麻烦覆盖谷歌地图上的kriged数据

Question

在下面的代码中，我尝试使用ggmap().将kriged meuse数据叠加到谷歌地图上代码似乎一直运行到get_map(),但是陷入了某种巨大的困境在最后print(ggmap())执行时，计算（我的8G机器上的RAM使用量跳到7G - 被警告！）。我做错了什么？

更新：我想我发现了问题=＆gt; stat_contour()似乎无法使用kriged数据（仍然不确定原因）。当我用分箱函数stat_summary_2d(),替换它时，代码现在可以正常工作。如果可能的话，我还是想展示轮廓线。有人可以帮忙吗？

由于

# transform meuse data to SpatialPointsDataFrame
suppressMessages(library(sp))
data(meuse)
coordinates(meuse) <- ~ x + y
proj4string(meuse) <- CRS("+proj=stere
                          +lat_0=52.15616055555555 +lon_0=5.38763888888889
                          +k=0.999908 +x_0=155000 +y_0=463000
                          +ellps=bessel +units=m +no_defs
                          +towgs84=565.2369,50.0087,465.658,
                          -0.406857330322398,0.350732676542563,-1.8703473836068, 4.0812")

# define sample grid for kriging
set.seed(42)
grid <-spsample(meuse, type = "regular", n = 10000)

# do kriging
suppressMessages(library(automap))
krg <- autoKrige(formula = copper ~ 1,
                 input_data = meuse,
                 new_data = grid)

# extract kriged data
krg_df <- data.frame(krg$krige_output@coords,
                     pred = krg$krige_output@data$var1.pred)
names(krg_df) <- c("x", "y", "pred")

# transform to SpatialPointsDF & assign original (meuse) projection
krg_spdf <- krg_df
coordinates(krg_spdf) <- ~ x + y 
proj4string(krg_spdf) <- proj4string(meuse)

# transform again to longlat coordinates (for overlaying on google map below)
krg_spdf <- spTransform(krg_spdf, CRS("+init=epsg:4326"))
krg_df <- data.frame(krg_spdf@coords, pred = krg_spdf@data$pred)

# get meuse map and overlay kriged data
suppressMessages(library(ggmap))
lon <- range(krg_df$x)
lat <- range(krg_df$y)
meuse_map <- get_map(location = c(lon = mean(lon), lat = mean(lat)),
                     zoom = 13)
print(ggmap(meuse_map, extent = "normal", maprange = F) +
        #### old code (does not work) ####
        #stat_contour(aes(x = x, y = y, z = pred, fill = ..level..),
        #             alpha = 0.5,
        #             color = "gray80",
        #             geom = "polygon",
        #             data = df) +
        #### replaced with stat_summary_2d() ####
        stat_summary_2d(aes(x = x, y = y, z = pred),
                        binwidth = c(0.0005,0.0005),
                        alpha = 0.5,
                        data = krg_df) +
        scale_fill_gradient(low = "yellow",
                            high = "red",
                            name = "Copper") +
        coord_cartesian(xlim = lon, ylim = lat, expand = 0) +
        theme(aspect.ratio = 1))