Prediksi Hujan Menggunakan Metode Artificial Neural Network, K-Nearest Neighbors, dan Naïve Bayes
Abstract
Rain is a natural phenomenon that has a significant impact on human life and ecosystems around the world. The ability to predict the weather, including predicting the next day's rain, has become an important aspect of our daily lives. Accurate rain predictions have broad implications, from planning outdoor activities to natural resource management, as well as controlling natural disasters. This research presents the results of an analysis of whether it will rain or not tomorrow based on 22 features, including location, temperature, wind speed, wind direction, humidity, and also the number of clouds covering the sky. In an effort to improve the accuracy of rain predictions, various methods have been developed, including Artificial Neural Network (ANN), K-Nearest Neighbors (KNN), and Naive Bayes. After training and testing the models from these three methods, an evaluation was carried out using a confusion matrix and classification report to measure prediction performance. The experimental results show that ANN, KNN and Naive Bayes obtain accuracy scores of 85%, 84%, and 79%, respectively. So, it can be concluded that ANN is the best method for predicting tomorrow's rain.
Downloads
References
Panggabean, D. A., & Aruan, N. M. (2021). Prediksi Tinggi Curah Hujan Dan Kecepatan Angin Berdasarkan Data Cuaca Dengan Penerapan Algoritma Artificial Neural Network (Ann). PROSIDING SEMINASTIKA, 3(1), 1-7.
Aprianto, R., & Puspitasari, P. A. (2020). Prediksi curah hujan bulanan tahun 2020 kabupaten Sumbawa menggunakan Artificial Neural Network (ANN) Back Propagation. Prosiding Seminar Nasional IPPeMas, 1(1), 622-628.
Gultepe, I., Sharman, R., Williams, P. D., Zhou, B., Ellrod, G., Minnis, P., . . . Gharabaghi. (2019). A review of high impact weather for aviation meteorology. Pure and applied geophysics, 176, 1869-1921.
Herlina, N., & Prasetyorini, A. (2020). Pengaruh perubahan iklim pada musim tanam dan produktivitas jagung (Zea mays L.) di Kabupaten Malang. Jurnal Ilmu Pertanian Indonesia, 25(1), 118-128.
Syamsul, N. H., Fathona, I. W., & Kirom, M. R. (2019). Studi Pengaruh Suhu Substrat Teradap Produksi Daya Listrik Microbial Fuel Cell Dengan Substrat Lumpur Sawah Dan Nasi Basi. eProceedings of Engineering, 6(2).
Putra, R. M. (2020). Prediksi Curah Hujan Harian di Stasiun Meteorologi Kemayoran Menggunakan Artificial Neural Network (ANN). Buletin GAW Bariri (BGB), 1(2), 101-108.
Ananda, N., & Aras, R. A. (2021). Clustering Pengeluaran Tahunan Berbagai Macam Produk Menggunakan Metode K-Means. Dalam Seminar Nasional Sains dan Teknologi Informasi (SENSASI) (hal. 143-147).
Wibisono, A. B., & Fahrurozi, A. (2020). Perbandingan Algoritma Klasifikasi Dalam Pengklasifikasian Data Penyakit Jantung Koroner. jurnal ilmiah teknologi dan rekayasa, 24(3), 161-170.
Haq, A. U., Li, J. P., Memon, M. H., Nazir, S., & Sun, R. (2018). A hybrid intelligent system framework for the prediction of heart disease using machine learning algorithms. Mobile information systems, 2018, 1-21.
Walczak, S. (2019). Artificial Neural Newtworks. Advanced methodologies and technologies in artificial intelligence, computer simulation, and human-computer interaction. IGI Global.
Abiodun, O. I., Jantan, A., Omolara, A. E., Dada, K. V., Mohamed, N. A., & Arshad, H. (2018). State-of-the-art in artificial neural networks applications: A survey. Heliyon, 4(11), 6-8.
Azis, A., Zy, A. T., & Sunge, A. S. (2024). Prediksi Penjualan Obat Dan Alat Kesehatan Terlaris Menggunakan Algoritma K-Nearest Neighbor. Jurnal Teknologi Dan Sistem Informasi Bisnis, 6(1), 117-124.
Nursobah, N., Lailiyah, S., Harpad, B., & Fahmi, M. (2022). Penerapan Data Mining Untuk Prediksi Perkiraan Hujan dengan Menggunakan Algoritma K-Nearest Neighbor. Building Of Informatics, Technology And Science (Bits), 4(3), 1395-1400.
Azizah, H. W., Nurdiawan, O., Dwilestari, G., Kaslani, K., & Tohidi, E. (2022). Klasifikasi Pemberian Bantuan UMKM Cirebon dengan Menggunakan Algoritma K-Nearest Neighbor. Journal of Computer System and Informatics (JoSYC), 3(3), 110-115.
Rizqi, A. A., & Kusumaningsih, D. (2022). Klasifikasi Curah Hujan di Kota Bogor Provinsi Jawa Barat dengan Menggunakan Metode Naive Bayes. Prosiding Seminar Nasional Mahasiswa Fakultas Teknologi Informasi (SENAFTI), 1(1), 542-550.
Hayuningtyas, R. Y. (2019). Penerapan Algoritma Naive Bayes untuk Rekomendasi Pakaian Wanita. Jurnal Infromatika, 6(1), 18-22.
Ridwan, A. (2020). Penerapan Algoritma Naive Bayes Untuk Klasifikasi Penyakit Diabetes Mellitus. J. SISKOM-KB (Sistem Komput. dan Kecerdasan Buatan), 4(1), 15-21.
Saputra, R., & Hasan, F. N. (2024). Sentiment Analysis on Free Lunch & Milk Program Using Naive Bayes Algorithm. Jurnal Teknologi Dan Sistem Informasi Bisnis, 6(3), 411-419.
Andika, L. A., Azizah, P. A., & Respatiwulan, R. (2019). Analisis Sentimen Masyarakat terhadap Hasil Quick Count Pemilihan Presiden Indonesia 2019 pada Media Sosial Twitter Menggunakan Metode Naive Bayes Classifier. Indonesian Journal of Applied Statistics, 2(1), 34-41.
Santoso, B. (2019). An analysis of spam email detection performance assessment using machine learning. Jurnal Online Informatika, 4(1), 53-56.
Derisma, D., & others. (2020). Perbandingan Kinerja Algoritma untuk Prediksi Penyakit Jantung dengan Teknik Data Mining. Journal of Applied Informatics and Computing, 4(1), 84-88.
Rafrastaraa, F. A., Pramunendar, R. A., Prabowo, D. P., Kartikadarma, E., & Sudibyo, U. (2023). Optimasi Algoritma Random Forest menggunakan Principal Component Analysis untuk Deteksi Malware. Jurnal Teknologi Dan Sistem Informasi Bisnis, 5(3), 217-223.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under an Attribution 4.0 International (CC BY 4.0) that allows others to share — copy and redistribute the material in any medium or format and adapt — remix, transform, and build upon the material for any purpose, even commercially with an acknowledgment of the work's authorship and initial publication in this journal.
