Perbandingan Metode Deep Learning dengan Model LSTM dan GRU untuk Prediksi Perubahan Iklim
-
Amin Mustofa
*
Universitas Islam Indonesia, Yogyakarta,
Indonesia
- Hendra Setiawan Universitas Islam Indonesia, Yogyakarta, Indonesia (*) Corresponding Author
Abstract
Climate plays a critical role in determining the quality of life in Indonesia, which demands in-depth understanding through the Koppen climate classification and the latest technology. From agriculture to urban infrastructure, public health, to ecosystem sustainability, every aspect of our lives is affected by climate conditions. Deep Learning methods such as Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU) are used to predict time series data because of their adaptive ability in learning complex data patterns. The LSTM and GRU models were tested with 2010-2021 data using batch_size 64, epochs 150, optimizer adam, and showed high accuracy (<10%). LSTM recorded MAPE: Rainfall 5.50%, Humidity 7.60%, Temperature 4.36%, Sunlight 8.29%. GRU recorded MAPE: Rainfall 5.01%, Humidity 6.86%, Temperature 4.35%, Sunlight 8.28%. Predictions for 2028 show that the Special Region of Yogyakarta has a Tropical Monsoon (Am), Tropical Savannah (As) and Tropical Rain Forest (Af) climate. These climate changes have significant impacts: increased rainfall increases the risk of flooding, threatening infrastructure and lives, while the As climate reduces agricultural productivity and increases food insecurity. Changes in rainfall and temperature affect people's health, with high humidity increasing the risk of tropical diseases and high temperatures causing heat stress. Climate change in the Am type increases the risk of floods and landslides, while in the Af type it threatens tropical rainforest ecosystems.
Downloads
References
B. D. A. Nugroho, “Relationships among Global Climate Indices and Rainfall Pattern to Detect Impact of Climate Change in Yogyakarta Special Region, Indonesia,” IOP Conf Ser Earth Environ Sci, vol. 515, no. 1, 2020, doi: 10.1088/1755-1315/515/1/012038.
E. Saptutyningsih, “Does social capital matter in climate change adaptation? A lesson from agricultural sector in Yogyakarta, Indonesia,” Land use policy, vol. 95, 2020, doi: 10.1016/j.landusepol.2019.104189.
S. R. K. Sari, “Strategy mitigation action of climate change of land-based in geopark karst area of Gunungsewu, Yogyakarta, Indonesia,” IOP Conf Ser Earth Environ Sci, vol. 824, no. 1, 2021, doi: 10.1088/1755-1315/824/1/012071.
F. Farhangi, A. Sadeghi-Niaraki, J. Safari Bazargani, S. V. Razavi-Termeh, D. Hussain, and S.-M. Choi, “Time-Series Hourly Sea Surface Temperature Prediction Using Deep Neural Network Models,” J Mar Sci Eng, vol. 11, no. 6, pp. 11–36, May 2023, doi: 10.3390/jmse11061136.
L. Fitriana, “Climate stresses and its impact towards food sufficiency: A case in Bantul regency Yogyakarta-Indonesia,” IOP Conf Ser Earth Environ Sci, vol. 653, no. 1, 2021, doi: 10.1088/1755-1315/653/1/012141.
E. Saptutyningsih, “Climate change adaptability of the agriculture sector in Yogyakarta, Indonesia,” E3S Web of Conferences, vol. 232, 2021, doi: 10.1051/e3sconf/202123204001.
J. H. Mulyo, “Assessing the Vulnerability of Farm Households in Yogyakarta to Risks Associated with Climate Change,” E3S Web of Conferences, vol. 142, 2020, doi: 10.1051/e3sconf/202014203002.
S. Mahjoub, “Predicting Energy Consumption Using LSTM, Multi-Layer GRU and Drop-GRU Neural Networks,” Sensors, vol. 22, no. 11, 2022, doi: 10.3390/s22114062.
G. R. FREDYAN and P. Kusuma, “Spatiotemporal convolutional LSTM with attention mechanism for monthly rainfall prediction,” 2022. doi: 10.28919/cmbn/7761.
A. Saxena, R. Chauhan, D. Chauhan, and G. Aggarwal, “Time Series Prediction of Sea Surface Temperature Using LSTM,” 2023. doi: 10.1109/Confluence56041.2023.10048855.
P. T. Yamak, L. Yujian, and P. K. Gadosey, “A Comparison between ARIMA, LSTM, and GRU for Time Series Forecasting,” in Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence, New York, NY, USA: ACM, Dec. 2019, pp. 49–55. doi: 10.1145/3377713.3377722.
H. Sak, A. Senior, and F. Beaufays, “Long short-term memory recurrent neural network architectures for large scale acoustic modeling,” Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 338–342, Aug. 2014, doi: DOI:10.21437/Interspeech.2014-80.
M. Gupta, A. Asthana, N. Joshi, and P. Mehndiratta, “Improving Time Series Forecasting Using Mathematical and Deep Learning Models,” 2018, pp. 115–125. doi: 10.1007/978-3-030-04780-1_8.
A. Rasyid, D. Agushinta R., and D. Ediraras, “Deep Learning Methods In Predicting Indonesia Composite Stock Price Index (IHSG),” International Journal of Computer and Information Technology(2279-0764), vol. 10, Oct. 2021, doi: 10.24203/ijcit.v10i5.153.
A. Bhavani, “Comparative Analysis between LSTM and GRU in Stock Price Prediction,” International Conference on Edge Computing and Applications, ICECAA 2022 - Proceedings, pp. 532–537, 2022, doi: 10.1109/ICECAA55415.2022.9936434.
B. Aprilia, M. Marzuki, and I. Taufiq, “Prediksi El Nino Southern Oscillation (ENSO) Menggunakan Jaringan Saraf Tiruan (JST)-Backpropagation,” Jurnal Fisika Unand, vol. 9, no. 4, pp. 421–427, Jan. 2021, doi: 10.25077/jfu.9.4.421-427.2020.
C. Chen, L. Xue, and W. Xing, “Research on Improved GRU-Based Stock Price Prediction Method,” Applied Sciences, vol. 13, no. 15, p. 8813, Jul. 2023, doi: 10.3390/app13158813.
A. A. Ningrum, I. Syarif, A. I. Gunawan, E. Satriyanto, and R. Muchtar, “Algoritma Deep Learning-LSTM untuk Memprediksi Umur Transformator,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 8, no. 3, pp. 539–548, Jun. 2021, doi: 10.25126/jtiik.2021834587.
H. Song and H. Choi, “Forecasting Stock Market Indices Using the Recurrent Neural Network Based Hybrid Models: CNN-LSTM, GRU-CNN, and Ensemble Models,” Applied Sciences, vol. 13, no. 7, p. 4644, Apr. 2023, doi: 10.3390/app13074644.
A. Mayer and E. K. Smith, “Unstoppable climate change? The influence of fatalistic beliefs about climate change on behavioural change and willingness to pay cross-nationally,” 2018. doi: 10.1080/14693062.2018.1532872.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Perbandingan Metode Deep Learning dengan Model LSTM dan GRU untuk Prediksi Perubahan Iklim
Pages: 868-882
Copyright (c) 2024 Amin Mustofa, Hendra Setiawan
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- 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.
- 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 (Refer to The Effect of Open Access).
