Kerangka Pemodelan Iklim Berbasis Kecerdasan Buatan Menggunakan Fusi Data Satelit dan Pembelajaran Mendalam

Ledyana Fitriani

doi:10.31004/riggs.v4i4.4954

Authors

Ledyana Fitriani Universitas Almuslim

DOI:

https://doi.org/10.31004/riggs.v4i4.4954

Keywords:

Pemodelan Iklim, Kecerdasan Buatan, Fusi Data Satelit, Pembelajaran Mendalam, LSTM, Prediksi Cuaca

Abstract

Perubahan iklim global menuntut pengembangan sistem pemodelan yang akurat, adaptif, dan responsif untuk mendukung upaya mitigasi serta adaptasi di berbagai sektor. Penelitian ini mengembangkan sebuah kerangka pemodelan iklim berbasis kecerdasan buatan yang mengintegrasikan fusi data satelit multisumber dengan arsitektur pembelajaran mendalam. Model dirancang dengan pendekatan Long Short-Term Memory (LSTM) yang dikombinasikan dengan mekanisme attention dan Convolutional Neural Networks (CNN) untuk mengekstraksi fitur spasial. Sistem dilatih menggunakan data satelit MODIS, Sentinel-2, dan ERA5 pada periode 2018–2024, mencakup 156 titik pengamatan di wilayah Indonesia dengan resolusi temporal harian dan resolusi spasial 1 kilometer. Proses fusi data dilakukan menggunakan teknik weighted averaging berdasarkan tingkat kepercayaan sensor dan konsistensi temporal. Validasi model dilakukan menggunakan data observasi stasiun meteorologi BMKG dengan metrik Root Mean Square Error (RMSE), Mean Absolute Error (MAE), serta koefisien korelasi. Hasil penelitian menunjukkan bahwa model hybrid CNN-LSTM dengan mekanisme attention mencapai RMSE 0,87°C untuk prediksi suhu, 12,3% untuk kelembapan relatif, dan 8,9 mm untuk curah hujan pada horizon prediksi tujuh hari. Analisis ablasi mengonfirmasi bahwa fusi multisensor meningkatkan akurasi sebesar 23,4% dibandingkan pemodelan berbasis satu sumber data satelit. Kerangka kerja ini memberikan kontribusi penting bagi pengembangan sistem peringatan dini iklim dan pengambilan keputusan berbasis data pada sektor pertanian, manajemen sumber daya air, serta mitigasi bencana iklim.

Downloads

Download data is not yet available.

References

wcasting from radar images. Artificial Intelligence for the Earth Systems, 1(3), e220033. https://doi.org/10.1175/AIES-D-22-0033.1

Bahdanau, D., Cho, K., & Bengio, Y. (2015). Neural machine translation by jointly learning to align and translate. Proceedings of the International Conference on Learning Representations. https://doi.org/10.48550/arXiv.1409.0473

Bi, K., Xie, L., Zhang, H., Chen, X., Gu, X., & Tian, Q. (2023). Accurate medium-range global weather forecasting with 3D neural networks. Nature, 619(7970), 533-538. https://doi.org/10.1038/s41586-023-06185-3

Cachay, S. R., Ramesh, V., Cole, J. N. S., Barker, H., & Rolnick, D. (2024). The downscaling of climate extremes using deep learning. Nature Machine Intelligence, 6(1), 63-74. https://doi.org/10.1038/s42256-023-00776-z

Chen, K., Hakim, G. J., & Battisti, D. S. (2023). Evaluation of tropical convection in numerical weather prediction models using satellite observations. Journal of Climate, 36(8), 2567-2584. https://doi.org/10.1175/JCLI-D-22-0456.1

Das, S., Ghosal, S., & Sahany, S. (2023). Machine learning techniques for Indian summer monsoon prediction: A critical review. Climate Dynamics, 60(5-6), 1401-1417. https://doi.org/10.1007/s00382-022-06379-z

Ham, Y. G., Kim, J. H., & Luo, J. J. (2019). Deep learning for multi-year ENSO forecasts. Nature, 573(7775), 568-572. https://doi.org/10.1038/s41586-019-1559-7

Hilburn, K. A., Ebert-Uphoff, I., & Miller, S. D. (2021). Development and interpretation of a neural-network-based synthetic radar reflectivity estimator using GOES-R satellite observations. Monthly Weather Review, 149(9), 3073-3089. https://doi.org/10.1175/MWR-D-20-0346.1

Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735

Kurth, T., Treichler, S., Romero, J., Mudigonda, M., Luehr, N., Phillips, E., Mahesh, A., Matheson, M., Deslippe, J., Fatica, M., Prabhat, & Houston, M. (2023). FourCastNet: Accelerating global high-resolution weather forecasting using adaptive Fourier neural operators. Computing in Science & Engineering, 25(1), 66-76. https://doi.org/10.1109/MCSE.2023.3250086

Lam, R., Sanchez-Gonzalez, A., Willson, M., Wirnsberger, P., Fortunato, M., Alet, F., Ravuri, S., Ewalds, T., Eaton-Rosen, Z., Hu, W., Merose, A., Hoyer, S., Holland, G., Vinyals, O., Stott, J., Pritzel, A., Mohamed, S., & Battaglia, P. (2023). Learning skillful medium-range global weather forecasting. Science, 382(6677), 1416-1421. https://doi.org/10.1126/science.adi2336

Liu, D., Wang, J., Jiang, W., Wang, W., Li, Z., & Liu, X. (2024). Satellite-based precipitation estimation using deep learning: A comprehensive review. Remote Sensing of Environment, 300, 113894. https://doi.org/10.1016/j.rse.2023.113894

Liu, Y., Racah, E., Correa, J., Khosrowshahi, A., Lavers, D., Kunkel, K., Wehner, M., & Collins, W. (2022). Application of deep convolutional neural networks for detecting extreme weather in climate datasets. Nature Communications, 13(1), 1305. https://doi.org/10.1038/s41467-022-28830-7

McGovern, A., Lagerquist, R., John Gagne, D., Jergensen, G. E., Elmore, K. L., Homeyer, C. R., & Smith, T. (2019). Making the black box more transparent: Understanding variable relationships captured by deep learning using Shapley additive explanations. Bulletin of the American Meteorological Society, 100(11), 2175-2199. https://doi.org/10.1175/BAMS-D-18-0195.1

Nguyen, T., Brandstetter, J., Kapoor, A., Gupta, J. K., & Grover, A. (2023). ClimaX: A foundation model for weather and climate. Proceedings of the 40th International Conference on Machine Learning, 202, 25904-25938. https://doi.org/10.48550/arXiv.2301.10343

Pathak, J., Subramanian, S., Harrington, P., Raja, S., Chattopadhyay, A., Mardani, M., Kurth, T., Hall, D., Li, Z., Azizzadenesheli, K., Hassanzadeh, P., Kashinath, K., & Anandkumar, A. (2022). FourCastNet: A global data-driven high-resolution weather model using adaptive Fourier neural operators. Geophysical Research Letters, 49(17), e2022GL099483. https://doi.org/10.1029/2022GL099483

Price, I., Sanchez-Gonzalez, A., Alet, F., Ewalds, T., El-Kadi, A., Stott, J., Mohamed, S., Battaglia, P., Lam, R., & Willson, M. (2024). GenCast: Diffusion-based ensemble forecasting for medium-range weather. Nature, 625(7995), 522-527. https://doi.org/10.1038/s41586-023-06992-7

Rasp, S., & Thuerey, N. (2021). Data-driven medium-range weather prediction with a resnet pretrained on climate simulations: A new model for WeatherBench. Journal of Advances in Modeling Earth Systems, 13(2), e2020MS002405. https://doi.org/10.1029/2020MS002405

Ravuri, S., Lenc, K., Willson, M., Kangin, D., Lam, R., Mirowski, P., Fitzsimons, M., Athanassiadou, M., Kashem, S., Madge, S., Prudden, R., Mandhane, A., Clark, A., Brock, A., Simonyan, K., Hadsell, R., Robinson, N., Clancy, E., Arribas, A., & Mohamed, S. (2021). Skilful precipitation nowcasting using deep generative models of radar. Nature, 597(7878), 672-677. https://doi.org/10.1038/s41586-021-03854-z

Schneider, T., Lan, S., Stuart, A., & Teixeira, J. (2020). Earth system modeling 2.0: A blueprint for models that learn from observations and targeted high-resolution simulations. Nature Communications, 11(1), 3191. https://doi.org/10.1038/s41467-020-16770-9

Shi, X., Chen, Z., Wang, H., Yeung, D. Y., Wong, W. K., & Woo, W. C. (2020). Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Advances in Neural Information Processing Systems, 28, 802-810. https://doi.org/10.48550/arXiv.1506.04214

Weyn, J. A., Durran, D. R., & Caruana, R. (2020). Improving data-driven global weather prediction using deep convolutional neural networks on a cubed sphere. Journal of Advances in Modeling Earth Systems, 12(8), e2020MS002109. https://doi.org/10.1029/2020MS002109

Xu, T., Guo, Z., Xia, Y., Ferreira, V. G., Liu, S., Wang, K., Yao, Y., Zhang, X., & Zhao, C. (2023). Evaluation of twelve evapotranspiration products from machine learning, remote sensing and land surface models over conterminous United States. Hydrology and Earth System Sciences, 27(1), 155-175. https://doi.org/10.5194/hess-27-155-2023

Zhang, Y., Ye, A., You, J., & Jia, S. (2022). An attention-based Conv-LSTM network for satellite precipitation downscaling over China. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15, 4908-4919. https://doi.org/10.1109/JSTARS.2022.3177216

Zhao, Y., Wang, C., Zhang, L., Chang, Y., & Hao, Y. (2021). Converting waste cooking oil to biodiesel in China: Environmental impacts and economic feasibility. In Renewable and Sustainable Energy Reviews (Vol. 140, p. 110661). Elsevier BV. https://doi.org/10.1016/j.rser.2020.110661