor urban flood conditions.

References

A’ziziyyah, A. A., Nugroho, I. I., Sabillillah, R., Aji, B. A. S., & Amiroh, K. (2022). Perbandingan sistem deteksi banjir menggunakan algoritma Naive Bayes dan K-NN berbasis IoT. IJCIT (Indonesian Journal on Computer and Information Technology), 7(1).

Adwil, B. D. B. (2022). Pentingnya status pulau bagi Gazetir Republik Indonesia. Direktorat Jenderal Bina Administrasi Kewilayahan Kementerian Dalam Negeri Republik Indonesia. https://ditjenbinaadwil.kemendagri.go.id/berita/detail/pentingnya-status-pulau-bagi-gazetir-republik-indonesia

Akbar, H., Dewi, S., Rozali, Y. A., Lunanta, L. P., Anwar, N., & Anwar, D. (2021). Exploiting facial action unit in video for recognizing depression using metaheuristic and neural networks. In 2021 1st International Conference on Computer Science and Artificial Intelligence (ICCSAI) (Vol. 1, pp. 438–443).

Angrelia, C., Prihasta, R., Mubarok, A. C., & Utami, W. K. (2020). Peranan Pemerintah Kota Tangerang dalam penanggulangan dan pencegahan banjir tahun 2020. Jurnal Agregasi: Aksi Reformasi Government dalam Demokrasi, 8(1).

Aurora, A. N., et al. (2021). Studi komparasi kebijakan penanggulangan banjir di wilayah DKI Jakarta pada era kepemimpinan Basuki Tjahja Purnama dan Anies Baswedan. Jurnal Politik dan Government Studies, 10(3), 138–161.

Dihni, V. A. (2021). BNPB: Kejadian bencana alam Indonesia capai 3.058 sepanjang 2021. Databoks. https://databoks.katadata.co.id/datapublish/2021/12/29/bnpb-kejadian-bencana-alam-indonesia-capai-3058-sepanjang-2021

DLH. (2016). Kerusakan sungai dan daerah aliran sungai di Indonesia. Dinas Lingkungan Hidup Kabupaten Grobogan. https://dlh.grobogan.go.id/index.php/info-lh/berita/36-kerusakan-sungai-dan-daerah-aliran-sungai-di-indonesia

Findayani, A. (2018). Kesiapsiagaan masyarakat dalam penanggulangan banjir di Kota Semarang. Jurnal Geografi: Media Informasi Pengembangan dan Profesi Kegeografian, 12(1), 102–114.

Fukushima, K., & Miyake, S. (1982). Neocognitron: A self-organizing neural network model for a mechanism of visual pattern recognition. In Competition and cooperation in neural nets (pp. 267–285). Springer.

He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 770–778).

Hidayat, M. A., Husni, N. L., & Damsi, F. (2022). Pendeteksi banjir dengan image processing berbasis convolutional neural network (CNN) pada kamera pengawas: Image processing based flood detector using convolutional neural network (CNN) within surveillance camera. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 2(2), 10–18.

Jovandy, A. (2020). Image classification using VGG19 and ResNet50 [Computer software]. GitHub. https://github.com/Adithia88/Image-Classification-using-VGG19-and-Resnet

Khattar, A., & Quadri, S. M. K. (2022). Generalization of convolutional network to domain adaptation network for classification of disaster images on Twitter. Multimedia Tools and Applications, 1–28.

Khvostikov, A., Aderghal, K., Benois-Pineau, J., Krylov, A., & Catheline, G. (2018). 3D CNN-based classification using sMRI and MD-DTI images for Alzheimer disease studies. arXiv. https://arxiv.org/abs/1801.05968

Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25, 1097–1105.

LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278–2324.

Lidwina, A. (2020). Berapa jumlah kejadian banjir dalam lima tahun terakhir? Databoks. https://databoks.katadata.co.id/datapublish/2020/06/08/berapa-jumlah-kejadian-banjir-dalam-lima-tahun-terakhir

Rahardjo, P. N. (2018). 7 penyebab banjir di wilayah perkotaan yang padat penduduknya. Jurnal Air Indonesia, 7(2).

Sazara, C., Cetin, M., & Iftekharuddinbh, K. (2019). Image dataset for roadway flooding (Version 1) [Data set]. Mendeley Data. https://doi.org/10.17632/t395bwcvbw.1

Sebastian, L. (2008). Pendekatan pencegahan dan penanggulangan banjir.

Siahaan, A. Y. S., et al. (2019). Implementasi program pembangunan drainase dalam upaya penanggulangan banjir di Kota Medan.

Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv. https://arxiv.org/abs/1409.1556

Sulistyowati, R., Sujono, H. A., & Musthofa, A. K. (2015). Sistem pendeteksi banjir berbasis sensor ultrasonik dan mikrokontroler dengan media komunikasi SMS gateway [Skripsi, Institut Teknologi Adhi Tama Surabaya].

Szegedy, C., et al. (2015). Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 1–9).

Ulum, M. C. (2013). Governance dan capacity building dalam manajemen bencana banjir di Indonesia. Jurnal Dialog Penanggulangan Bencana, 4(2), 69–76.

Yeafi, A. (2021). Road vehicle images dataset [Data set]. Kaggle. https://www.kaggle.com/datasets/ashfakyeafi/road-vehicle-images-dataset?resource=download