人口的過度增長、土地的開發以及化石能源的消耗在近百年來造成地球氣候的變遷。自然災害發生的頻率也因此增加，並造成許多人類的傷亡以及產業的經濟損失。為了減緩自然的衝擊與資源的消耗，各國政府機關制定了相關政策，以減緩消耗；科學家們研發全新的、乾淨的替代能源，另一方面，氣象學家們則是藉由模型的建構，來模擬並預測這些極端事件的發生，以利人們在災害來臨之前做好準備，減少損失。其中，以水資源的影響最為深遠，它是地球中最基本也是重要的循環之一，同時也是占比最重的溫室氣體，且與人類活動息息相關。我們以台灣為例，台灣雖然年降雨平均高達2,500毫米，然而人均水資源卻是低於全球平均值。這是因為台灣的崎嶇地形特色所致，再加上季風與洋流的作用，使得降水的時空間分布不均。若能預測雨量的分布，則可訂定相關的防洪或者儲水建設，以降低災害並最大化水資源的利用，故一個準確且高解析度的預測模型一直是科學家們努力研究的方向之一。現今普遍的做法是將氣象模型的模擬資料做降尺度來提升解析度以供區域性的參考。然而這些預測模型所消耗的計算資源甚鉅，且解析度有限，很難提供疆域小且地形交互作用複雜的地區有準確的預測結果。我們提出了一個以深度學習為基礎，並結合殘差連接、注意力模塊的超解析度模型，可望提升現有的氣象模型所產出之低解析度的結果之準確性和解析度。文末，我們也比較了其他氣象降尺度的方法和其他機器學習為基礎的模型，並在四種指標(平均絕對誤差、方均根誤差、皮爾森係數、結構相似性)、定量降雨預報檢測中優於其他氣象降尺度的方法。

Human activities accelerate consumption of fossil fuels and produce greenhouse gases, resulting in urgent issues today: global warming and the climate changes. These indirectly cause severe natural disasters, plenty of lives suffering and huge losses of agricultural properties.
To mitigate impacts on our lands, scientists are developing renewable, reusable, and clean energies and climatologists are trying to predict the extremes. While, governments are publicizing resources saving policies for more eco-friendly society and arousing environment awareness. One of the most influencing factors is the precipitation, bringing condensed water vapor onto lands. Water resources are the most significant but basic needs in society, not only support our livings, but also economics.
In Taiwan, although the average annual precipitation is up to 2,500 millimeter (mm), the water allocation for each person is lower than global average, due to the drastically geographical elevation changes and uneven distribution through the year. Thus, it is crucial to track and predict the rainfall to make the most uses of it and to prevent the floods.
However, climate models have limited resolution and require intensive computational power for local-scale uses. Therefore, we proposed a deep convolutional neural network with skip connections, attention blocks, and auxiliary data concatenation, in order to downscale the low-resolution precipitation data into high-resolution one. Eventually, we compare with other climate downscaling methods and show better performance in metrics of Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Pearson Correlation, structural similarity index (SSIM), and forecast indicators.

“climate modeling, programs in atmospheres, oceans and climate (poac)”. http://paocweb.mit.edu/research/climate/climate-modeling. (accessed June 26, 2023.)
“copernicus knowledge base: Era5 data documentation”. https://confluence.ecmwf.int/display/CKB/ERA5. (accessed Mar. 14, 2023).
“global climate models, geophysical fluid dynamic laboratory”. https://www.gfdl.noaa.gov/climate-models/. (accessed June 26, 2023).
“taiwan climate change projection information and adaptation knowledge platform (tccip), coordinated by national science and technology center for disaster reduction (ncdr)”. https://tccip.ncdr.nat.gov.tw/ds_03_eng.aspx. (accessed July 30, 2022).
“rasterization of daily observational precipitation data in taiwan”. https://tccip.ncdr.nat.gov.tw/km_newsletter_one.aspx, publishedon May 1, 2020. (accessed Mar. 1, 2023).
E. Bergin, W. Buytaert, C. Kwok-Pan, A. Turner, I. Chawla, and P. Mujumdar. Using satellite products to evaluate statistical downscaling with generalised linear models. In EGU General Assembly Conference Abstracts, p. 5667, 2015.
E. Bergin, W. Buytaert, C. Onof, and H. Wheater. Downscaling of rainfall in peru using generalised linear models. In World congress on water, climate and energy. Dublin, Ireland, vol. 1318, 2012.
A. J. Cannon, S. R. Sobie, and T. Q. Murdock. Bias correction of gcm precipitation by quantile mapping: how well do methods preserve changes in quantiles and extremes? Journal of Climate, 28(17):6938–6959, 2015.
J. Cheng, Q. Kuang, C. Shen, J. Liu, X. Tan, and W. Liu. Reslap: Generating high-resolution climate prediction through image super-resolution. IEEE Access, 8:39623–39634, 2020.
J. Cheng, J. Liu, Z. Xu, C. Shen, and Q. Kuang. Generating high-resolution climate prediction through generative adversarial network. Procedia Computer Science, 174:123–127, 2020.
J.-L. Chu, H. Kang, C.-Y. Tam, C.-K. Park, and C.-T. Chen. Seasonal forecast for local precipitation over northern taiwan using statistical downscaling. Journal of Geophysical Research: Atmospheres, 113(D12), 2008.
C. Daly, R. P. Neilson, and D. L. Phillips. A statistical-topographic model for mapping climatological precipitation over mountainous terrain. Journal of Applied Meteorology and Climatology, 33(2):140–158, 1994.
C. Dong, C. C. Loy, K. He, and X. Tang. Image super-resolution using deep convolutional networks. IEEE transactions on pattern analysis and machine intelligence, 38(2):295–307, 2015.
C. Dong, C. C. Loy, and X. Tang. Accelerating the super-resolution convolutional neural network. CoRR, abs/1608.00367, 2016.
C. DOSWELL, R. Davies-Jones, and D. L. Keller. On summary measures of skill in rare event forecasting based on contingency tables. Weather and forecasting, 5(4):576–585, 1990.
R. Fealy and J. Sweeney. Statistical downscaling of precipitation for a selection of sites in ireland employing a generalised linear modelling approach. International Journal of Climatology: A Journal of the Royal Meteorological Society, 27(15):2083–2094, 2007.
H. J. Fowler, S. Blenkinsop, and C. Tebaldi. Linking climate change modelling to impacts studies: recent advances in downscaling techniques for hydrological modelling. International Journal of Climatology: A Journal of the Royal Meteorological Society, 27(12):1547–1578, 2007.
C. Fu, S. Wang, Z. Xiong, W. J. Gutowski, D.-K. Lee, J. L. McGregor, Y. Sato, H. Kato, J.-W. Kim, and M.-S. Suh. Regional climate model intercomparison project for asia. Bulletin of the American Meteorological Society, 86(2):257–266, 2005.
S. Golian, C. Murphy, R. L. Wilby, T. Matthews, S. Donegan, D. F. Quinn, and S. Harrigan. Dynamical–statistical seasonal forecasts of winter and summer precipitation for the island of ireland. International Journal of Climatology, 42(11):5714–5731, 2022.
A. M. Greene, A. W. Robertson, P. Smyth, and S. Triglia. Downscaling projections of indian monsoon rainfall using a non-homogeneous hidden markov model. Quarterly Journal of the Royal Meteorological Society, 137(655):347–359, 2011.
K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. CoRR, abs/1512.03385, 2015.
B. C. Hewitson and R. G. Crane. Climate downscaling: techniques and application. Climate Research, 7(2):85–95, 1996.
A. F. Khalil, H.-H. Kwon, U. Lall, and Y. H. Kaheil. Predictive downscaling based on non-homogeneous hidden markov models. Hydrological Sciences Journal–Journal des Sciences Hydrologiques, 55(3):333–350, 2010.
J. Kim, J. K. Lee, and K. M. Lee. Deeply-recursive convolutional network for image super-resolution. CoRR, abs/1511.04491, 2015.
J. Kim, J. K. Lee, and K. M. Lee. Accurate image super-resolution using very deep convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1646–1654, 2016.
B. Kumar, K. Atey, B. B. Singh, R. Chattopadhyay, N. Acharya, M. Singh, R. S. Nanjundiah, and S. A. Rao. On the modern deep learning approaches for precipitation downscaling. Earth Science Informatics, pp. 1–14, 2023.
B. Kumar, R. Chattopadhyay, M. Singh, N. Chaudhari, K. Kodari, and A. Barve. Deep learning–based downscaling of summer monsoon rainfall data over indian region. Theoretical and Applied Climatology, 143:1145–1156, 2021.
W.-S. Lai, J.-B. Huang, N. Ahuja, and M.-H. Yang. Deep laplacian pyramid networks for fast and accurate super-resolution. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5835–5843, 2017. doi: 10.1109/CVPR.2017.618
C. Ledig, L. Theis, F. Husz ́ar, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, Z. Wang, et al. Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.4681–4690, 2017.
B. Lim, S. Son, H. Kim, S. Nah, and K. Mu Lee. Enhanced deep residual networks for single image super-resolution. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp.136–144, 2017.
Y. Liu, A. R. Ganguly, and J. Dy. Climate downscaling using ynet: A deep convolutional network with skip connections and fusion. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 3145–3153, 2020.
X.-J. Mao, C. Shen, and Y.-B. Yang. Image restoration using convolutional auto-encoders with symmetric skip connections. arXiv preprint arXiv:1606.08921, 2016.
P. McCullagh. Generalized linear models. Routledge, 2019.
L. O. Mearns, W. Gutowski, R. Jones, R. Leung, S. McGinnis, A. Nunes, and Y. Qian. A regional climate change assessment program for north america. Eos, Transactions American Geophysical Union, 90(36):311–311, 2009.
R. Mehrotra and A. Sharma. A nonparametric nonhomogeneous hidden markov model for downscaling of multisite daily rainfall occurrences. Journal of Geophysical Research: Atmospheres, 110(D16), 2005.
A. H. Murphy. The finley affair: A signal event in the history of forecast verification. Weather and forecasting, 11(1):3–20, 1996.
V. Nair and G. E. Hinton. Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th international conference on machine learning (ICML-10), pp. 807–814, 2010.
V. Nourani, S. Uzelaltinbulat, F. Sadikoglu, and N. Behfar. Artificial intelligence based ensemble modeling for multi-station prediction of precipitation. Atmosphere, 10(2):80, 2019.
A. M. Nyongesa, G. Zeng, and V. Ongoma. Non-homogeneous hidden markov model for downscaling of short rains occurrence in kenya. Theoretical and Applied Climatology, 139(3-4):1333–1347, 2020.
A. Odena, V. Dumoulin, and C. Olah. Deconvolution and checkerboard artifacts. Distill, 2016. doi: 10.23915/distill.00003 L. S. Passarella, S. Mahajan, A. Pal, and M. R. Norman. Reconstructing high resolution esm data through a novel fast super resolution convolutional neural network (fsrcnn). Geophysical Research Letters, 49(4):e2021GL097571, 2022.
D. N. Ratri, K. Whan, and M. Schmeits. Calibration of ecmwf seasonal ensemble precipitation reforecasts in java (indonesia) using bias-corrected precipitation and climate indices. Weather and Forecasting, 36(4):1375–
1386, 2021.
H. Ren, M. El-Khamy, and J. Lee. CT-SRCNN: cascade trained and trimmed deep convolutional neural networks for image super resolution. CoRR, abs/1711.04048, 2017.
M. Rummukainen. State-of-the-art with regional climate models. Wiley Interdisciplinary Reviews: Climate Change, 1(1):82–96, 2010.
S. C. M. Sharma and A. Mitra. Resdeepd: A residual super-resolution network for deep downscaling of daily precipitation over india. Environmental Data Science, 1:e19, 2022.
W. Shi, J. Caballero, F. Husz ́ar, J. Totz, A. P. Aitken, R. Bishop, D. Rueckert, and Z. Wang. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.1874–1883, 2016.
S. Sreehari, S. V. Venkatakrishnan, K. L. Bouman, J. P. Simmons, L. F. Drummy, and C. A. Bouman. Multi-resolution data fusion for super-resolution electron microscopy. CoRR, abs/1612.00874, 2016.
M. J. Themeßl, A. Gobiet, and G. Heinrich. Empirical-statistical downscaling and error correction of regional climate models and its impact on the climate change signal. Climatic Change, 112:449–468, 2012.
B. Thrasher, E. P. Maurer, C. McKellar, and P. B. Duffy. Bias correcting climate model simulated daily temperature extremes with quantile mapping. Hydrology and Earth System Sciences, 16(9):3309–3314, 2012.
van der Linden P. and J. M. (eds.). Ensembles: Climate change and its impacts: Summary of research and results from the ensembles project. 2009.
T. Vandal, E. Kodra, S. Ganguly, A. Michaelis, R. Nemani, and A. R. Ganguly. Deepsd: Generating high resolution climate change projections through single image super-resolution. In Proceedings of the 23rd acm sigkdd international conference on knowledge discovery and data mining, pp. 1663–1672, 2017.
H. Von Storch, E. Zorita, and U. Cubasch. Downscaling of global climate change estimates to regional scales: an application to iberian rainfall in wintertime. Journal of Climate, 6(6):1161–1171, 1993.
Y. Wang, L. R. Leung, J. L. McGREGOR, D.-K. Lee, W.-C. Wang, Y. Ding, and F. Kimura. Regional climate modeling: progress, challenges, and prospects. Journal of the Meteorological Society of Japan. Ser. II, 82(6):1599–1628, 2004.
Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, 13(4):600–612, 2004.
R. L. Wilby and T. Wigley. Precipitation predictors for downscaling: observed and general circulation model relationships. International Journal of Climatology: A Journal of the Royal Meteorological Society, 20(6):641–661, 2000.
R. L. Wilby, T. Wigley, D. Conway, P. Jones, B. Hewitson, J. Main, and D. Wilks. Statistical downscaling of general circulation model output: A comparison of methods. Water resources research, 34(11):2995–3008, 1998.
S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon. Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV), pp. 3–19, 2018.
Z. Xu, Y. Han, and Z. Yang. Dynamical downscaling of regional climate: A review of methods and limitations. Science China Earth Sciences, 62:365–375, 2019.
W. Yang, X. Zhang, Y. Tian, W. Wang, J.-H. Xue, and Q. Liao. Deep learning for single image super-resolution: A brief review. IEEE Transactions on Multimedia, 21(12):3106–3121, 2019. doi: 10.1109/TMM.2019.2919431
Y. Zhang, Y. Tian, Y. Kong, B. Zhong, and Y. Fu. Residual dense network for image super-resolution. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2472–2481, 2018.
W. Zucchini and P. Guttorp. A hidden markov model for space-time precipitation. Water Resources Research, 27(8):1917–1923, 1991.