在天氣預報中應用機器學習

原文發表於 2017年7月21日 ，是由英國氣象信息部門（Met Office Informatics Lab, UK）發表的。

Authors list ：Rachel Prudden, Niall Robinson, Alberto Arribas , Charles Ewen

In the 1950s, there was a revolution in weather forecasting. Advances in technology made it possible to simulate the atmosphere using dynamical models, quickly and accurately enough to be used for operational forecasts. Dynamical models are now a central part of weather forecasting. Starting from basic physical laws, they make it possible to predict events such as storms before they have even begun to form.

二十世紀五十年代，天氣預報有了革命性的變化。技術進步使咱們可使用模式來模擬大氣運動，這種方法在預報業務中是快速而準確的。模式直到如今還是天氣預報的核心。經過基本的物理學原理，模式能夠在暴風雨造成以前便作出預測。

A crucial challenge in the coming decade will be the integration of direct physical simulations on the one hand, and data-driven approaches on the other. Such a hybrid approach holds many opportunities for weather forecasting, as well as countless other fields.

將來十年的一個關鍵挑戰將是直接物理模擬與數據驅動方式融合應用。這種混合方式爲天氣預報以及無數其餘領域帶來許多機會（可能性）。

From model to outcomes 從模式到結果

• Localisation and super-resolution (downscaling) 局地和超高分辨率（降尺度）
• Links to the real world 與其餘領域結合

Operational weather models are usually run at a resolution of between 1km and 10km, that is, everything within the same square kilometer is represented by a single grid cell. This resolution is fine enough to capture a wide range of phenomena, but will obviously be unable to capture very localised details.

目前業務運行的天氣模式的空間分辨率在1千米和10千米之間，這意味着在這個分辨率網格內只有一個值。這個分辨率對於一個大尺度的天氣現象是夠用的，可是對於一些局地性的天氣倒是不夠的。

It may be possible to perform this kind of localisation using models trained on historical data, providing a mapping between the large-scale predictions of the simulation and the small-scale effects. This is an area of active research which could make forecasts more useful for day-to-day activities.

能夠嘗試使用歷史數據訓練的模型（機器學習的方法）來預測局地效應，以後創建一個大尺度模型預測與小規模效應之間的映射關係。此類研究如今很是活躍，有助於提高天氣預測對平常活動的價值。

As well as predicting weather at finer scales, similar techniques could help to link weather forecasts with their broader impacts. Many things are affected by the weather, either directly or indirectly; these include traffic, hayfever, flight delays, and hospital admissions. While some effects may not be easy to simulate, using data-driven models could help to provide advance warning of significant impacts.

除了在更細微的尺度上預測天氣，相似的技術能夠幫助將天氣預報與更普遍的領域聯繫起來。許多事情直接或間接地受到天氣的影響，包括交通、花粉過敏、飛行延誤和住院率，這些事情不容易經過模型來推理，但可使用數據驅動的模型來預測進而提供預警。

Emulation

• Faster components (emulation) 局部加速
• Hybrid models 混合模式

Once a machine learning model has been trained, it is often much faster to run than a full simulation. This is the motivation for a technique called model emulation. The idea is to build a fast statistical model which closely approximates a far more expensive simulation. Emulators are already being applied to problems such as climate sensitivity. An area of current interest is using the same tools to speed up some components of the weather model.

機器學習模型一旦被創建，一般是要比完整的數值模擬工程要快。可使用一種模式仿真（model emulation）的方法，創建一個很是接近於數值模式的統計學模型，這種方法已經應用於氣候敏感性研究。如今比較熱的領域是使用機器學習工具加速天氣模式的部分 組件。

There are some aspects of weather prediction which require a full physical simulation; this is what lets you predict unseen events with confidence. Other places this is not possible or even justified, and a statistical approximation may be the best you can do. This second case is where emulation can be useful in operational forecasting.

天氣預測中的一些場景是須要經過大氣物理模式來實現，但有些場景使用模式倒是不可能或不合理的，這些場景下使用統計學趨近是最好的選擇，模式仿真（model emulation）在預報業務中會有效果。

Beyond emulators, there is broader potential for hybrid models with both learned and simulated components. Such models would combine data-driven and physically-driven approaches. For example, it may be possible to adapt statistical components of the model to the local terrain, based on previous observations.

除了模式仿真（model emulation），創建融合機器學習與數值模擬的混合模式也是很是有潛力的。這種混合模型能夠融合數據驅動和物理驅動兩種方法。好比，在局地地形對天氣影響方面，能夠基於前期觀測的結果訓練模型，融合到數值模式中。

Descriptive learning 描述學習

• Finding features 特徵識別
• Exploring and summarising 信息彙總

An area where machine learning has made dramatic progress is feature detection. You can see examples of this in apps which not only detect your face, but add glasses and a moustache in real-time.

機器學習取得了顯着進步的一個領域是特徵檢測。一些基於機器學習的應用程序不只能夠檢測到您的臉部，還能夠實時在臉上添加眼鏡和鬍子。

There is currently a lot of interest in applying similar methods to hazard detection, especially to storm tracking. Trained experts are able to recognise storms and trace their paths from weather imagery; in principle there is no reason an algorithm could not learn to do the same.

目前有不少研究在使用相似的方法作災害監測，特別是風暴跟蹤。訓練有素的專家可以識別風暴，並從天氣圖像中追蹤路徑，理論上算法也能夠作獲得。

Another application could address the challenges posed by data volume and complexity when dealing with data from physical simulations. The fields output by such models are highly multidimensional; making sense of them is a complex task, requiring many 「screens」 of information. An algorithm which could summarise the salient features and bring them to the forecaster’s attention would help streamline this task.

預報員在使用觀測數據和數值預報結果時，須要處理大量的多維度的數據，理解這些數據是一項複雜的工做，常常須要切換多個屏幕來查閱信息。經過算法能夠自動識別這些數據中的關鍵信息，而後彙總到預報員的桌面，從而簡化這項工做。

Summary 總結

Exploring combinations of machine learning and numerical simulation is an area of great interest and promise for the Met Office. Not only does it offer an advance in scientific capability, but the challenges arising from the attempt could drive new research in the field of machine learning. This article has given an outline of a few research directions within meteorology, but a similar story holds across a range of scientific disciplines.

探索機器學習和數值模擬的組合是 Met Office 很是感興趣且抱有指望的領域。它不只促進了預報能力的進步，並且可能會推進機器學習領域的新研究。本文概述了氣象學中的一些研究方向，在其餘科學學科中，機器學習的應用的方向與本文所述相似。