Stasiun Cuaca Mini Pintar Berbasis Deep Learning
Abstract
Abstrak — Perubahan iklim dan cuaca yang semakin tidak menentu menuntut data cuaca lokal yang akurat dan prediksi yang cepat. Namun, stasiun cuaca konvensional cenderung mahal dan rumit, sehingga sulit diakses oleh masyarakat umum. Untuk mengatasi hal ini, penelitian ini mengembangkan Stasiun Cuaca Mini Pintar berbasis Internet of Things (IoT) dan Deep Learning. Sistem ini menggunakan mikrokontroler ESP32-S3, sensor BME280 (suhu, kelembaban, tekanan), dan anemometer (kecepatan angin) untuk mengumpulkan data secara otomatis, yang disimpan di Google Spreadsheet. Data kemudian diproses melalui pembersihan, penanganan nilai hilang, normalisasi, dan pembentukan urutan waktu. Prediksi dilakukan menggunakan model Long Short-Term Memory (LSTM) yang dioptimalkan dengan Keras Tuner. Model ini mampu memprediksi suhu, kelembaban, tekanan, dan kecepatan angin dengan akurasi tinggi, ditunjukkan oleh nilai R² antara 0.83 hingga 0.96. Untuk klasifikasi cuaca (cerah atau hujan), model mencapai akurasi 88%. Sisrem ini juga dilengkapi API FatApi dan aplikasi mobile berbasis React Native Expo sebagai antarmuka pengguna. Hasil penelitian menunjukkan bahwa kombinasi IoT dan Deep Learning efektif untuk solusi cuaca yang akurat dan terjangkau.
Kata kunci— Stasiun Cuaca Mini Pintar, Internet of Things (IoT), Deep Learning, Long Short-Term Memory (Long Short-Term Memory (LSTM)), Prediksi Cuaca.
References
[1] T. Lattifia, P. W. Buana, and N. K. D. Rusjayanthi, “Model Prediksi Cuaca Menggunakan Metode LSTM,” JITTER: Jurnal Ilmiah Teknologi dan Komputer, vol. 3, no. 1, 2022.
[2] Y. E. N. Nugraha, I. Ariawan, and W. A. Arifin, “Weather Forecast from Time Series Data Using LSTM Algorithm,” 2023, doi: 10.51903/jtikp.v14i1.531.
[3] K. Ioannou, D. Karampatzakis, P. Amanatidis, V. Aggelopoulos, and I. Karmiris, “Low-Cost Automatic Weather Stations in the Internet of Things,” Information (Switzerland), vol. 12, no. 4, pp. 1–21, 2021, doi: 10.3390/info12040146.
[4] E. Supriyadi, “Prediksi Parameter Cuaca Menggunakan Deep Learning Long-Short Term Memory (LSTM) / Weather Parameters Prediction Using Deep Learning Long-Short Term Memory (LSTM),” Jurnal Meteorologi dan Geofisika, vol. 21, no. 21, pp. 56–59, 2019. [Online]. Available: http://bmkgsoft.database.bmkg.go.id
[5] L. Chen et al., “FuXi: A Cascade Machine Learning Forecasting System for 15-Day Global Weather Forecast,” NPJ Climate and Atmospheric Science, vol. 6, no. 1, pp. 1–11, 2023, doi: 10.1038/s41612-023-00512-1.
[6] I. Salehin, I. M. Talha, M. Mehedi Hasan, S. T. Dip, M. Saifuzzaman, and N. N. Moon, “An Artificial Intelligence Based Rainfall Prediction Using LSTM and Neural Network,” Proceedings of 2020 IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE 2020), pp. 5–8, 2020, doi: 10.1109/WIECON-ECE52138.2020.9398022.
[7] R. Farikhul Firdaus and I. V. Paputungan, “Prediksi Curah Hujan di Kota Bandung Menggunakan Metode Long Short Term Memory,” 2022, doi: 10.54082/jupin.99.
[8] K. Chao Miao et al., “Application of LSTM for Short-Term Fog Forecasting Based on Meteorological Elements,” Neurocomputing, vol. 408, pp. 285–291, 2020, doi: 10.1016/j.neucom.2019.12.129.
[9] W. Fang, Y. Chen, and Q. Xue, “Survey on Research of RNN-Based Spatio-Temporal Sequence Prediction Algorithms,” Journal on Big Data, vol. 3, no. 3, pp. 97–110, 2021, doi: 10.32604/jbd.2021.016993.
[10] A. F. Pauzi and M. Z. Hasan, “Development of IoT Based Weather Reporting System,” IOP Conference Series: Materials Science and Engineering, vol. 917, no. 1, 2020, doi: 10.1088/1757-899X/917/1/012032.
[11] Q. Wen et al., “Time Series Data Augmentation for Deep Learning: A Survey,” IJCAI International Joint Conference on Artificial Intelligence, pp. 4653–4660, 2021, doi: 10.24963/ijcai.2021/631.
[12] L. Zhang, Z. Huang, W. Liu, Z. Guo, and Z. Zhang, “Weather Radar Echo Prediction Method Based on Convolution Neural Network and Long Short-Term Memory Networks for Sustainable E-Agriculture,” Journal of Cleaner Production, vol. 298, p. 126776, 2021, doi: 10.1016/j.jclepro.2021.126776.
[13] S. Aburass, O. Dorgham, and J. Al Shaqsi, “A Hybrid Machine Learning Model for Classifying Gene Mutations in Cancer Using LSTM, BiLSTM, CNN, GRU, and GloVe,” Systems and Soft Computing, vol. 6, no. August, p. 200110, 2024, doi: 10.1016/j.sasc.2024.200110.
[14] A. Al Hamoud, A. Hoenig, and K. Roy, “Sentence Subjectivity Analysis of a Political and Ideological Debate Dataset Using LSTM and BiLSTM with Attention and GRU Models,” Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 10, pp. 7974–7987, 2022, doi: 10.1016/j.jksuci.2022.07.014.
[15] B. C. Mateus, M. Mendes, J. T. Farinha, R. Assis, and A. M. Cardoso, “Comparing LSTM and GRU Models to Predict the Condition of a Pulp Paper Press,” Energies (Basel), vol. 14, no. 21, pp. 1–21, 2021, doi: 10.3390/en14216958.
[16] D. Chicco, M. J. Warrens, and G. Jurman, “The Coefficient of Determination R-Squared Is More Informative than SMAPE, MAE, MAPE, MSE and RMSE in Regression Analysis Evaluation,” pp. 1–24, 2021, doi: 10.7717/peerj-cs.623.
[17] Anita S. and Cahyono N., “Penerapan Bi-LSTM dengan Optimizer ADAM dan Word2Vec untuk Analisis Sentimen,” Ejournal.Katersipublisher.Com, vol. 1, no. 2, pp. 35–39, 2024.
