特化型卷積神經網路於颱風強度估計與預報的應用

Abstract

熱帶氣旋是發生於熱帶地區的極端天氣現象，強烈的熱帶氣旋所形成的颱風每年皆帶來可觀的經濟損失。對颱風強度的精準估計是防災的重要關鍵，更甚者，能讓颱風的生成與路徑預測更為準確。過去40年來，大氣研究員主要使用Dvorak法來估計颱風強度，然而此種方法在判讀衛星資料時得仰賴有經驗的研究員的人為判斷，因而受限於人為判斷帶來的潛在誤差。 近年來，颱風強度的估計吸引了許多資料科學家投身其中，各式各樣的機器學習技法被應用於此項任務。然而，至今為止並無對應的指標性數據集供科學家們用來比較各個方法之間的利與弊。這篇論文的其中一個目標便是整合現有來自衛星的觀測資料，成立一個全新的指標性數據集供未來各領域的科學家共同研究此一重要議題。 與此同時，近年來卷積神經網路技術已經發展得相當成熟，並在圖片辨識任務中取得豐碩的成果。我們以經典的卷積神經網路結構作為基礎，結合大氣科學家的專業知識，並根據颱風強度估計的任務特性做了些許特化，建立了一套全自動的颱風強度估計模型。相較於現行使用的系統，此應用了深度學習的模型表現更加穩定、全面，且同時降低人為判斷所帶來的潛在誤差，領先於全球，乃目前為止颱風強度相關研究在人工智慧上標誌性的重大突破。 此研究結果更充分顯示了深度學習在颱風科學上進一步發展的潛力，我們可將此深度學習模型應用在颱風強度預報、颱風形成預測等議題，應用範圍將不侷限於颱風強度的估計。其中颱風生成的預測更是現今大氣科學界尚未清楚了解的重要議題，我們或能以此研究作為基礎、仰賴人工智慧來探索，協助人類找出影響颱風形成的關鍵要素。

Tropical cyclone (TC) is a type of severe weather systems that occur in tropical regions. Accurate estimation of TC intensity is crucial for disaster management. Moreover, the intensity estimation task is the key to understand and forecast the behavior of TCs better. For over 40 years, the Dvorak technique has been applied primarily for estimating TC intensity by meteorologists worldwide. However, these techniques are suffering from several issues, such as the inconsistency across various basins and the uncertainty raised by the inherent subjectivity. Recently, the task has begun to attract attention from not only meteorologists but also data scientists. Nevertheless, it is hard to stimulate joint research between both types of scholars without a benchmark dataset to work on together. In this work, we release a such a benchmark dataset, which is a new open dataset collected from satellite remote sensing, for the TC-image-to-intensity estimation task. We also propose a novel model to solve this task based on the convolutional neural network (CNN). We discover that the usual CNN, which is mature for object recognition, requires several modifications when being used for the intensity estimation task. Furthermore, we combine the domain knowledge of meteorologists, such as the rotation-invariance of TCs, into our model design to reach better performance. Experimental results on the released benchmark dataset verify that the proposed model not only outperforms the state-of-the-art operational techniques used nowadays for TC intensity estimation, but also is more stable across all situations. The results demonstrate the potential of applying data science for meteorology study.