r語言怎么以第二列繪制線圖

Part I of this blog series is here.

本博客系列的第一部分 在這里 。

At the UKHO we are interested in the oceans, the seabed and the coastline — not to mention everything in and on them! In our previous blog, we (the UKHO Data Science team) outlined our quest to automate mapping of the world’s coastlines.

在UKHO，我們對海洋，海床和海岸線感興趣-更不用說其中的一切了！ 在我們以前的博客中，我們(UKHO數(shù)據(jù)科學(xué)團隊)概述了我們對世界海岸線的自動化地圖繪制的追求。

From that work, a satellite-derived coastline for the British Isles was created, available for free on the ADMIRALTY Marine Data Portal. Since then we have come across use cases for this data on an almost-daily basis, and the feedback we have received can be summarised into three main themes:

通過這項工作，創(chuàng)建了不列顛群島的衛(wèi)星海岸線，可以在ADMIRALTY海洋數(shù)據(jù)門戶網(wǎng)站上免費獲得。 從那時起，我們幾乎每天都會遇到這些數(shù)據(jù)的用例，并且我們收到的反饋可以概括為三個主要主題：

• Can I get satellite-derived coastline data for my local beach/town/country?

  我可以獲取本地海灘/城鎮(zhèn)/國家的衛(wèi)星海岸線數(shù)據(jù)嗎？

• Does the data show mean sea level?

  數(shù)據(jù)顯示平均海平面嗎？

• Can you capture coastline at high tide and low tide?

  您可以在漲潮和退潮時捕獲海岸線嗎？

The answers at the time were maybe, no and maybe, which definitely wasn’t good enough! The feedback themes helped us redefine our approach to continued research and development on this project. In this article, I will describe the progress we have made as we iterate, and hopefully show how we’ve answered (or will answer) these questions.

當時的答案可能是，也許不是，這絕對不夠好！ 反饋主題幫助我們重新定義了對該項目進行持續(xù)研發(fā)的方法。 在本文中，我將描述迭代過程中所取得的進展，并希望展示我們?nèi)绾位卮?或?qū)⒒卮?這些問題。

一些背景 (Some background)

Initially we created a yearly, median pixel mosaic of Sentinel-2 satellite images and used this as a base to extract one representative coastline. This worked well, and was a useful thing, however, deriving coastline in this way has some pros and cons.

最初，我們創(chuàng)建了Sentinel-2衛(wèi)星圖像的年度中值像素馬賽克，并以此為基礎(chǔ)提取了一個有代表性的海岸線。 這很好用，并且是有用的，但是，以這種方式獲得海岸線有其優(yōu)缺點。

Satellite-derived Coastline for the British Isles. 不列顛群島的衛(wèi)星衍生海岸線。 UK Hydrographic Office ? Crown Copyright 2020. Created using Google Earth Engine.英國水文局?版權(quán)為Crown2020。使用Google Earth Engine創(chuàng)建。

• Pro. Averaged mosaics take care of a large amount of the variation intrinsic in satellite imagery — clouds, shadows, saturated pixels and so on. This makes classification a lot easier.

  專業(yè)版 平均鑲嵌圖可處理衛(wèi)星圖像中固有的大量變化-云，陰影，飽和像素等。 這使分類容易得多。

• Pro. You can create a mosaic as large as you want, removing the need to deal with the edges of images, and how to ‘bridge’ data over those edges.

  專業(yè)版 您可以創(chuàng)建所需大小的鑲嵌圖，從而無需處理圖像邊緣以及如何在這些邊緣上“橋接”數(shù)據(jù)。

• Con. The chance of assigning a vertical datum (such as mean sea level) to the data is lost in the averaging process used to create the mosaic. The median pixel is chosen in all areas, so the final image is a composite of thousands of images, all taken at different states of tide.

  騙局 。 在用于創(chuàng)建鑲嵌的平均過程中，丟失了為數(shù)據(jù)分配垂直基準(例如平均海平面)的機會。 在所有區(qū)域都選擇中值像素，因此最終圖像是數(shù)千張圖像的合成，所有圖像都是在不同的潮汐狀態(tài)下拍攝的。

• Con. There is no way of knowing what the tidal state was when any of the images were taken, either by looking at an image or it’s metadata.

  騙局 。 通過查看圖像或其元數(shù)據(jù)，無法知道拍攝任何圖像時的潮汐狀態(tài)。

To identify which areas of the mosaic are water and which are land (i.e. to perform image segmentation), we calculate the Normalised Difference Water Index’ (NDWI) and define a local threshold using Otsu’s Method.

為了確定馬賽克的哪些區(qū)域是水而哪些區(qū)域是土地(即執(zhí)行圖像分割)，我們計算了“ 標準化差分水指數(shù)”(NDWI)，并使用Otsu方法定義了局部閾值。

A Sentinel-2 image (left), image NDWI (middle) and the binary image after thresholding (right). UK Hydrographic Office ? Crown Copyright 2019. Created using Google Earth Engine. Copernicus Sentinel data 2020. Sentinel-2圖像(左)，圖像NDWI(中)和閾值后的二進制圖像(右)。 英國水文辦公室?Crown版權(quán)所有2019。使用Google Earth Engine創(chuàng)建。 哥白尼前哨數(shù)據(jù)2020。

Again, this has some pros and cons.

再次，這有一些優(yōu)點和缺點。

• Pro. Unsupervised classification is quick, easy to understand and simple to implement.

  專業(yè)版 無監(jiān)督分類是快速，易于理解和易于實現(xiàn)的。

• Pro. Works very well most of the time.

  專業(yè)版 大多數(shù)時候效果很好。

• Con. Built-up areas and (exposed) intertidal zones have NDWI values that are very close to water, resulting in misclassifications.

  騙局 。 建成區(qū)和(裸露的)潮間帶的NDWI值非常接近水，導(dǎo)致分類錯誤。

• Con. Even with Otsu’s method, it’s hard to pick a threshold in an automated way, particularly if there is an imbalanced ratio of land and water pixels.

  騙局 。 即使使用Otsu的方法，也很難以自動化方式選擇閾值，尤其是在陸地和水像素比例不平衡的情況下。

• Con. The classification method is not robust enough to deploy anywhere in the world without significant manual intervention.

  騙子 分類方法不夠強大，無法在沒有大量人工干預(yù)的情況下部署到世界任何地方。

任務(wù) (The task)

Assigning tidal information to satellite images has been successfully demonstrated by Robbi Bishop-Taylor, Stephen Sagar and colleagues at Geoscience Australia in their work modelling the intertidal zones of Australia. Satellite images can be attributed with a predicted tide height using the time, date and location of the images to query a global, gridded tidal model. Then, by deriving coastline over a long time-series of imagery the generated coastline vectors can be labelled with a predicted tidal height, resulting in a picture of the intertidal zone emerging and an estimate of the coastline’s position relative to mean sea level.

在澳大利亞的潮間帶建模中 ， Robbi Bishop-Taylor ，Stephen Sagar及其同事已經(jīng)成功地證明了將潮汐信息分配給衛(wèi)星圖像的方法。 衛(wèi)星圖像可以使用圖像的時間，日期和位置來歸因于預(yù)測的潮汐高度，以查詢?nèi)志W(wǎng)格化的潮汐模型。 然后，通過得出長時間圖像序列的海岸線，可以用預(yù)測的潮汐高度標記生成的海岸線矢量，從而生成潮間帶的圖片以及海岸線相對于平均海平面的位置的估計值。

To choose a tidal model (there are a number of options out there, including TPXO9-atlas, FES2014 and DTU10) we teamed up with Chris Jones and Colin Shepherd from the UKHO Tides Team to assess various models against our own ADMIRALTY TotalTide software. ADMIRALTY TotalTide can be used to predict tidal heights and tidal streams at the locations of over 7,000 tidal stations, distributed globally (7,433 at the time of writing). All of these tidal stations will have been visited in order to measure in situ observations of sea level, which are then subsequently analysed to derive the necessary underlying data (i.e. the harmonic constituents and/or time and height differences from a reference port) in order to compute a predicted tidal curve.

為了選擇一種潮汐模型(那里有很多選擇，包括TPXO9-atlas ， FES2014和DTU10 )，我們與UKHO潮汐團隊的Chris Jones和Colin Shepherd合作，根據(jù)我們自己的ADMIRALTY TotalTide軟件評估了各種潮汐模型。 ADMIRALTY TotalTide可用于預(yù)測全球分布的7,000多個站的潮汐高度和潮汐流(撰寫本文時為7,433)。 所有這些潮汐站都將被訪問以測量海平面的原位觀測值，然后對其進行分析以按順序?qū)С霰匾幕A(chǔ)數(shù)據(jù)(即諧波分量和/或來自參考端口的時間和高度差)。計算預(yù)測的潮汐曲線。

We could use ADMIRALTY TotalTide to provide the satellite image tide predictions, however using a gridded, global model is preferential for our purposes to obtaining estimates using in situ stations because:

我們可以使用ADMIRALTY TotalTide來提供衛(wèi)星圖像潮汐預(yù)測，但是出于我們的目的，使用網(wǎng)格全局模型對于使用原位站獲得估算值是優(yōu)先考慮的，因為：

• In-situ observed data may not be available at the specific location of the satellite images, thus the ‘next best thing’ is a tidal prediction.

  在衛(wèi)星圖像的特定位置可能無法獲得現(xiàn)場觀測到的數(shù)據(jù)，因此“下一件好事”是潮汐預(yù)測。

• There may also be a lack of ‘traditional’ tidal prediction stations available in the region, thus relying on tidal stations potentially quite distant from the required area (and therefore potentially unsuitable).

  該地區(qū)還可能缺少“傳統(tǒng)”潮汐預(yù)報站，因此依賴于可能與所需區(qū)域相距甚遠(因此可能不合適)的潮汐站。

• A tidal model (once validated and assured that the predictions are suitable) offers ‘seamless’ tidal predictions over the required region on a regularly gridded scale.
  潮汐模型(一旦驗證并確保預(yù)測是合適的)，將以規(guī)則的網(wǎng)格規(guī)模在所需區(qū)域上提供“無縫”的潮汐預(yù)測。

Assessing the tidal models against a number of metrics (these included root mean square error comparison with ADMIRALTY TotalTide, number of harmonics, ease of automation, resolution and others) concluded that FES2014 performed best in our tests. FES is available after registration on the CNES data centre website, and comes with a handy Python package.

根據(jù)許多指標(包括與ADMIRALTY TotalTide的均方根誤差比較，諧波次數(shù)，自動化程度，分辨率等)評估潮汐模型，得出的結(jié)論是FES2014在我們的測試中表現(xiàn)最佳。 在CNE S數(shù)據(jù)中心網(wǎng)站上注冊后即可使用FES，并附帶了一個方便的Python軟件包 。

Tidal predictions at Station 2940 (Eastern edge of Nova Scotia, outside Bay of Fundy) for March 2011 at 15-minute intervals.2011年3月在2940站(新斯科舍省的東部邊緣，芬迪灣外)的潮汐預(yù)報，間隔為15分鐘。

In order to maximise the chance of getting a satellite image where the tide is at all the different stages in its range, we grab all the imagery for an area from Landsat 7, Landsat 8 and Sentinel-2 satellites (available in Earth Engine), which returns a 20 year time series. Coastline is detected on each of these images using our original classifier and, following the methodology of Bishop-Taylor et. al., we derive 10 coastline contours, covering the intertidal range visible on the satellite image series, and attributed with their height relative to mean sea level.

為了最大程度地獲得潮汐處于其范圍內(nèi)不同階段的衛(wèi)星圖像的機會，我們從Landsat 7，Landsat 8和Sentinel-2衛(wèi)星(在Earth Engine中提供 )中獲取了某個區(qū)域的所有圖像，返回20年時間序列。 使用我們的原始分類器，并按照Bishop-Taylor等人的方法，在這些圖像中的每一個上都檢測到海岸線。 等 ，我們得出了10個海岸線等值線，覆蓋了衛(wèi)星圖像序列上可見的潮間帶范圍，并歸因于它們相對于平均海平面的高度。

結(jié)果 (Results)

Here are some of the results, overlaid on ADMIRALTY charts.

這是一些結(jié)果，覆蓋在ADMIRALTY圖表上。

St. Michael’s Mount, Cornwall, UK. UK Hydrographic Office ? Crown Copyright 2020. Created using Google Earth Engine. Background ? Crown Copyright and/or database rights. UK Hydrographic Office (www.GOV.uk/UKHO). 英國康沃爾郡圣邁克爾山。 英國水文局?版權(quán)為Crown2020。使用Google Earth Engine創(chuàng)建。 背景?Crown版權(quán)和/或數(shù)據(jù)庫權(quán)利。 英國水文局( www.GOV.uk/UKHO) 。 Portsmouth Harbour, UK. UK Hydrographic Office ? Crown Copyright 2020. Created using Google Earth Engine. Background ? Crown Copyright and/or database rights. UK Hydrographic Office (www.GOV.uk/UKHO). 英國樸次茅斯海港。 英國水文局?版權(quán)為Crown2020。使用Google Earth Engine創(chuàng)建。 背景?Crown版權(quán)和/或數(shù)據(jù)庫權(quán)利。 英國水文局( www.GOV.uk/UKHO)。

These data samples are available for free on the ADMIRALTY Marine Data Portal.

這些數(shù)據(jù)樣本可在ADMIRALTY海洋數(shù)據(jù)門戶網(wǎng)站上免費獲得。

To conclude, out of the two tasks identified, we have now integrated tidal information into the coastline-derivation process and can answer two of the three questions:

總而言之，在確定的兩個任務(wù)中，我們現(xiàn)在已將潮汐信息整合到海岸線推導(dǎo)過程中，可以回答三個問題中的兩個：

• Does the data show mean sea level? YES — coastlines are attributed with estimated height relative to mean sea level.

  數(shù)據(jù)顯示平均海平面嗎？ 是的-海岸線歸因于相對于平均海平面的估計高度。

• Can you classify coastline at high tide and low tide? YES — if it has been captured on satellite imagery in the past 20 years, we can classify it.

  您可以在漲潮和退潮時對海岸線進行分類嗎？ 是的-如果過去20年來已在衛(wèi)星圖像上捕獲了它，則可以對其進行分類。

• Will this work for my local beach/town/country? We are working on it now 😊

  這對我當?shù)氐暮?城鎮(zhèn)/國家有用嗎？ 我們現(xiàn)在正在努力😊

下一個是什么？ (So, what’s next?)

Up next is the creation of a geo-generalised and temporally-generalised model that performs well on coastlines all around the globe. We have been working for a few months on gathering training data and developing a deep neural network to classify images that will plug into the pipeline, replacing the original classifier.

接下來是創(chuàng)建地理通用和時間通用的模型，該模型在全球海岸線上均能良好運行。 我們已經(jīng)花了幾個月的時間來收集訓(xùn)練數(shù)據(jù)并開發(fā)一個深度神經(jīng)網(wǎng)絡(luò)，以對將插入管道中的圖像進行分類，以取代原始分類器。

Lyttelton Harbour, near Christchurch, New Zealand. UK Hydrographic Office ? Crown Copyright 2019. Created using Google Earth Engine. Copernicus Sentinel data 2020. 新西蘭基督城附近的利特爾頓海港。 英國水文辦公室?Crown版權(quán)所有2019。使用Google Earth Engine創(chuàng)建。 哥白尼前哨數(shù)據(jù)2020。

This work is part of a wider venture into detection of marine and coastal features visible on satellite imagery, such as mangrove forests, kelp and seagrass. We’ve found there are commonalities in these image segmentation tasks, such as the difficulty in creating training data for remote sensing data.

這項工作是對探測衛(wèi)星圖像上可見的海洋和沿海特征(例如紅樹林 ，海帶和海草)的更廣泛嘗試的一部分。 我們發(fā)現(xiàn)這些圖像分割任務(wù)存在一些共性，例如難以為遙感數(shù)據(jù)創(chuàng)建訓(xùn)練數(shù)據(jù)。

Part III (the classifier strikes back) coming soon!

第三部分(分類器反擊)即將推出！

翻譯自: https://medium.com/uk-hydrographic-office/mapping-the-worlds-coastlines-with-satellite-imagery-part-ii-5ee01d3034b7

r語言怎么以第二列繪制線圖

總結(jié)

以上是生活随笔為你收集整理的r语言怎么以第二列绘制线图_用卫星图像绘制世界海岸线图-第二部分的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。