删除R中的异常值/错误航迹位置

我有需要删除的位置错误的船舶航迹数据。实际数据带有时间戳，这一切都是正确的，所以这只是错误的位置。下面的轨迹数据是从数千个点精简下来的，最终我将处理数千个轨迹，其中每个轨迹都有一个唯一的标识符。所以我想我正在寻找一些我可以通过识别的轨迹循环，或者利用某种应用功能的东西

library(raster)
lon<-c(-51.78193,-51.81608,-51.84973,-51.87794,-51.90512,-51.93439,-51.97748,-51.99078,-52.01859,-52.05304,-52.09032,-52.11666,-52.14285,-52.148,-52.17649,-52.20045,-52.23174,-52.26725,-52.54347,-52.58133,-52.60582,-52.63488,-52.68516,-52.71636,-52.73323,-52.75245,-52.7841,-52.81515,-52.85468,-52.87921,-52.90336,-52.93189,-52.9668,-53.00284,-53.03107,-53.05711,-53.08144,-53.11514,-53.14655,-53.17014,-53.20378,-53.23456,-53.2592,-53.28848,-53.32375,-53.34618,-53.37059,-53.40495,-53.44164,-53.46389,-53.49467,-53.52195,-53.54907,-53.58261,-53.61221,-53.63979,-53.6711,-53.70189,-53.73083,-53.75592,-53.79139,-53.81248,-53.84491,-53.87275,-53.90827,-53.94056,-53.20628,-53.29157,-53.37664,-53.43295,-53.50926,-53.54763,-53.5308,-53.45378,-53.36347,-53.28677,-53.21579,-53.26883,-53.32472,-53.42001,-53.53779,-53.54862,-53.54463,-53.54347,-53.54112,-53.53776,-53.53544,-53.53371,-53.53253,-53.54352,-53.67201,-53.84997,-54.02544,-54.06773,-54.08187,-54.01061,-53.88699,-53.83143,-53.81131,-53.81129,-53.66085,-53.50664,-53.36597,-53.35885,-53.35733,-53.35396,-53.35365,-53.29068,-53.25288,-53.82416,-53.79995,-53.80232,-53.79829,-53.79229,-53.7916,-53.78755,-53.78941,-53.7011,-53.69994,-53.6904,-53.67371,-53.65907,-53.64894,-53.63509,-53.63701,-53.63439,-53.62771,-53.61821,-53.60222,-53.60806,-53.70518,-53.87085,-53.96563,-53.96513,-53.90161,-53.82244,-53.93002,-53.99709,-53.99348,-53.97484,-53.9677,-53.96035,-53.94005,-53.9383,-53.9297,-53.91872,-53.91387,-53.87099,-53.86221,-53.84477,-53.82911,-53.82378,-53.94748,-54.03159,-53.98624,-53.88608,-53.86299,-54.03941,-54.05013,-54.03648,-54.00837,-53.99941,-53.99059,-53.99127,-53.98312,-53.97016,-53.95708,-53.94976,-53.93531,-53.90229,-53.89552,-53.88579,-53.87435,-53.86112,-53.84461,-53.83519,-53.82621,-53.81792,-53.77803,-53.77256,-53.7618,-53.74539,-53.73061,-53.71999,-53.70535,-53.68502,-53.67025,-53.63705,-53.61305,-53.60845,-53.6012,-53.60221,-53.60939,-53.77555,-53.91931,-54.04305,-54.14216,-54.24885,-54.35944,-54.45926,-54.57114,-54.65697,-54.75472,-54.81421,-54.77102,-54.79547,-54.73668,-54.78792,-54.82384,-54.81429,-54.80961,-54.7985,-54.78972,-54.77996,-54.77269,-54.79461,-54.79427,-53.48531,-53.47651,-53.4668,-53.45837,-53.45424,-53.44696,-53.44312,-53.43799,-53.43141,-53.41028,-53.44231,-53.47333,-53.46801,-53.44096,-53.44419,-53.444,-53.44258,-53.44043,-53.43795,-53.44064,-53.48221,-53.47701,-53.46984,-53.46089,-53.45405,-53.45133,-53.46035,-53.46227,-53.46478,-53.46478,-53.4648,-53.46677,-53.46682,-53.47491,-53.47903,-53.45114,-53.48326,-53.49792,-53.45361,-53.42362,-53.39288,-53.40779,-53.47211,-53.47626,-53.47801,-53.48045,-53.48308,-53.48495,-53.45969,-53.42952,-53.42525,-53.43083,-53.4369,-53.44251,-53.44925,-53.45253,-53.47048,-53.49092,-53.49267,-51.69181,-51.69187,-51.69182,-51.69182,-51.6918,-51.69186,-51.69181,-51.69186,-51.68801,-51.59391,-51.44388,-51.36637,-51.31173,-51.16821,-51.04421,-50.9008,-50.74962,-50.59657,-50.41781,-50.29026,-50.12057,-49.96384,-49.79701,-49.63739,-49.46486,-49.30147,-49.13393,-48.96035,-48.80381,-48.61952,-48.45892)
lat<-c(-56.55267,-56.3172,-56.02908,-55.79571,-55.51683,-55.21784,-54.88933,-54.72725,-54.49151,-54.24643,-53.99626,-53.73947,-53.46504,-39.4404,-53.17445,-52.94424,-52.67243,-52.40723,-49.99949,-49.69163,-49.42935,-49.08267,-48.72683,-48.48531,-48.29534,-48.04958,-47.77321,-47.50704,-47.18987,-46.98237,-46.7177,-46.44685,-46.1688,-45.89386,-45.61032,-45.2959,-45.06144,-44.79999,-44.50892,-44.27473,-44.01957,-43.76157,-43.50397,-43.24589,-42.98375,-42.72919,-42.45255,-42.15245,-41.83462,-41.65027,-41.38326,-41.12483,-40.86827,-40.60549,-40.34339,-40.1036,-39.82512,-39.57131,-39.30234,-38.99869,-38.68091,-38.46827,-38.19384,-37.90784,-37.61987,-37.34363,-42.0334,-41.80125,-41.57331,-41.41558,-41.1913,-41.1152,-41.28024,-41.48734,-41.69731,-41.92312,-42.07949,-41.81352,-41.56565,-41.32117,-41.14789,-41.13923,-41.16341,-41.1869,-41.21315,-41.23677,-41.26419,-55.26491,-41.30147,-41.32603,-41.2977,-41.22637,-41.16645,-41.27923,-41.56475,-41.76029,-41.81287,-41.88363,-41.59704,-41.59703,-41.45421,-41.50432,-41.68923,-41.70459,-41.72872,-41.7677,-41.78814,-41.92939,-41.99335,-36.00016,-36.12187,-36.1464,-36.17408,-36.20501,-36.22095,-36.24589,-36.25432,-36.0807,-36.07502,-36.08755,-36.09947,-36.10061,-36.09171,-35.84048,-35.82509,-35.84504,-35.86965,-35.89392,-35.92707,-35.91924,-35.89015,-35.83128,-35.61168,-35.47165,-35.60996,-35.48226,-35.37217,-35.44069,-35.44331,-35.4609,-35.47691,-35.49499,-35.52224,-35.54073,-35.56731,-35.59203,-35.60203,-35.56525,-35.57104,-35.58187,-35.58772,-35.5935,-35.50794,-35.45205,-35.44089,-35.55421,-35.54669,-35.47803,-35.436,-35.45037,-35.4621,-35.46598,-35.48235,-35.44461,-35.44723,-35.46581,-35.48765,-35.50768,-35.52987,-35.55048,-35.56136,-35.56208,-35.56595,-35.57435,-35.58368,-35.58682,-35.59239,-35.62389,-35.70309,76.1311,-35.74169,-35.77592,-35.80891,-35.83576,-35.86417,-35.89993,-35.93433,-36.01445,-36.08262,-36.13651,-36.18798,-36.25093,-36.30776,-36.30312,-36.30463,-36.19625,-35.96459,-35.74429,-35.48469,-35.252,-35.02239,-34.82073,-34.5941,-34.528,-34.63688,-34.46486,-34.64301,-34.57707,-34.4996,-34.54093,-34.55711,-34.58755,-34.60825,-34.63708,-34.66088,-34.4544,-34.47375,-36.48943,-36.51373,-36.53941,-36.5648,-36.58192,-36.61139,-36.62759,-36.64671,-36.66894,-36.69743,-36.61913,-36.46643,-36.29231,-36.32571,-36.33936,-36.36867,-36.39741,-36.42591,-36.44596,-36.4531,-36.50245,-36.51723,-36.54053,-36.56305,-36.58464,-36.45531,-36.27352,-36.29299,-36.32136,-36.32136,-36.34504,-36.37435,-36.40137,-36.4557,-36.42461,-36.53902,-36.3658,-36.2912,-36.32765,-36.40103,-36.47648,-36.44464,-36.28135,75.56117,-36.29889,-36.3248,-36.34978,-36.36482,-36.53892,-36.68122,-36.6772,-36.65253,-36.63074,-36.60533,-36.58368,-36.5814,-36.43587,-36.25542,-36.26169,-57.82277,-57.82283,-57.82282,-57.82279,-57.8228,-57.82276,-57.82277,-57.82277,-57.82783,-57.68789,-57.62636,-1.67,-57.55762,-57.45478,-57.36555,-57.26608,-57.16677,-57.07131,-56.97163,-56.89879,-56.80383,-56.71541,-56.62544,-56.54953,-56.477,-56.40733,-56.33073,-56.25659,-56.20153,-56.15121,-56.09129)
tm<-c("12/05/2018 01:08","12/05/2018 02:01","12/05/2018 03:05","12/05/2018 04:00","12/05/2018 05:03","12/05/2018 06:10","12/05/2018 07:27","12/05/2018 08:05","12/05/2018 09:02",
      "12/05/2018 10:02","12/05/2018 11:00","12/05/2018 12:00","12/05/2018 13:02","12/05/2018 13:12","12/05/2018 14:07","12/05/2018 15:00","12/05/2018 16:01","12/05/2018 17:00",
      "13/05/2018 02:01","13/05/2018 03:07","13/05/2018 04:01","13/05/2018 05:14","13/05/2018 06:32","13/05/2018 07:25","13/05/2018 08:06","13/05/2018 09:00","13/05/2018 10:01",
      "13/05/2018 11:00","13/05/2018 12:12","13/05/2018 13:00","13/05/2018 14:00","13/05/2018 15:00","13/05/2018 16:01","13/05/2018 17:00","13/05/2018 18:00","13/05/2018 19:08",
      "13/05/2018 20:01","13/05/2018 21:00","13/05/2018 22:06","13/05/2018 23:00","14/05/2018 00:00","14/05/2018 01:00","14/05/2018 02:00","14/05/2018 03:00","14/05/2018 04:01",
      "14/05/2018 05:00","14/05/2018 06:03","14/05/2018 07:10","14/05/2018 08:19","14/05/2018 09:00","14/05/2018 10:00","14/05/2018 11:00","14/05/2018 12:00","14/05/2018 13:04",
      "14/05/2018 14:04","14/05/2018 15:00","14/05/2018 16:03","14/05/2018 17:00","14/05/2018 18:00","14/05/2018 19:05","14/05/2018 20:14","14/05/2018 21:00","14/05/2018 22:00",
      "14/05/2018 23:00","15/05/2018 00:00","15/05/2018 01:00","27/06/2018 15:00","27/06/2018 16:09","27/06/2018 17:16","27/06/2018 18:00","27/06/2018 19:03","27/06/2018 20:09",
      "27/06/2018 21:00","27/06/2018 22:00","27/06/2018 23:00","28/06/2018 00:05","28/06/2018 01:00","28/06/2018 02:03","28/06/2018 03:00","28/06/2018 04:04","28/06/2018 05:00",
      "28/06/2018 06:05","28/06/2018 07:08","28/06/2018 08:04","28/06/2018 09:02","28/06/2018 10:00","28/06/2018 11:00","28/06/2018 11:36","28/06/2018 12:05","28/06/2018 13:07",
      "28/06/2018 14:00","28/06/2018 15:10","28/06/2018 16:18","28/06/2018 17:00","28/06/2018 18:07","28/06/2018 19:18","28/06/2018 20:06","28/06/2018 21:00","28/06/2018 22:00",
      "28/06/2018 22:00","28/06/2018 23:02","29/06/2018 00:00","29/06/2018 01:03","29/06/2018 02:00","29/06/2018 03:00","29/06/2018 04:16","29/06/2018 05:04","29/06/2018 06:00",
      "29/06/2018 07:07","20/07/2018 02:00","20/07/2018 03:02","20/07/2018 04:08","20/07/2018 05:08","20/07/2018 06:22","20/07/2018 07:00","20/07/2018 08:05","20/07/2018 09:00",
      "20/07/2018 10:01","20/07/2018 11:04","20/07/2018 12:00","20/07/2018 13:00","20/07/2018 14:00","20/07/2018 15:00","20/07/2018 16:00","20/07/2018 17:03","20/07/2018 18:07",
      "20/07/2018 19:00","20/07/2018 20:01","20/07/2018 21:00","20/07/2018 22:04","20/07/2018 23:02","21/07/2018 00:01","21/07/2018 01:00","21/07/2018 02:04","21/07/2018 03:07",
      "21/07/2018 04:24","21/07/2018 05:23","21/07/2018 06:12","21/07/2018 07:00","21/07/2018 08:19","21/07/2018 09:00","21/07/2018 10:01","21/07/2018 11:00","21/07/2018 12:00",
      "21/07/2018 13:00","21/07/2018 14:00","21/07/2018 15:00","21/07/2018 16:02","21/07/2018 17:00","21/07/2018 18:14","21/07/2018 19:07","21/07/2018 20:00","21/07/2018 21:05",
      "21/07/2018 22:07","21/07/2018 23:00","22/07/2018 00:00","22/07/2018 01:00","22/07/2018 02:08","22/07/2018 03:00","22/07/2018 04:01","22/07/2018 05:39","22/07/2018 06:14",
      "22/07/2018 07:21","22/07/2018 08:01","22/07/2018 09:00","22/07/2018 10:00","22/07/2018 11:00","22/07/2018 12:00","22/07/2018 13:00","22/07/2018 14:00","22/07/2018 15:04",
      "22/07/2018 16:00","22/07/2018 17:00","22/07/2018 18:00","22/07/2018 19:12","22/07/2018 20:08","22/07/2018 21:02","22/07/2018 22:01","22/07/2018 23:19","22/07/2018 23:36",
      "23/07/2018 00:08","23/07/2018 01:00","23/07/2018 02:04","23/07/2018 03:00","23/07/2018 04:10","23/07/2018 05:16","23/07/2018 06:00","23/07/2018 07:02","23/07/2018 08:08",
      "23/07/2018 09:07","23/07/2018 10:01","23/07/2018 11:00","23/07/2018 12:00","23/07/2018 13:04","23/07/2018 14:00","23/07/2018 15:00","23/07/2018 16:00","23/07/2018 17:00",
      "23/07/2018 18:05","23/07/2018 19:05","23/07/2018 20:07","23/07/2018 21:00","23/07/2018 22:00","23/07/2018 23:00","24/07/2018 00:00","24/07/2018 01:00","24/07/2018 02:02",
      "24/07/2018 03:01","24/07/2018 04:00","24/07/2018 05:28","24/07/2018 06:02","24/07/2018 07:11","24/07/2018 08:00","24/07/2018 09:01","24/07/2018 10:00","24/07/2018 11:00",
      "24/07/2018 12:00","04/08/2018 11:01","04/08/2018 12:00","04/08/2018 13:11","04/08/2018 14:15","04/08/2018 15:02","04/08/2018 16:16","04/08/2018 17:01","04/08/2018 18:00",
      "04/08/2018 19:13","04/08/2018 20:28","04/08/2018 21:05","04/08/2018 22:04","04/08/2018 23:00","05/08/2018 00:08","05/08/2018 01:01","05/08/2018 02:00","05/08/2018 03:03",
      "05/08/2018 04:10","05/08/2018 05:04","05/08/2018 06:00","05/08/2018 07:18","05/08/2018 08:00","05/08/2018 09:00","05/08/2018 10:00","05/08/2018 11:00","05/08/2018 12:00",
      "05/08/2018 13:00","05/08/2018 14:03","05/08/2018 15:07","05/08/2018 15:07","05/08/2018 16:00","05/08/2018 17:07","05/08/2018 18:15","05/08/2018 19:21","05/08/2018 20:01",
      "05/08/2018 21:09","05/08/2018 22:04","05/08/2018 23:02","06/08/2018 00:02","06/08/2018 01:00","06/08/2018 02:06","06/08/2018 03:01","06/08/2018 04:04","06/08/2018 04:27",
      "06/08/2018 05:00","06/08/2018 06:01","06/08/2018 07:02","06/08/2018 08:00","06/08/2018 09:11","06/08/2018 10:00","06/08/2018 11:00","06/08/2018 12:03","06/08/2018 13:00",
      "06/08/2018 14:06","06/08/2018 15:00","06/08/2018 16:01","06/08/2018 17:14","06/08/2018 18:30","06/08/2018 19:01","28/08/2018 04:00","28/08/2018 05:01","28/08/2018 06:18",
      "28/08/2018 07:02","28/08/2018 08:02","28/08/2018 09:10","28/08/2018 10:03","28/08/2018 11:00","28/08/2018 12:00","28/08/2018 13:00","28/08/2018 14:01","28/08/2018 14:35",
      "28/08/2018 15:00","28/08/2018 16:04","28/08/2018 17:00","28/08/2018 18:02","28/08/2018 19:05","28/08/2018 20:05","28/08/2018 21:12","28/08/2018 22:00","28/08/2018 23:02",
      "29/08/2018 00:00","29/08/2018 01:01","29/08/2018 02:00","29/08/2018 03:01","29/08/2018 04:00","29/08/2018 05:00","29/08/2018 06:03","29/08/2018 07:01","29/08/2018 08:06",
      "29/08/2018 09:06")

        trk<-data.frame(lat,lon,tm)
        coordinates(trk) = ~ lat + lon
        crs(trk)<-"+proj=longlat +datum=WGS84 +no_defs +ellps=WGS84 +towgs84=0,0,0"
        plot(trk, pch=20,cex=0.8, col="red")

库（光栅）
lon我能想到的最好办法是将每个点与其最近的邻居进行比较，并将距离相加。你必须为你的工作设定门槛

# Data from question already loaded

library(tidyverse)
library(sf)
library(nngeo)

# make trk an sf object
trk <- st_as_sf(trk)

# This returns distances$nn the index of each point's nearest neighbors
#  and distances$dist the distance of each neighbor.
#  I've used 5 nearest neighbors below, maybe another number will
#  work better. Use >1, as each point is its own nearest neighbor.
distances <- nngeo::st_nn(trk, trk, k = 5, returnDist = T)

# Add the total distance of each point's 5 nearest neighbors in column dst
trk$dst <- distances$dist %>% lapply(., FUN = sum) %>% unlist()

# The big ones stick out at the top
trk %>% arrange(desc(dst))

Simple feature collection with 307 features and 2 fields
geometry type:  POINT
dimension:      XY
bbox:           xmin: -57.82783 ymin: -54.82384 xmax: 76.1311 ymax: -48.45892
CRS:            +proj=longlat +ellps=WGS84 +towgs84=0,0,0,0,0,0,0 +no_defs
First 10 features:
                 tm        dst                    geometry
1  22/07/2018 23:36 17859348.0   POINT (76.1311 -53.77256)
2  06/08/2018 04:27 17845535.0  POINT (75.56117 -53.47626)
3  28/08/2018 14:35  8839610.8     POINT (-1.67 -51.36637)
4  28/06/2018 11:36   705017.3 POINT (-55.26491 -53.53371)
5  12/05/2018 13:12   690426.5    POINT (-39.4404 -52.148)
6  13/05/2018 02:01   211161.7 POINT (-49.99949 -52.54347)
7  29/08/2018 09:06   191774.2 POINT (-56.09129 -48.45892)
8  12/05/2018 17:00   182993.3 POINT (-52.40723 -52.26725)
9  15/05/2018 01:00   181530.1 POINT (-37.34363 -53.94056)
10 12/05/2018 01:08   179524.1 POINT (-56.55267 -51.78193)

# You'll have to decide how exactly to find them,
#  below the top 2% are plotted in red. One non-outlier is found
ggplot() + 
  geom_sf(data = trk, 
          color = 'blue') + 
  geom_sf(data = top_frac(trk, n = .02, dst),
          color = 'red') +
  theme_void() +
  theme(legend.position = 'none')
  



#问题中的数据已加载
图书馆（tidyverse）
图书馆（sf）
图书馆（nngeo）
#使trk成为sf对象
trk 1，因为每个点都是其自己的最近邻。
你追踪的距离不是按时间顺序排列的，这使得这一点更加困难。您是否没有用于订购数据的时间戳？如果你能做到这一点，那么异常值将更容易发现，因为你可以设置一个更低的阈值。嗨，我同意使用时间会更好。然而，时间戳实际上是有序的，甚至对于异常值也是正确的。这只是偶尔的错误立场。为了准备数据和识别独特的轨迹，我使用时间戳。但是当我画点的时候，有些位置是错误的。我还认为这些异常值在时间上实际上是重复的，但位置是错误的。但即使是这样，我也需要确定错误的位置。我认为在您的示例中，这些点没有按时间戳正确排序。即使在结果中可以看到的路径的“绝对正确”部分，也有一些情况下，路径上看似正确的点的顺序不正确。这些事情太多了，他们不可能是巧合。是的，有些点显然是错误的，但如果你有严格的时间顺序点，你可以计算出滚动平均方位和距离，这将使异常值更容易确定阈值。好的，我明白你的意思。这可能反映了我是如何准备样本数据的。我会在这方面做另一次尝试，更新原始帖子，并将包括时间戳。有什么方法可以共享csv文件吗？如果csv文件不太大，您可以直接复制并粘贴到问题中的代码块中。嗨-非常感谢。我对那些图书馆不熟悉，但我想我能看懂它们。然而，我需要避免的一件事是，由于我有数千条曲目要处理，所以必须对每条曲目进行干预并评估阈值。你之前提到过观察移动平均线，但如果过程中有很大的变化，这可能不起作用？如果不看到更多的情况，就很难找到好的解决方案，特别是如果你不考虑错误的话。如果时间戳正确，还可以使用速度。这对于提供的数据来说并不容易，这些数据似乎是多年来的几条轨迹。