{"Package":"spotoroo","Title":"Spatiotemporal Clustering of Satellite Hot Spot Data","Version":"0.1.4","Authors@R":"c(person(given = \"Weihao\",\nfamily = \"Li\",\nrole = c(\"aut\", \"cre\"),\nemail = \"llreczx@gmail.com\",\ncomment = c(ORCID = \"0000-0003-4959-106X\")),\nperson(\"Di\", \"Cook\",\nemail = \"dicook@monash.edu\",\nrole = \"ctb\",\ncomment = c(ORCID = \"0000-0002-3813-7155\")),\nperson(\"Emily\", \"Dodwell\",\nemail = \"emdodwell@gmail.com\",\nrole = \"ctb\"))","Description":"An algorithm to cluster satellite hot spot data spatially and temporally.","License":"MIT + file LICENSE","URL":"https://tengmcing.github.io/spotoroo/,\nhttps://github.com/TengMCing/spotoroo/","BugReports":"https://github.com/TengMCing/spotoroo/issues","Encoding":"UTF-8","LazyData":"true","RoxygenNote":"7.2.1","Depends":"R (>= 3.3.0)","Imports":"utils, geodist (>= 0.0.4), progress (>= 1.2.2), dplyr (>=\n1.0.0), cli (>= 2.3.0), stats, patchwork, ggrepel, ggExtra (>=\n0.9), ggbeeswarm (>= 0.7.2), ggplot2 (>= 3.0.0)","Suggests":"sf (>= 0.7-3), testthat (>= 3.0.0), covr, knitr, rmarkdown,\nmarkdown","Config/testthat/edition":"3","VignetteBuilder":"knitr","NeedsCompilation":"no","Packaged":"2023-08-21 05:29:13 UTC; patrickli","Author":"Weihao Li [aut, cre] (),\nDi Cook [ctb] (),\nEmily Dodwell [ctb]","Maintainer":"Weihao Li ","Repository":"CRAN","Date/Publication":"2023-08-21 05:50:02 UTC","repoType":"cran","tarballUrl":"ftp://cran.r-project.org/pub/R/src/contrib/spotoroo_0.1.4.tar.gz","jsonAuthors":[{"name":"Weihao Li","email":"llreczx@gmail.com","maintainer":true},{"name":"Di Cook","email":"dicook@monash.edu","maintainer":false},{"name":"Emily Dodwell","email":"emdodwell@gmail.com","maintainer":false}],"readme":"\n\n\n# spotoroo\n\n\n\n[![R-CMD-check](https://github.com/TengMCing/spotoroo/workflows/R-CMD-check/badge.svg)](https://github.com/TengMCing/spotoroo/actions)\n[![Codecov test\ncoverage](https://codecov.io/gh/TengMCing/spotoroo/branch/master/graph/badge.svg)](https://app.codecov.io/gh/TengMCing/spotoroo?branch=master)\n\n\n## Overview\n\n“spotoroo” stands for spatiotemporal clustering in R of hot spot data.\nIt is an algorithm to cluster satellite hot spots, detect ignition\npoints and reconstruct fire movement.\n\n## Installation\n\nYou can install the released version of spotoroo from\n[CRAN](https://CRAN.R-project.org) with:\n\n``` r\ninstall.packages(\"spotoroo\")\n```\n\nYou can install the development version from GitHub with:\n\n``` r\n# install.packages(\"devtools\")\ndevtools::install_github(\"TengMCing/spotoroo\")\n```\n\n## Usage\n\n``` r\nlibrary(spotoroo)\n```\n\nThe below examples use the built-in dataset `hotspots`. The hot spot\ndata needs to has at least three columns: the longitude, the latitude,\nand the observed time.\n\n``` r\nstr(hotspots)\n#> 'data.frame': 1070 obs. of 3 variables:\n#> $ lon : num 147 146 143 149 142 ...\n#> $ lat : num -37.5 -37.9 -37.8 -37.4 -37.1 ...\n#> $ obsTime: POSIXct, format: \"2020-02-01 05:20:00\" \"2020-01-02 06:30:00\" ...\n```\n\nPerform spatiotemporal clustering on this dataset. You need to specify\nwhich columns correspond to the spatial variables (“lon”, “lat”), and\nwhich to observed time (“obsTime”).\n\nThere is a choice of options for the algorithm.\n\n- “activeTime” sets the time to consider that a fire can be active, and\n longer than this between hot spots will create a new cluster\n\n- “adjDist” sets the maximum intra-cluster spatial distance between\n nearest hot spots beyond which they would be considered part of a\n different cluster\n\n- “minPts” sets the minimum number of hot spots in a cluster\n\n- “minTime” sets the minimum length of time of a cluster\n\n- “ignitionCenter” sets the method to calculate the ignition points\n\n- “timeUnit” and “timeStep” set the length of time between successive\n time indexes\n\n``` r\nresult <- hotspot_cluster(hotspots,\n lon = \"lon\",\n lat = \"lat\",\n obsTime = \"obsTime\",\n activeTime = 24,\n adjDist = 3000,\n minPts = 4,\n minTime = 3,\n ignitionCenter = \"mean\",\n timeUnit = \"h\",\n timeStep = 1)\n#> \n#> ──────────────────────────────── SPOTOROO 0.1.4 ────────────────────────────────\n#> \n#> ── Calling Core Function : `hotspot_cluster()` ──\n#> \n#> ── \"1\" time index = 1 hour\n#> ✔ Transform observed time → time indexes\n#> ℹ 970 time indexes found\n#> \n#> ── activeTime = 24 time indexes | adjDist = 3000 meters\n#> ✔ Cluster\n#> ℹ 16 clusters found (including noise)\n#> \n#> ── minPts = 4 hot spots | minTime = 3 time indexes\n#> ✔ Handle noise\n#> ℹ 6 clusters left\n#> ℹ noise proportion : 0.935 %\n#> \n#> ── ignitionCenter = \"mean\"\n#> ✔ Compute ignition points for clusters\n#> ℹ average hot spots : 176.7\n#> ℹ average duration : 131.9 hours\n#> \n#> ── Time taken = 0 mins 1 sec for 1070 hot spots\n#> ℹ 0.001 secs per hot spot\n#> \n#> ────────────────────────────────────────────────────────────────────────────────\n\n\nresult\n#> ℹ spotoroo object: 6 clusters | 1070 hot spots (including noise points)\n```\n\nYou can make a summary of the clustering results.\n\n``` r\nsummary(result)\n#> \n#> ──────────────────────────────── SPOTOROO 0.1.4 ────────────────────────────────\n#> \n#> ── Calling Core Function : `summary_spotoroo()` ──\n#> \n#> CLUSTERS: ALL\n#> OBSERVATIONS: 1070\n#> FROM: 2019-12-29 13:10:00\n#> TO: 2020-02-07 22:50:00\n#> \n#> ── Clusters\n#> ℹ Number of clusters: 6\n#> \n#> Observations in cluster\n#> Min. 1st Qu. Mean 3rd Qu. Max.\n#> 111.0 131.0 176.7 233.2 256.0\n#> Duration of cluster (hours)\n#> Min. 1st Qu. Mean 3rd Qu. Max.\n#> 111.2 118.2 131.9 146.1 148.3\n#> \n#> ── Hot spots (excluding noise)\n#> ℹ Number of hot spots: 1060\n#> \n#> Distance to ignition points (m)\n#> Min. 1st Qu. Mean 3rd Qu. Max.\n#> 0.0 2840.3 5058.2 6981.6 13452.7\n#> Time from ignition (hours)\n#> Min. 1st Qu. Mean 3rd Qu. Max.\n#> 0.0 25.2 62.5 98.2 148.3\n#> \n#> ── Noise\n#> ℹ Number of noise points: 10 (0.93 %)\n#> \n#> ────────────────────────────────────────────────────────────────────────────────\n```\n\nYou can extract a subset of clusters from the results.\n\n``` r\nfire_1_and_2 <- extract_fire(result, 1:2)\nhead(fire_1_and_2, 2)\n#> lon lat obsTime timeID membership noise distToIgnition\n#> 1 149.3 -37.75999 2019-12-29 13:10:00 1 1 FALSE 1111.885\n#> 2 149.3 -37.78000 2019-12-29 13:10:00 1 1 FALSE 1111.885\n#> distToIgnitionUnit timeFromIgnition timeFromIgnitionUnit type obsInCluster\n#> 1 m 0 hours h hotspot 146\n#> 2 m 0 hours h hotspot 146\n#> clusterTimeLen clusterTimeLenUnit\n#> 1 116.1667 hours h\n#> 2 116.1667 hours h\n```\n\nPlot of the result. In this example, there is a total of 6 clusters, so\nall can be displayed.\n\n``` r\nplot(result, bg = plot_vic_map())\n```\n\n

\n\nYou can also choose a subset of clusters, and this will plot without a\nmap, so that you can see a zoomed in view of the hot spot clusters and\ntheir ignition points.\n\n``` r\nplot(result, cluster = c(1,2,3,4))\n```\n\n

\n\nTo examine the fire movements, use the option “mov”, and the movement\nwill be shown as connected lines between centroids at each time step,\nfor each cluster.\n\n``` r\nplot(result,\n type = \"mov\",\n cluster = 1:3,\n step = 6,\n bg = plot_vic_map())\n```\n\n

\n\nTo examine the time line of clusters and learn about the intensity of\nfire periods, use the option “timeline”.\n\n``` r\nplot(result, \"timeline\", \n dateLabel = \"%b %d\", \n mainBreak = \"1 week\")\n```\n\n

","jobInfo":{"package":"spotoroo","version":"0.1.4","parsingStatus":"success","parserVersion":2,"parsedAt":"2023-08-21T08:31:11+0000"}}

Description

Usage

Arguments

Format

Details