I figure Markdown will be easier so that I can just demo what the script is doing without having to share data along with the script. But, happy to share data and the script if we need to go that route. Nothing exciting going on here, just some basic project setup.
library(stringr)
library(rgdal)## Warning: package 'rgdal' was built under R version 4.0.3## Loading required package: sp## Warning: package 'sp' was built under R version 4.0.3## rgdal: version: 1.5-23, (SVN revision 1121)
## Geospatial Data Abstraction Library extensions to R successfully loaded
## Loaded GDAL runtime: GDAL 3.2.1, released 2020/12/29
## Path to GDAL shared files: C:/Users/u0942838/Documents/R/win-library/4.0/rgdal/gdal
## GDAL binary built with GEOS: TRUE
## Loaded PROJ runtime: Rel. 7.2.1, January 1st, 2021, [PJ_VERSION: 721]
## Path to PROJ shared files: C:/Users/u0942838/Documents/R/win-library/4.0/rgdal/proj
## PROJ CDN enabled: FALSE
## Linking to sp version:1.4-5
## To mute warnings of possible GDAL/OSR exportToProj4() degradation,
## use options("rgdal_show_exportToProj4_warnings"="none") before loading rgdal.
## Overwritten PROJ_LIB was C:/Users/u0942838/Documents/R/win-library/4.0/rgdal/projlibrary(rgeos)## rgeos version: 0.5-5, (SVN revision 640)
## GEOS runtime version: 3.8.0-CAPI-1.13.1
## Linking to sp version: 1.4-2
## Polygon checking: TRUElibrary(randomForest)## randomForest 4.6-14## Type rfNews() to see new features/changes/bug fixes.library(ranger)##
## Attaching package: 'ranger'## The following object is masked from 'package:randomForest':
##
## importance# set random seed
set.seed(1234)
# define input directories
main.dir <- "S:/ursa/campbell/CNH"
gedi.dir <- paste0(main.dir, "/GEDI")
gedi.dir.scale.1 <- paste0(gedi.dir, "/Real")
gedi.dir.scale.2 <- paste0(gedi.dir, "/Real_BENM")
gedi.dir.analysis <- paste0(gedi.dir, "/Analysis")
model.dir <- paste0(main.dir, "/Modeling")
uc.dir <- paste0(model.dir, "/Uncertainty/GEDI")This first data frame (df.1) contains airborne lidar structural metrics that were used to predict biomass at the local scale. The metrics are calculated within each GEDI footprint. Footprints are identified by their shot number “shot.num” field.
# read in footprint metrics, add "als" to the start of their column names
df.1 <- read.csv(paste0(gedi.dir.analysis, "/footprint_metrics_3000cm.csv"))
df.1 <- df.1[,c(1,6:ncol(df.1))]
colnames(df.1)[3:ncol(df.1)] <- paste0("als.", colnames(df.1)[3:ncol(df.1)])
colnames(df.1) <- str_replace_all(colnames(df.1), "_", ".")
colnames(df.1)[which(colnames(df.1) == "shot_num")] <- "shot.num"
df.1$shot.num <- as.character(df.1$shot.num)
head(df.1)## shot.num n.pts als.cc als.cd als.p.0 als.p.5 als.p.10 als.p.15
## 1 23550024100152228 10137 0.1871722 0.1730295 0.04 0.6300 0.89 1.02
## 2 23550000100152228 16048 0.1749235 0.1601446 0.02 0.4200 0.83 1.01
## 3 23550000300152232 18293 0.1773321 0.1605532 0.04 0.7400 0.98 1.13
## 4 23550000500152232 20725 0.1793475 0.1627503 0.05 0.6200 0.90 1.06
## 5 23550000700152232 28946 0.2118119 0.1891108 0.02 0.5165 0.88 1.06
## 6 23550000900152232 33527 0.1867704 0.1782146 0.00 0.1500 0.26 0.54
## als.p.20 als.p.25 als.p.30 als.p.35 als.p.40 als.p.45 als.p.50 als.p.55
## 1 1.14 1.26 1.38 1.50 1.63 1.73 1.84 1.98
## 2 1.17 1.27 1.38 1.48 1.60 1.70 1.82 1.93
## 3 1.24 1.34 1.43 1.53 1.63 1.73 1.83 1.94
## 4 1.19 1.32 1.44 1.54 1.66 1.77 1.88 1.98
## 5 1.18 1.30 1.42 1.55 1.68 1.79 1.90 2.02
## 6 0.86 1.08 1.29 1.48 1.65 1.80 1.96 2.12
## als.p.60 als.p.65 als.p.70 als.p.75 als.p.80 als.p.85 als.p.90 als.p.95
## 1 2.13 2.30 2.480 2.6700 2.90 3.123 3.400 3.8900
## 2 2.05 2.20 2.340 2.5100 2.66 2.850 3.040 3.3200
## 3 2.05 2.17 2.320 2.4600 2.67 2.860 3.170 3.6000
## 4 2.11 2.24 2.370 2.5275 2.68 2.860 3.093 3.4600
## 5 2.15 2.29 2.431 2.5975 2.78 3.010 3.320 3.6935
## 6 2.30 2.46 2.630 2.8200 3.01 3.240 3.580 4.0755
## als.p.100 als.mh als.mh.ag als.skew als.skew.ag als.kurt als.kurt.ag
## 1 6.30 0.4963668 2.029718 2.150394 0.8339563 4.299392 1.0257531
## 2 4.95 0.4271099 1.885110 2.015646 0.2533658 3.041096 -0.1664849
## 3 5.06 0.4262406 1.954190 2.118246 0.5917054 3.712611 0.2830931
## 4 4.94 0.4316261 1.937083 2.007593 0.2656120 2.962176 -0.2591705
## 5 4.66 0.5199067 1.986958 1.820766 0.3213053 2.245442 -0.3265480
## 6 6.35 0.5229469 1.999184 2.101940 0.3703822 3.691192 -0.1896823
## als.vrd.0.50 als.vrd.50.100 als.vrd.100.150 als.vrd.150.200 als.vrd.200.250
## 1 0.7643287 0.02505672 0.05119858 0.05050804 0.03669725
## 2 0.7862039 0.01987787 0.04798106 0.05028664 0.03782403
## 3 0.7885530 0.01607172 0.04908982 0.05340841 0.04017930
## 4 0.7860555 0.02016888 0.04381182 0.05100121 0.04159228
## 5 0.7509155 0.02179921 0.05171699 0.05454985 0.04770953
## 6 0.7762699 0.02207176 0.03233215 0.04107138 0.03963969
## als.vrd.250.300 als.vrd.300.350 als.vrd.350.400 als.vrd.400.450
## 1 0.02910131 0.02170267 0.011936470 0.004932426
## 2 0.03227817 0.01863161 0.004548853 0.001620140
## 3 0.02525556 0.01470508 0.007434538 0.003935932
## 4 0.03001206 0.01708082 0.008540410 0.001254524
## 5 0.03340703 0.01986458 0.014129759 0.005423893
## 6 0.03561309 0.02392102 0.014734393 0.007426850
## als.vrd.450.500 als.vnrd.0.50 als.vnrd.50.100 als.vnrd.100.150
## 1 0.0012824307 1 0.03174206 0.06090834
## 2 0.0007477567 1 0.02465986 0.05617978
## 3 0.0012573115 1 0.01997418 0.05750144
## 4 0.0004825090 1 0.02501646 0.05154113
## 5 0.0004836592 1 0.02821120 0.06273047
## 6 0.0035493781 1 0.02764701 0.03892280
## als.vnrd.150.200 als.vnrd.200.250 als.vnrd.250.300 als.vnrd.300.350
## 1 0.05668106 0.03955343 0.03041237 0.02217742
## 2 0.05560532 0.04014550 0.03312444 0.01876137
## 3 0.05887670 0.04241445 0.02596819 0.01489480
## 4 0.05660276 0.04412367 0.03085624 0.01725819
## 5 0.06206029 0.05148375 0.03479544 0.02027075
## 6 0.04711397 0.04349391 0.03760630 0.02463750
## als.vnrd.350.400 als.vnrd.400.450 als.vnrd.450.500 als.mi.b1 als.mi.b1.ag
## 1 0.012050593 0.004954910 0.0012866192 815.9076 281.5628
## 2 0.004559650 0.001621352 0.0007477567 764.1609 269.9974
## 3 0.007474170 0.003941318 0.0012574490 783.8776 253.2583
## 4 0.008555271 0.001255129 0.0004825090 815.7691 257.2924
## 5 0.014213727 0.005426517 0.0004836592 722.4081 264.7367
## 6 0.014948859 0.007478600 0.0035613815 746.6205 305.7609
## als.mi.b2 als.mi.b2.ag als.mi.b3 als.mi.b3.ag als.sdi.b1 als.sdi.b1.ag
## 1 745.1183 356.3026 NA NA 332.6547 153.9817
## 2 731.8723 368.8095 296.5883 133.1921 352.7364 131.1355
## 3 755.8638 341.3530 293.2914 138.6060 366.9536 120.0238
## 4 730.2492 345.4928 298.8658 139.9717 364.8449 117.4022
## 5 717.0822 355.4244 291.3111 140.8642 366.2332 126.1922
## 6 724.2978 365.5527 264.2503 151.3917 342.3209 183.4334
## als.sdi.b2 als.sdi.b2.ag als.sdi.b3 als.sdi.b3.ag als.pi.b1.0 als.pi.b1.5
## 1 362.1247 209.2519 NA NA 16 64
## 2 342.4202 195.9871 134.6285 54.10937 16 64
## 3 356.1154 189.0052 125.2472 53.89597 16 64
## 4 346.1234 186.7357 127.3334 57.52428 16 64
## 5 363.0082 200.3636 138.3772 59.77104 16 64
## 6 351.1210 204.3031 109.8386 73.36550 16 64
## als.pi.b1.10 als.pi.b1.15 als.pi.b1.20 als.pi.b1.25 als.pi.b1.30 als.pi.b1.35
## 1 96 128 144 192 219.2 224
## 2 96 144 144 176 192.0 224
## 3 96 128 144 176 192.0 208
## 4 112 144 160 192 192.0 224
## 5 112 128 160 176 208.0 224
## 6 112 128 160 192 208.0 224
## als.pi.b1.40 als.pi.b1.45 als.pi.b1.50 als.pi.b1.55 als.pi.b1.60 als.pi.b1.65
## 1 240 256 272 288 304 320
## 2 224 256 272 272 288 304
## 3 224 240 256 272 272 288
## 4 224 240 256 272 272 288
## 5 240 240 256 272 288 304
## 6 240 256 272 288 304 320
## als.pi.b1.70 als.pi.b1.75 als.pi.b1.80 als.pi.b1.85 als.pi.b1.90 als.pi.b1.95
## 1 336 352 384 416 448 520.8
## 2 320 352 368 384 432 496.0
## 3 304 320 336 352 384 432.0
## 4 304 320 336 368 400 448.0
## 5 320 336 352 368 400 464.0
## 6 352 368 416 512 592 672.0
## als.pi.b1.100 als.pi.b2.0 als.pi.b2.5 als.pi.b2.10 als.pi.b2.15 als.pi.b2.20
## 1 1024 16 64 80.0 99.2 144
## 2 1072 16 64 96.0 144.0 160
## 3 1232 16 64 80.0 112.0 144
## 4 880 16 64 80.0 112.0 144
## 5 1008 16 64 91.2 112.0 144
## 6 1184 16 64 80.0 112.0 144
## als.pi.b2.25 als.pi.b2.30 als.pi.b2.35 als.pi.b2.40 als.pi.b2.45 als.pi.b2.50
## 1 176 208 240 272 304 352
## 2 196 240 272 304 352 384
## 3 176 224 256 288 320 336
## 4 176 224 256 288 320 352
## 5 176 208 256 288 320 368
## 6 192 224 256 304 336 368
## als.pi.b2.55 als.pi.b2.60 als.pi.b2.65 als.pi.b2.70 als.pi.b2.75 als.pi.b2.80
## 1 384 416 464 496 528 560.0
## 2 416 432 464 496 528 560.0
## 3 368 400 416 448 496 524.8
## 4 384 416 448 464 496 528.0
## 5 400 416 448 480 512 544.0
## 6 400 432 464 496 528 560.0
## als.pi.b2.85 als.pi.b2.90 als.pi.b2.95 als.pi.b2.100 als.pi.b3.0 als.pi.b3.5
## 1 592.0 624 688 1008 NA NA
## 2 576.0 608 672 928 16 48
## 3 560.0 592 640 1104 16 64
## 4 559.2 592 640 864 16 48
## 5 576.0 608 672 992 16 48
## 6 592.0 640 704 1024 16 48
## als.pi.b3.10 als.pi.b3.15 als.pi.b3.20 als.pi.b3.25 als.pi.b3.30 als.pi.b3.35
## 1 NA NA NA NA NA NA
## 2 64 64 80 96 112 112
## 3 64 80 96 96 112 112
## 4 64 64 80 96 112 112
## 5 64 64 80 96 112 112
## 6 64 64 80 96 112 112
## als.pi.b3.40 als.pi.b3.45 als.pi.b3.50 als.pi.b3.55 als.pi.b3.60 als.pi.b3.65
## 1 NA NA NA NA NA NA
## 2 112 128 128 144 144 160
## 3 128 128 144 144 144 160
## 4 128 128 144 144 160 160
## 5 128 128 144 160 160 160
## 6 128 128 144 144 160 176
## als.pi.b3.70 als.pi.b3.75 als.pi.b3.80 als.pi.b3.85 als.pi.b3.90 als.pi.b3.95
## 1 NA NA NA NA NA NA
## 2 160 160 176 192 192 224
## 3 176 176 192 192 208 224
## 4 176 176 192 192 208 240
## 5 176 192 192 208 208 240
## 6 176 192 208 224 256 288
## als.pi.b3.100
## 1 NA
## 2 336
## 3 304
## 4 368
## 5 368
## 6 400There are two main types of GEDI metrics, Level 2A (l2a) and Level 2B (l2b). These CSV files have metrics associated with each footprint contained within df.1.
# read in gedi 2a and 2b metrics csv files
df.2 <- read.csv(paste0(gedi.dir.scale.1, "/l2a_metrics_cnh_20200921.csv"))
df.3 <- read.csv(paste0(gedi.dir.scale.1, "/l2b_metrics_cnh_20200921.csv"))
# change all column names to replace underscores with periods
colnames(df.2) <- str_replace_all(colnames(df.2), "_", ".")
colnames(df.3) <- str_replace_all(colnames(df.3), "_", ".")
# add "gedi" to beginning of all gedi predictors
colnames(df.2)[10:ncol(df.2)] <- paste0("gedi.", colnames(df.2)[10:ncol(df.2)])
colnames(df.3)[12:ncol(df.3)] <- paste0("gedi.", colnames(df.3)[12:ncol(df.3)])
# change column names for df.2 and df.3 to match df.1
colnames(df.2)[which(colnames(df.2) == "shot.number")] <- "shot.num"
colnames(df.3)[which(colnames(df.3) == "shot.number")] <- "shot.num"
# change them to character
df.2$shot.num <- as.character(df.2$shot.num)
df.3$shot.num <- as.character(df.3$shot.num)
# print the first few rows of each
head(df.2)## beam shot.num degrade.flag quality.flag delta.time sensitivity
## 1 BEAM0000 23550007900152148 0 1 42987580 0.9412481
## 2 BEAM0000 23550008100152148 0 1 42987580 0.9318883
## 3 BEAM0000 23550008300152152 0 1 42987580 0.9316657
## 4 BEAM0000 23550008500152152 0 1 42987580 0.9296457
## 5 BEAM0000 23550008700152152 0 1 42987580 0.9447677
## 6 BEAM0000 23550008900152152 0 1 42987580 0.9412529
## solar.elevation lat.lowestmode lon.lowestmode gedi.elev.highestreturn
## 1 7.698283 37.80390 -110.1511 1805.347
## 2 7.698581 37.80357 -110.1506 1810.891
## 3 7.698879 37.80324 -110.1501 1816.936
## 4 7.699178 37.80290 -110.1496 1819.310
## 5 7.699476 37.80257 -110.1491 1822.997
## 6 7.699775 37.80224 -110.1487 1823.650
## gedi.elev.lowestmode gedi.rh0 gedi.rh1 gedi.rh2 gedi.rh3 gedi.rh4 gedi.rh5
## 1 1799.993 -4.04 -3.66 -3.36 -3.10 -2.92 -2.73
## 2 1805.987 -5.12 -4.67 -4.34 -4.08 -3.85 -3.66
## 3 1812.144 -4.45 -4.04 -3.74 -3.48 -3.29 -3.10
## 4 1815.079 -4.04 -3.66 -3.33 -3.10 -2.92 -2.73
## 5 1818.355 -4.19 -3.74 -3.36 -3.10 -2.92 -2.73
## 6 1819.120 -4.00 -3.59 -3.29 -3.03 -2.84 -2.69
## gedi.rh6 gedi.rh7 gedi.rh8 gedi.rh9 gedi.rh10 gedi.rh11 gedi.rh12 gedi.rh13
## 1 -2.58 -2.47 -2.32 -2.20 -2.13 -2.02 -1.94 -1.87
## 2 -3.48 -3.33 -3.18 -3.07 -2.95 -2.84 -2.73 -2.62
## 3 -2.95 -2.80 -2.69 -2.54 -2.47 -2.35 -2.24 -2.17
## 4 -2.58 -2.43 -2.32 -2.20 -2.13 -2.02 -1.94 -1.87
## 5 -2.58 -2.43 -2.32 -2.20 -2.09 -2.02 -1.90 -1.83
## 6 -2.54 -2.39 -2.28 -2.17 -2.09 -1.98 -1.90 -1.83
## gedi.rh14 gedi.rh15 gedi.rh16 gedi.rh17 gedi.rh18 gedi.rh19 gedi.rh20
## 1 -1.75 -1.68 -1.60 -1.57 -1.49 -1.42 -1.34
## 2 -2.54 -2.43 -2.35 -2.28 -2.17 -2.09 -2.02
## 3 -2.09 -1.98 -1.90 -1.83 -1.75 -1.68 -1.64
## 4 -1.79 -1.72 -1.64 -1.57 -1.49 -1.46 -1.38
## 5 -1.75 -1.68 -1.60 -1.53 -1.49 -1.42 -1.34
## 6 -1.75 -1.68 -1.60 -1.53 -1.46 -1.42 -1.34
## gedi.rh21 gedi.rh22 gedi.rh23 gedi.rh24 gedi.rh25 gedi.rh26 gedi.rh27
## 1 -1.31 -1.23 -1.19 -1.12 -1.08 -1.01 -0.97
## 2 -1.94 -1.87 -1.79 -1.75 -1.68 -1.60 -1.53
## 3 -1.57 -1.49 -1.46 -1.38 -1.31 -1.27 -1.19
## 4 -1.34 -1.27 -1.23 -1.16 -1.12 -1.08 -1.01
## 5 -1.31 -1.23 -1.19 -1.16 -1.08 -1.04 -0.97
## 6 -1.31 -1.23 -1.19 -1.12 -1.08 -1.04 -0.97
## gedi.rh28 gedi.rh29 gedi.rh30 gedi.rh31 gedi.rh32 gedi.rh33 gedi.rh34
## 1 -0.89 -0.86 -0.82 -0.74 -0.71 -0.67 -0.63
## 2 -1.46 -1.42 -1.34 -1.27 -1.23 -1.16 -1.12
## 3 -1.16 -1.12 -1.04 -1.01 -0.93 -0.89 -0.86
## 4 -0.97 -0.93 -0.89 -0.82 -0.78 -0.74 -0.71
## 5 -0.93 -0.89 -0.86 -0.78 -0.74 -0.71 -0.67
## 6 -0.93 -0.89 -0.82 -0.78 -0.74 -0.71 -0.67
## gedi.rh35 gedi.rh36 gedi.rh37 gedi.rh38 gedi.rh39 gedi.rh40 gedi.rh41
## 1 -0.56 -0.52 -0.48 -0.44 -0.37 -0.33 -0.29
## 2 -1.04 -0.97 -0.93 -0.86 -0.82 -0.74 -0.71
## 3 -0.78 -0.74 -0.71 -0.67 -0.59 -0.56 -0.52
## 4 -0.67 -0.63 -0.59 -0.52 -0.48 -0.44 -0.41
## 5 -0.63 -0.56 -0.52 -0.48 -0.44 -0.41 -0.37
## 6 -0.59 -0.56 -0.52 -0.48 -0.44 -0.41 -0.37
## gedi.rh42 gedi.rh43 gedi.rh44 gedi.rh45 gedi.rh46 gedi.rh47 gedi.rh48
## 1 -0.26 -0.18 -0.14 -0.11 -0.07 -0.03 0.00
## 2 -0.63 -0.59 -0.52 -0.48 -0.41 -0.37 -0.29
## 3 -0.48 -0.41 -0.37 -0.33 -0.29 -0.26 -0.18
## 4 -0.37 -0.33 -0.29 -0.26 -0.22 -0.18 -0.14
## 5 -0.33 -0.26 -0.22 -0.18 -0.14 -0.11 -0.07
## 6 -0.33 -0.26 -0.22 -0.18 -0.14 -0.11 -0.07
## gedi.rh49 gedi.rh50 gedi.rh51 gedi.rh52 gedi.rh53 gedi.rh54 gedi.rh55
## 1 0.07 0.11 0.14 0.18 0.22 0.29 0.33
## 2 -0.26 -0.18 -0.14 -0.11 -0.03 0.00 0.07
## 3 -0.14 -0.11 -0.07 -0.03 0.03 0.07 0.11
## 4 -0.11 -0.07 -0.03 0.00 0.03 0.07 0.11
## 5 -0.03 0.00 0.03 0.07 0.14 0.18 0.22
## 6 -0.03 0.00 0.03 0.07 0.14 0.18 0.22
## gedi.rh56 gedi.rh57 gedi.rh58 gedi.rh59 gedi.rh60 gedi.rh61 gedi.rh62
## 1 0.37 0.41 0.48 0.52 0.56 0.59 0.67
## 2 0.11 0.18 0.22 0.29 0.33 0.41 0.44
## 3 0.14 0.18 0.26 0.29 0.33 0.37 0.41
## 4 0.14 0.18 0.22 0.26 0.29 0.33 0.41
## 5 0.26 0.29 0.33 0.37 0.41 0.44 0.52
## 6 0.26 0.29 0.33 0.37 0.41 0.44 0.52
## gedi.rh63 gedi.rh64 gedi.rh65 gedi.rh66 gedi.rh67 gedi.rh68 gedi.rh69
## 1 0.71 0.74 0.82 0.86 0.89 0.97 1.01
## 2 0.52 0.56 0.63 0.67 0.74 0.78 0.86
## 3 0.48 0.52 0.56 0.59 0.67 0.71 0.74
## 4 0.44 0.48 0.52 0.56 0.59 0.63 0.67
## 5 0.56 0.59 0.63 0.67 0.74 0.78 0.82
## 6 0.56 0.59 0.63 0.67 0.74 0.78 0.82
## gedi.rh70 gedi.rh71 gedi.rh72 gedi.rh73 gedi.rh74 gedi.rh75 gedi.rh76
## 1 1.08 1.12 1.19 1.23 1.31 1.34 1.42
## 2 0.89 0.97 1.01 1.08 1.16 1.19 1.27
## 3 0.82 0.86 0.89 0.97 1.01 1.08 1.12
## 4 0.74 0.78 0.82 0.86 0.89 0.97 1.01
## 5 0.86 0.93 0.97 1.01 1.08 1.12 1.16
## 6 0.86 0.93 0.97 1.01 1.08 1.12 1.19
## gedi.rh77 gedi.rh78 gedi.rh79 gedi.rh80 gedi.rh81 gedi.rh82 gedi.rh83
## 1 1.49 1.57 1.60 1.68 1.75 1.83 1.90
## 2 1.34 1.42 1.46 1.53 1.60 1.68 1.75
## 3 1.19 1.23 1.31 1.38 1.42 1.49 1.57
## 4 1.04 1.12 1.16 1.23 1.27 1.34 1.42
## 5 1.23 1.27 1.34 1.42 1.46 1.53 1.60
## 6 1.23 1.31 1.34 1.42 1.49 1.53 1.60
## gedi.rh84 gedi.rh85 gedi.rh86 gedi.rh87 gedi.rh88 gedi.rh89 gedi.rh90
## 1 1.98 2.09 2.17 2.28 2.35 2.47 2.58
## 2 1.83 1.90 2.02 2.09 2.17 2.28 2.39
## 3 1.64 1.72 1.79 1.87 1.98 2.05 2.17
## 4 1.46 1.53 1.60 1.68 1.75 1.83 1.94
## 5 1.68 1.75 1.83 1.90 1.98 2.05 2.17
## 6 1.68 1.75 1.83 1.90 2.02 2.09 2.20
## gedi.rh91 gedi.rh92 gedi.rh93 gedi.rh94 gedi.rh95 gedi.rh96 gedi.rh97
## 1 2.73 2.84 2.99 3.18 3.36 3.55 3.81
## 2 2.50 2.62 2.73 2.88 3.07 3.25 3.48
## 3 2.28 2.39 2.54 2.69 2.88 3.07 3.33
## 4 2.02 2.13 2.24 2.39 2.54 2.69 2.92
## 5 2.28 2.39 2.50 2.65 2.80 2.99 3.21
## 6 2.32 2.43 2.54 2.69 2.84 3.03 3.21
## gedi.rh98 gedi.rh99 gedi.rh100
## 1 4.15 4.60 5.35
## 2 3.74 4.15 4.90
## 3 3.63 4.04 4.79
## 4 3.18 3.55 4.23
## 5 3.48 3.89 4.64
## 6 3.48 3.85 4.53head(df.3)## beam shot.num algorithmrun.flag l2b.quality.flag delta.time
## 1 BEAM0000 23550007900152148 1 1 42987580
## 2 BEAM0000 23550008100152148 1 1 42987580
## 3 BEAM0000 23550008300152152 1 1 42987580
## 4 BEAM0000 23550008500152152 1 1 42987580
## 5 BEAM0000 23550008700152152 1 1 42987580
## 6 BEAM0000 23550008900152152 1 1 42987580
## sensitivity solar.elevation latitude.lastbin latitude.bin0 longitude.lastbin
## 1 0.9412481 7.698283 37.80390 37.80390 -110.1511
## 2 0.9318883 7.698581 37.80357 37.80357 -110.1506
## 3 0.9316657 7.698879 37.80323 37.80324 -110.1501
## 4 0.9296457 7.699178 37.80290 37.80290 -110.1496
## 5 0.9447677 7.699476 37.80257 37.80257 -110.1492
## 6 0.9412529 7.699775 37.80224 37.80224 -110.1487
## longitude.bin0 gedi.elev.highestreturn gedi.elev.lowestmode gedi.pai
## 1 -110.1511 1805.347 1799.993 0.18924421
## 2 -110.1506 1810.891 1805.987 0.02768178
## 3 -110.1501 1816.936 1812.144 0.03807665
## 4 -110.1496 1819.310 1815.079 0.08509696
## 5 -110.1491 1822.997 1818.355 0.11969749
## 6 -110.1487 1823.650 1819.120 0.13578381
## gedi.fhd.normal gedi.omega gedi.pgap.theta gedi.cover
## 1 1.553638 1 0.9096580 0.09028049
## 2 1.082759 1 0.9862452 0.01374548
## 3 1.596079 1 0.9811291 0.01885812
## 4 1.373797 1 0.9583162 0.04165540
## 5 1.428055 1 0.9418685 0.05809183
## 6 1.352983 1 0.9343182 0.06563703In order to link ALS to GEDI metrics, I need to first merge the tables together. They’re linked based on the shared “shot.num” field. Then, some quick filtering.
# merge them together
df <- merge(df.1, df.2)
df <- merge(df, df.3)
# get rid of bad points
df <- df[df$quality.flag == 1 & df$l2b.quality.flag == 1,]
# get rid of rows with na values
df <- df[complete.cases(df),]
# print the first few rows
head(df)## shot.num beam delta.time sensitivity solar.elevation
## 1 23550000100152228 BEAM0000 42987581 0.9362459 7.722781
## 2 23550000100152712 BEAM0000 42987585 0.9221157 7.867496
## 3 23550000300152232 BEAM0000 42987581 0.9355166 7.723080
## 4 23550000300152712 BEAM0000 42987585 0.9238452 7.867795
## 5 23550000500152232 BEAM0000 42987581 0.9416424 7.723378
## 6 23550000500152712 BEAM0000 42987585 0.9169669 7.868093
## gedi.elev.highestreturn gedi.elev.lowestmode n.pts als.cc als.cd
## 1 1946.024 1941.606 16048 0.1749235 0.1601446
## 2 2439.756 2433.466 112901 0.5019777 0.4010239
## 3 1948.486 1944.405 18293 0.1773321 0.1605532
## 4 2440.234 2434.393 108949 0.5699298 0.4216744
## 5 1951.415 1947.559 20725 0.1793475 0.1627503
## 6 2441.118 2434.716 75810 0.5251198 0.4038122
## als.p.0 als.p.5 als.p.10 als.p.15 als.p.20 als.p.25 als.p.30 als.p.35
## 1 0.02 0.42 0.83 1.01 1.17 1.27 1.38 1.48
## 2 -0.15 0.32 0.99 1.21 1.40 1.58 1.75 1.92
## 3 0.04 0.74 0.98 1.13 1.24 1.34 1.43 1.53
## 4 0.01 0.82 1.11 1.28 1.45 1.61 1.77 1.93
## 5 0.05 0.62 0.90 1.06 1.19 1.32 1.44 1.54
## 6 0.00 0.94 1.18 1.37 1.55 1.72 1.90 2.07
## als.p.40 als.p.45 als.p.50 als.p.55 als.p.60 als.p.65 als.p.70 als.p.75
## 1 1.60 1.70 1.82 1.93 2.05 2.20 2.34 2.5100
## 2 2.09 2.26 2.42 2.59 2.76 2.93 3.11 3.3000
## 3 1.63 1.73 1.83 1.94 2.05 2.17 2.32 2.4600
## 4 2.10 2.24 2.40 2.54 2.69 2.85 3.01 3.1800
## 5 1.66 1.77 1.88 1.98 2.11 2.24 2.37 2.5275
## 6 2.22 2.38 2.54 2.70 2.87 3.05 3.23 3.4200
## als.p.80 als.p.85 als.p.90 als.p.95 als.p.100 als.mh als.mh.ag als.skew
## 1 2.66 2.85 3.040 3.32 4.95 0.4271099 1.885110 2.0156458
## 2 3.51 3.75 4.040 4.53 6.99 1.2257991 2.472866 0.9114223
## 3 2.67 2.86 3.170 3.60 5.06 0.4262406 1.954190 2.1182461
## 4 3.36 3.58 3.840 4.24 6.39 1.2372192 2.421213 0.7204498
## 5 2.68 2.86 3.093 3.46 4.94 0.4316261 1.937083 2.0075934
## 6 3.63 3.87 4.140 4.52 6.02 1.2309522 2.592396 0.8120000
## als.skew.ag als.kurt als.kurt.ag als.vrd.0.50 als.vrd.50.100
## 1 0.2533658 3.0410961 -0.16648489 0.7862039 0.01987787
## 2 0.3099793 -0.2585767 0.02274202 0.5333434 0.02135499
## 3 0.5917054 3.7126106 0.28309306 0.7885530 0.01607172
## 4 0.1453689 -0.7656600 -0.28571843 0.5083663 0.01928425
## 5 0.2656120 2.9621757 -0.25917047 0.7860555 0.02016888
## 6 0.1198931 -0.6917900 -0.51843651 0.5396650 0.01312492
## als.vrd.100.150 als.vrd.150.200 als.vrd.200.250 als.vrd.250.300
## 1 0.04798106 0.05028664 0.03782403 0.03227817
## 2 0.06239094 0.07122169 0.07495062 0.07227571
## 3 0.04908982 0.05340841 0.04017930 0.02525556
## 4 0.07048252 0.07920220 0.08461757 0.08226785
## 5 0.04381182 0.05100121 0.04159228 0.03001206
## 6 0.05997889 0.06856615 0.07419865 0.07107242
## als.vrd.300.350 als.vrd.350.400 als.vrd.400.450 als.vrd.450.500 als.vnrd.0.50
## 1 0.01863161 0.004548853 0.001620140 0.0007477567 1.0000000
## 2 0.06314382 0.048174950 0.027147678 0.0121433823 0.9999336
## 3 0.01470508 0.007434538 0.003935932 0.0012573115 1.0000000
## 4 0.06974823 0.046122498 0.025635848 0.0097385015 1.0000000
## 5 0.01708082 0.008540410 0.001254524 0.0004825090 1.0000000
## 6 0.06364596 0.050455085 0.034217122 0.0180978763 1.0000000
## als.vnrd.50.100 als.vnrd.100.150 als.vnrd.150.200 als.vnrd.200.250
## 1 0.02465986 0.05617978 0.05560532 0.04014550
## 2 0.03849593 0.10109941 0.10346780 0.09819325
## 3 0.01997418 0.05750144 0.05887670 0.04241445
## 4 0.03654739 0.11783752 0.11693204 0.11105356
## 5 0.02501646 0.05154113 0.05660276 0.04412367
## 6 0.02374305 0.09788178 0.10063502 0.09820696
## als.vnrd.250.300 als.vnrd.300.350 als.vnrd.350.400 als.vnrd.400.450
## 1 0.03312444 0.01876137 0.004559650 0.001621352
## 2 0.08649840 0.07025999 0.050876947 0.027871238
## 3 0.02596819 0.01489480 0.007474170 0.003941318
## 4 0.09744828 0.07631357 0.048039694 0.026007039
## 5 0.03085624 0.01725819 0.008555271 0.001255129
## 6 0.08598101 0.07149207 0.053635280 0.035097214
## als.vnrd.450.500 als.mi.b1 als.mi.b1.ag als.mi.b2 als.mi.b2.ag als.mi.b3
## 1 0.0007477567 764.1609 269.9974 731.8723 368.8095 296.5883
## 2 0.0123135233 459.4542 219.2522 453.4682 316.5222 203.1045
## 3 0.0012574490 783.8776 253.2583 755.8638 341.3530 293.2914
## 4 0.0097828593 413.7068 204.4048 402.5627 294.8912 162.6384
## 5 0.0004825090 815.7691 257.2924 730.2492 345.4928 298.8658
## 6 0.0182250501 461.5116 197.9051 437.1192 299.2065 178.7925
## als.mi.b3.ag als.sdi.b1 als.sdi.b1.ag als.sdi.b2 als.sdi.b2.ag als.sdi.b3
## 1 133.1921 352.7364 131.1355 342.4202 195.9871 134.62850
## 2 133.5203 360.1560 129.4848 317.1272 195.9312 148.35967
## 3 138.6060 366.9536 120.0238 356.1154 189.0052 125.24719
## 4 127.2127 336.8019 106.5820 284.1033 184.4893 92.36589
## 5 139.9717 364.8449 117.4022 346.1234 186.7357 127.33340
## 6 125.9178 369.2799 103.7008 306.2320 189.9243 103.40484
## als.sdi.b3.ag als.pi.b1.0 als.pi.b1.5 als.pi.b1.10 als.pi.b1.15 als.pi.b1.20
## 1 54.10937 16 64 96 144 144
## 2 66.71624 16 48 80 96 112
## 3 53.89597 16 64 96 128 144
## 4 59.12824 16 48 80 96 112
## 5 57.52428 16 64 112 144 160
## 6 59.34024 16 48 64 96 112
## als.pi.b1.25 als.pi.b1.30 als.pi.b1.35 als.pi.b1.40 als.pi.b1.45 als.pi.b1.50
## 1 176 192 224 224 256 272
## 2 144 160 176 192 208 208
## 3 176 192 208 224 240 256
## 4 128 144 160 176 192 208
## 5 192 192 224 224 240 256
## 6 128 144 160 176 192 208
## als.pi.b1.55 als.pi.b1.60 als.pi.b1.65 als.pi.b1.70 als.pi.b1.75 als.pi.b1.80
## 1 272 288 304 320 352 368
## 2 224 240 240 256 272 288
## 3 272 272 288 304 320 336
## 4 208 224 240 256 256 272
## 5 272 272 288 304 320 336
## 6 208 224 240 240 256 272
## als.pi.b1.85 als.pi.b1.90 als.pi.b1.95 als.pi.b1.100 als.pi.b2.0 als.pi.b2.5
## 1 384 432 496 1072 16 64
## 2 304 320 400 1104 16 48
## 3 352 384 432 1232 16 64
## 4 288 304 352 1120 16 48
## 5 368 400 448 880 16 64
## 6 272 288 320 960 16 48
## als.pi.b2.10 als.pi.b2.15 als.pi.b2.20 als.pi.b2.25 als.pi.b2.30 als.pi.b2.35
## 1 96 144 160 196 240 272
## 2 64 96 112 144 176 208
## 3 80 112 144 176 224 256
## 4 64 80 112 144 160 192
## 5 80 112 144 176 224 256
## 6 64 80 112 128 160 192
## als.pi.b2.40 als.pi.b2.45 als.pi.b2.50 als.pi.b2.55 als.pi.b2.60 als.pi.b2.65
## 1 304 352 384 416 432 464
## 2 240 272 304 336 368 400
## 3 288 320 336 368 400 416
## 4 224 256 272 304 336 368
## 5 288 320 352 384 416 448
## 6 208 240 272 304 336 384
## als.pi.b2.70 als.pi.b2.75 als.pi.b2.80 als.pi.b2.85 als.pi.b2.90 als.pi.b2.95
## 1 496 528 560.0 576.0 608 672
## 2 432 464 496.0 544.0 592 656
## 3 448 496 524.8 560.0 592 640
## 4 400 432 464.0 512.0 560 624
## 5 464 496 528.0 559.2 592 640
## 6 416 448 480.0 528.0 576 624
## als.pi.b2.100 als.pi.b3.0 als.pi.b3.5 als.pi.b3.10 als.pi.b3.15 als.pi.b3.20
## 1 928 16 48 64 64 80
## 2 1056 16 48 48 64 80
## 3 1104 16 64 64 80 96
## 4 1088 16 48 48 64 64
## 5 864 16 48 64 64 80
## 6 880 16 48 48 64 64
## als.pi.b3.25 als.pi.b3.30 als.pi.b3.35 als.pi.b3.40 als.pi.b3.45 als.pi.b3.50
## 1 96 112 112 112 128 128
## 2 80 96 96 112 112 128
## 3 96 112 112 128 128 144
## 4 80 96 96 112 112 128
## 5 96 112 112 128 128 144
## 6 80 96 96 112 112 128
## als.pi.b3.55 als.pi.b3.60 als.pi.b3.65 als.pi.b3.70 als.pi.b3.75 als.pi.b3.80
## 1 144 144 160 160 160 176
## 2 128 144 160 160 176 192
## 3 144 144 160 176 176 192
## 4 128 144 144 160 160 176
## 5 144 160 160 176 176 192
## 6 128 144 144 160 160 176
## als.pi.b3.85 als.pi.b3.90 als.pi.b3.95 als.pi.b3.100 degrade.flag
## 1 192 192 224 336 0
## 2 208 224 240 448 0
## 3 192 208 224 304 0
## 4 192 208 224 400 0
## 5 192 208 240 368 0
## 6 192 208 224 368 0
## quality.flag lat.lowestmode lon.lowestmode gedi.rh0 gedi.rh1 gedi.rh2
## 1 1 37.77660 -110.1106 -3.89 -3.51 -3.25
## 2 1 37.61505 -109.8719 -3.59 -3.25 -2.99
## 3 1 37.77627 -110.1101 -4.19 -3.81 -3.48
## 4 1 37.61472 -109.8715 -3.78 -3.44 -3.18
## 5 1 37.77594 -110.1096 -4.11 -3.70 -3.40
## 6 1 37.61438 -109.8710 -3.85 -3.48 -3.18
## gedi.rh3 gedi.rh4 gedi.rh5 gedi.rh6 gedi.rh7 gedi.rh8 gedi.rh9 gedi.rh10
## 1 -2.99 -2.80 -2.65 -2.50 -2.39 -2.24 -2.17 -2.05
## 2 -2.77 -2.58 -2.43 -2.28 -2.17 -2.05 -1.94 -1.83
## 3 -3.21 -3.03 -2.84 -2.65 -2.50 -2.39 -2.28 -2.17
## 4 -2.95 -2.77 -2.62 -2.47 -2.35 -2.20 -2.09 -2.02
## 5 -3.14 -2.95 -2.77 -2.62 -2.47 -2.35 -2.24 -2.13
## 6 -2.95 -2.77 -2.58 -2.43 -2.28 -2.17 -2.05 -1.94
## gedi.rh11 gedi.rh12 gedi.rh13 gedi.rh14 gedi.rh15 gedi.rh16 gedi.rh17
## 1 -1.98 -1.87 -1.79 -1.72 -1.64 -1.60 -1.53
## 2 -1.75 -1.68 -1.60 -1.53 -1.46 -1.38 -1.31
## 3 -2.05 -1.98 -1.87 -1.79 -1.72 -1.64 -1.57
## 4 -1.90 -1.83 -1.72 -1.64 -1.57 -1.49 -1.42
## 5 -2.05 -1.98 -1.87 -1.79 -1.72 -1.64 -1.60
## 6 -1.83 -1.75 -1.64 -1.57 -1.49 -1.42 -1.34
## gedi.rh18 gedi.rh19 gedi.rh20 gedi.rh21 gedi.rh22 gedi.rh23 gedi.rh24
## 1 -1.46 -1.42 -1.34 -1.31 -1.23 -1.19 -1.12
## 2 -1.23 -1.19 -1.12 -1.08 -1.01 -0.97 -0.89
## 3 -1.49 -1.46 -1.38 -1.34 -1.27 -1.23 -1.16
## 4 -1.34 -1.27 -1.19 -1.12 -1.04 -1.01 -0.93
## 5 -1.53 -1.46 -1.42 -1.34 -1.31 -1.23 -1.19
## 6 -1.27 -1.19 -1.12 -1.04 -1.01 -0.93 -0.86
## gedi.rh25 gedi.rh26 gedi.rh27 gedi.rh28 gedi.rh29 gedi.rh30 gedi.rh31
## 1 -1.08 -1.04 -0.97 -0.93 -0.89 -0.86 -0.78
## 2 -0.86 -0.78 -0.74 -0.71 -0.63 -0.59 -0.56
## 3 -1.12 -1.08 -1.01 -0.97 -0.93 -0.89 -0.82
## 4 -0.86 -0.82 -0.74 -0.67 -0.63 -0.56 -0.52
## 5 -1.16 -1.08 -1.04 -1.01 -0.97 -0.89 -0.86
## 6 -0.82 -0.74 -0.67 -0.63 -0.56 -0.52 -0.44
## gedi.rh32 gedi.rh33 gedi.rh34 gedi.rh35 gedi.rh36 gedi.rh37 gedi.rh38
## 1 -0.74 -0.71 -0.67 -0.63 -0.59 -0.56 -0.52
## 2 -0.48 -0.44 -0.41 -0.37 -0.29 -0.26 -0.22
## 3 -0.78 -0.74 -0.71 -0.67 -0.63 -0.59 -0.56
## 4 -0.44 -0.41 -0.33 -0.29 -0.22 -0.14 -0.11
## 5 -0.82 -0.78 -0.74 -0.71 -0.67 -0.59 -0.56
## 6 -0.41 -0.33 -0.29 -0.22 -0.18 -0.11 -0.07
## gedi.rh39 gedi.rh40 gedi.rh41 gedi.rh42 gedi.rh43 gedi.rh44 gedi.rh45
## 1 -0.44 -0.41 -0.37 -0.33 -0.29 -0.26 -0.22
## 2 -0.18 -0.11 -0.07 -0.03 0.00 0.07 0.11
## 3 -0.48 -0.44 -0.41 -0.37 -0.33 -0.29 -0.26
## 4 -0.03 0.00 0.07 0.11 0.18 0.22 0.29
## 5 -0.52 -0.48 -0.44 -0.41 -0.37 -0.33 -0.29
## 6 -0.03 0.03 0.07 0.14 0.18 0.26 0.29
## gedi.rh46 gedi.rh47 gedi.rh48 gedi.rh49 gedi.rh50 gedi.rh51 gedi.rh52
## 1 -0.18 -0.14 -0.11 -0.07 -0.03 0.00 0.03
## 2 0.14 0.18 0.22 0.29 0.33 0.37 0.44
## 3 -0.22 -0.18 -0.14 -0.11 -0.07 -0.03 0.00
## 4 0.33 0.41 0.44 0.52 0.59 0.63 0.71
## 5 -0.26 -0.22 -0.18 -0.14 -0.11 -0.07 -0.03
## 6 0.37 0.41 0.48 0.52 0.59 0.63 0.71
## gedi.rh53 gedi.rh54 gedi.rh55 gedi.rh56 gedi.rh57 gedi.rh58 gedi.rh59
## 1 0.07 0.11 0.14 0.18 0.22 0.26 0.29
## 2 0.48 0.52 0.56 0.63 0.67 0.74 0.78
## 3 0.03 0.07 0.11 0.14 0.18 0.22 0.26
## 4 0.74 0.82 0.89 0.93 1.01 1.08 1.12
## 5 0.00 0.03 0.07 0.11 0.14 0.18 0.22
## 6 0.78 0.82 0.89 0.93 1.01 1.08 1.12
## gedi.rh60 gedi.rh61 gedi.rh62 gedi.rh63 gedi.rh64 gedi.rh65 gedi.rh66
## 1 0.37 0.41 0.44 0.48 0.52 0.56 0.59
## 2 0.82 0.89 0.93 1.01 1.04 1.12 1.19
## 3 0.29 0.33 0.37 0.41 0.44 0.48 0.52
## 4 1.19 1.27 1.31 1.38 1.46 1.53 1.60
## 5 0.26 0.29 0.33 0.37 0.41 0.44 0.48
## 6 1.19 1.27 1.34 1.42 1.46 1.53 1.60
## gedi.rh67 gedi.rh68 gedi.rh69 gedi.rh70 gedi.rh71 gedi.rh72 gedi.rh73
## 1 0.63 0.67 0.74 0.78 0.82 0.86 0.89
## 2 1.23 1.31 1.38 1.46 1.53 1.60 1.68
## 3 0.56 0.59 0.63 0.71 0.74 0.78 0.82
## 4 1.64 1.72 1.79 1.87 1.94 2.02 2.09
## 5 0.52 0.56 0.63 0.67 0.71 0.74 0.78
## 6 1.68 1.75 1.83 1.90 1.98 2.05 2.13
## gedi.rh74 gedi.rh75 gedi.rh76 gedi.rh77 gedi.rh78 gedi.rh79 gedi.rh80
## 1 0.97 1.01 1.04 1.12 1.16 1.23 1.27
## 2 1.75 1.83 1.94 2.02 2.13 2.20 2.32
## 3 0.86 0.93 0.97 1.01 1.04 1.12 1.16
## 4 2.17 2.24 2.32 2.39 2.47 2.54 2.65
## 5 0.82 0.86 0.93 0.97 1.01 1.08 1.12
## 6 2.24 2.32 2.39 2.47 2.58 2.65 2.73
## gedi.rh81 gedi.rh82 gedi.rh83 gedi.rh84 gedi.rh85 gedi.rh86 gedi.rh87
## 1 1.34 1.38 1.46 1.53 1.60 1.68 1.75
## 2 2.43 2.54 2.65 2.80 2.92 3.03 3.18
## 3 1.23 1.27 1.34 1.38 1.46 1.53 1.60
## 4 2.73 2.80 2.88 2.99 3.07 3.18 3.25
## 5 1.16 1.23 1.27 1.34 1.42 1.46 1.53
## 6 2.84 2.92 3.03 3.10 3.21 3.33 3.44
## gedi.rh88 gedi.rh89 gedi.rh90 gedi.rh91 gedi.rh92 gedi.rh93 gedi.rh94
## 1 1.83 1.90 1.98 2.09 2.20 2.32 2.47
## 2 3.33 3.44 3.59 3.74 3.93 4.08 4.26
## 3 1.68 1.75 1.83 1.94 2.02 2.13 2.24
## 4 3.36 3.48 3.59 3.70 3.81 3.96 4.11
## 5 1.60 1.68 1.75 1.83 1.94 2.02 2.17
## 6 3.55 3.66 3.78 3.93 4.04 4.19 4.38
## gedi.rh95 gedi.rh96 gedi.rh97 gedi.rh98 gedi.rh99 gedi.rh100
## 1 2.62 2.80 3.03 3.33 3.74 4.41
## 2 4.45 4.68 4.94 5.24 5.65 6.29
## 3 2.39 2.58 2.77 3.03 3.40 4.08
## 4 4.26 4.45 4.64 4.90 5.24 5.84
## 5 2.28 2.43 2.62 2.84 3.18 3.85
## 6 4.56 4.79 5.01 5.31 5.72 6.40
## algorithmrun.flag l2b.quality.flag latitude.lastbin latitude.bin0
## 1 1 1 37.77660 37.77660
## 2 1 1 37.61505 37.61505
## 3 1 1 37.77627 37.77627
## 4 1 1 37.61471 37.61472
## 5 1 1 37.77594 37.77594
## 6 1 1 37.61438 37.61438
## longitude.lastbin longitude.bin0 gedi.pai gedi.fhd.normal gedi.omega
## 1 -110.1106 -110.1106 0.10241848 1.474927 1
## 2 -109.8719 -109.8719 0.32282248 1.650281 1
## 3 -110.1101 -110.1101 0.09158891 1.388859 1
## 4 -109.8715 -109.8715 0.43680799 1.593343 1
## 5 -110.1096 -110.1096 0.04019950 1.527447 1
## 6 -109.8710 -109.8710 0.48957416 1.634861 1
## gedi.pgap.theta gedi.cover
## 1 0.9500467 0.04991928
## 2 0.8508484 0.14904997
## 3 0.9552085 0.04476102
## 4 0.8036810 0.19618529
## 5 0.9800875 0.01989896
## 6 0.7827406 0.21711142This is kind of a weird step… I kept this in here just to maintain consistency with my original scale 2 biomass modeling procedure. It doesn’t have any major significance to this new uncertainty analysis, but I figured it would be good to be consistent. So, I kept it in.
# split into training and validation
sample.train <- sample(seq(1,nrow(df)), 0.5*nrow(df), replace = F)
df.train <- df[sample.train,]
df.valid <- df[-sample.train,]
dim(df.train)## [1] 4830 248dim(df.valid)## [1] 4831 248Let the fun begin! Now I’ll be reading in a random forest model that was used to link field data to airborne lidar data to map biomass on the local scale (within the ALS boxes). Note that the “predict.all” argument creates a matrix of n x m dimensions, where each row ([i…n]) represents the new data being predicted and each column ([j…m]) represents the predictions for each of the trees in the forest.
# read in live biomass random forest model
rf.1 <- readRDS(paste0(model.dir, "/rf_model_live_biomass_rel_no_steve.rds"))
rf.1##
## Call:
## randomForest(formula = bio.rel ~ ., data = df[c(y.col.rel, x.cols.rel)], ntree = 10000, importance = T)
## Type of random forest: regression
## Number of trees: 10000
## No. of variables tried at each split: 1
##
## Mean of squared residuals: 195.8464
## % Var explained: 74.14# predict biomass among each decision tree in the forest
biomass.all <- predict(rf.1,
newdata = list(vrd.0.50 = df.train$als.vrd.0.50,
cd = df.train$als.cd,
mi.b2 = df.train$als.mi.b2,
mh = df.train$als.mh),
predict.all = T)
dim(biomass.all)## NULLRecall that I’ve been using the “VSURF” variable selection technique to simplify and improve my random forest models throughout this analysis. Since VSURF takes such a long time to run, I’m just going to load in the full regional-scale RF model that already had the predictor variables refined. This ensures that the same predictor variables are being fed into the new random forest models.
# read in original gedi biomass rf model
rf.gd <- readRDS(paste0(model.dir, "/rf_model_landsat_vs_gedi_20210210_gd.rds"))
preds.gd <- rownames(rf.gd$importance)
x.cols.gd <- which(colnames(df.train) %in% preds.gd)
colnames(df.train)[x.cols.gd]## [1] "gedi.elev.highestreturn" "gedi.elev.lowestmode"
## [3] "gedi.rh1" "gedi.rh89"
## [5] "gedi.rh91" "gedi.rh92"
## [7] "gedi.rh93" "gedi.rh94"
## [9] "gedi.rh99" "gedi.rh100"
## [11] "gedi.fhd.normal" "gedi.pgap.theta"Up until this point, all of the data has been local scale. All within the ALS boxes. Now, in order to make predictions on the regional scale, I need to read in GEDI metrics for all of the footprints within Bears Ears National Monument. …And a bunch of little cleanup things.
# read in gedi 2a and 2b metrics csv files
df.gd.1 <- read.csv(paste0(gedi.dir.scale.2, "/l2a_metrics_cnh_20210214.csv"))
df.gd.2 <- read.csv(paste0(gedi.dir.scale.2, "/l2b_metrics_cnh_20210214.csv"))
# change all column names to replace underscores with periods
colnames(df.gd.1) <- str_replace_all(colnames(df.gd.1), "_", ".")
colnames(df.gd.2) <- str_replace_all(colnames(df.gd.2), "_", ".")
# add "gedi" to beginning of all gedi predictors
colnames(df.gd.1)[10:ncol(df.gd.1)] <- paste0("gedi.", colnames(df.gd.1)[10:ncol(df.gd.1)])
colnames(df.gd.2)[12:ncol(df.gd.2)] <- paste0("gedi.", colnames(df.gd.2)[12:ncol(df.gd.2)])
# change column names for df.2 and df.3 to match df.1
colnames(df.gd.1)[which(colnames(df.gd.1) == "shot.number")] <- "shot.num"
colnames(df.gd.2)[which(colnames(df.gd.2) == "shot.number")] <- "shot.num"
# change them to character
df.gd.1$shot.num <- as.character(df.gd.1$shot.num)
df.gd.2$shot.num <- as.character(df.gd.2$shot.num)
# merge them together
df.gd <- merge(df.gd.1, df.gd.2, by = "shot.num", suffixes = c("", ".rm"))
# get rid of bad points
df.gd <- df.gd[df.gd$quality.flag == 1 & df.gd$l2b.quality.flag == 1,]
# get rid of duplicate fields
df.gd <- df.gd[,-grep("\\.rm", colnames(df.gd))]
# print the first few rows
head(df.gd)## shot.num beam degrade.flag quality.flag delta.time sensitivity
## 1 23550000100151992 BEAM0000 0 1 42987579 0.9452723
## 3 23550000100152228 BEAM0000 0 1 42987581 0.9362459
## 4 23550000100152348 BEAM0000 0 1 42987582 0.9362535
## 5 23550000100152472 BEAM0000 0 1 42987583 0.9463900
## 6 23550000100152592 BEAM0000 0 1 42987584 0.9525461
## 7 23550000100152712 BEAM0000 0 1 42987585 0.9221157
## solar.elevation lat.lowestmode lon.lowestmode gedi.elev.highestreturn
## 1 7.650408 37.85712 -110.2303 1568.018
## 3 7.722781 37.77660 -110.1106 1946.024
## 4 7.758953 37.73627 -110.0509 2074.835
## 5 7.795084 37.69590 -109.9912 2371.058
## 6 7.831322 37.65550 -109.9315 2332.401
## 7 7.867496 37.61505 -109.8719 2439.756
## gedi.elev.lowestmode gedi.rh0 gedi.rh1 gedi.rh2 gedi.rh3 gedi.rh4 gedi.rh5
## 1 1562.889 -4.82 -4.38 -4.04 -3.74 -3.51 -3.33
## 3 1941.606 -3.89 -3.51 -3.25 -2.99 -2.80 -2.65
## 4 2070.717 -5.39 -4.97 -4.64 -4.34 -4.11 -3.89
## 5 2365.517 -3.93 -3.51 -3.21 -2.99 -2.80 -2.65
## 6 2307.728 -4.71 -4.30 -3.96 -3.70 -3.44 -3.25
## 7 2433.466 -3.59 -3.25 -2.99 -2.77 -2.58 -2.43
## gedi.rh6 gedi.rh7 gedi.rh8 gedi.rh9 gedi.rh10 gedi.rh11 gedi.rh12 gedi.rh13
## 1 -3.14 -2.99 -2.84 -2.73 -2.58 -2.47 -2.39 -2.28
## 3 -2.50 -2.39 -2.24 -2.17 -2.05 -1.98 -1.87 -1.79
## 4 -3.70 -3.55 -3.36 -3.25 -3.10 -2.99 -2.88 -2.77
## 5 -2.50 -2.35 -2.24 -2.13 -2.05 -1.94 -1.87 -1.79
## 6 -3.07 -2.88 -2.73 -2.58 -2.43 -2.32 -2.20 -2.05
## 7 -2.28 -2.17 -2.05 -1.94 -1.83 -1.75 -1.68 -1.60
## gedi.rh14 gedi.rh15 gedi.rh16 gedi.rh17 gedi.rh18 gedi.rh19 gedi.rh20
## 1 -2.17 -2.09 -2.02 -1.94 -1.87 -1.79 -1.72
## 3 -1.72 -1.64 -1.60 -1.53 -1.46 -1.42 -1.34
## 4 -2.65 -2.58 -2.47 -2.39 -2.32 -2.20 -2.13
## 5 -1.72 -1.64 -1.57 -1.49 -1.42 -1.34 -1.31
## 6 -1.94 -1.83 -1.72 -1.64 -1.53 -1.42 -1.34
## 7 -1.53 -1.46 -1.38 -1.31 -1.23 -1.19 -1.12
## gedi.rh21 gedi.rh22 gedi.rh23 gedi.rh24 gedi.rh25 gedi.rh26 gedi.rh27
## 1 -1.64 -1.57 -1.49 -1.42 -1.38 -1.31 -1.23
## 3 -1.31 -1.23 -1.19 -1.12 -1.08 -1.04 -0.97
## 4 -2.05 -1.98 -1.90 -1.83 -1.75 -1.68 -1.64
## 5 -1.23 -1.19 -1.12 -1.08 -1.01 -0.97 -0.89
## 6 -1.23 -1.16 -1.04 -0.97 -0.89 -0.78 -0.71
## 7 -1.08 -1.01 -0.97 -0.89 -0.86 -0.78 -0.74
## gedi.rh28 gedi.rh29 gedi.rh30 gedi.rh31 gedi.rh32 gedi.rh33 gedi.rh34
## 1 -1.19 -1.12 -1.04 -1.01 -0.93 -0.89 -0.82
## 3 -0.93 -0.89 -0.86 -0.78 -0.74 -0.71 -0.67
## 4 -1.57 -1.49 -1.42 -1.38 -1.31 -1.27 -1.19
## 5 -0.86 -0.82 -0.74 -0.71 -0.67 -0.63 -0.56
## 6 -0.63 -0.56 -0.48 -0.37 -0.29 -0.22 -0.14
## 7 -0.71 -0.63 -0.59 -0.56 -0.48 -0.44 -0.41
## gedi.rh35 gedi.rh36 gedi.rh37 gedi.rh38 gedi.rh39 gedi.rh40 gedi.rh41
## 1 -0.78 -0.71 -0.67 -0.59 -0.56 -0.48 -0.44
## 3 -0.63 -0.59 -0.56 -0.52 -0.44 -0.41 -0.37
## 4 -1.16 -1.08 -1.04 -0.97 -0.93 -0.86 -0.82
## 5 -0.52 -0.48 -0.44 -0.41 -0.33 -0.29 -0.26
## 6 -0.07 0.00 0.11 0.18 0.26 0.33 0.41
## 7 -0.37 -0.29 -0.26 -0.22 -0.18 -0.11 -0.07
## gedi.rh42 gedi.rh43 gedi.rh44 gedi.rh45 gedi.rh46 gedi.rh47 gedi.rh48
## 1 -0.41 -0.33 -0.29 -0.22 -0.18 -0.14 -0.07
## 3 -0.33 -0.29 -0.26 -0.22 -0.18 -0.14 -0.11
## 4 -0.74 -0.71 -0.67 -0.59 -0.56 -0.48 -0.44
## 5 -0.22 -0.18 -0.11 -0.07 -0.03 0.00 0.03
## 6 0.52 0.59 0.67 0.74 0.86 0.93 1.01
## 7 -0.03 0.00 0.07 0.11 0.14 0.18 0.22
## gedi.rh49 gedi.rh50 gedi.rh51 gedi.rh52 gedi.rh53 gedi.rh54 gedi.rh55
## 1 -0.03 0.03 0.07 0.11 0.18 0.22 0.29
## 3 -0.07 -0.03 0.00 0.03 0.07 0.11 0.14
## 4 -0.41 -0.33 -0.29 -0.26 -0.18 -0.14 -0.11
## 5 0.07 0.14 0.18 0.22 0.26 0.29 0.33
## 6 1.12 1.19 1.31 1.38 1.49 1.57 1.68
## 7 0.29 0.33 0.37 0.44 0.48 0.52 0.56
## gedi.rh56 gedi.rh57 gedi.rh58 gedi.rh59 gedi.rh60 gedi.rh61 gedi.rh62
## 1 0.33 0.37 0.44 0.48 0.56 0.59 0.67
## 3 0.18 0.22 0.26 0.29 0.37 0.41 0.44
## 4 -0.07 0.00 0.03 0.07 0.14 0.18 0.22
## 5 0.41 0.44 0.48 0.52 0.59 0.63 0.67
## 6 1.79 1.90 2.02 2.13 2.24 2.39 2.50
## 7 0.63 0.67 0.74 0.78 0.82 0.89 0.93
## gedi.rh63 gedi.rh64 gedi.rh65 gedi.rh66 gedi.rh67 gedi.rh68 gedi.rh69
## 1 0.71 0.78 0.82 0.89 0.93 1.01 1.04
## 3 0.48 0.52 0.56 0.59 0.63 0.67 0.74
## 4 0.29 0.33 0.37 0.44 0.48 0.52 0.59
## 5 0.71 0.78 0.82 0.86 0.93 0.97 1.04
## 6 2.65 2.80 2.99 3.18 3.40 3.66 3.96
## 7 1.01 1.04 1.12 1.19 1.23 1.31 1.38
## gedi.rh70 gedi.rh71 gedi.rh72 gedi.rh73 gedi.rh74 gedi.rh75 gedi.rh76
## 1 1.12 1.16 1.23 1.31 1.34 1.42 1.49
## 3 0.78 0.82 0.86 0.89 0.97 1.01 1.04
## 4 0.63 0.71 0.74 0.78 0.86 0.89 0.97
## 5 1.08 1.16 1.19 1.27 1.31 1.38 1.46
## 6 4.34 4.90 5.57 6.32 7.11 7.82 8.57
## 7 1.46 1.53 1.60 1.68 1.75 1.83 1.94
## gedi.rh77 gedi.rh78 gedi.rh79 gedi.rh80 gedi.rh81 gedi.rh82 gedi.rh83
## 1 1.53 1.60 1.68 1.75 1.83 1.90 1.98
## 3 1.12 1.16 1.23 1.27 1.34 1.38 1.46
## 4 1.04 1.08 1.16 1.19 1.27 1.34 1.42
## 5 1.53 1.60 1.68 1.75 1.83 1.90 1.98
## 6 9.36 10.29 11.26 12.24 13.14 13.92 14.63
## 7 2.02 2.13 2.20 2.32 2.43 2.54 2.65
## gedi.rh84 gedi.rh85 gedi.rh86 gedi.rh87 gedi.rh88 gedi.rh89 gedi.rh90
## 1 2.05 2.13 2.20 2.32 2.39 2.50 2.62
## 3 1.53 1.60 1.68 1.75 1.83 1.90 1.98
## 4 1.49 1.57 1.64 1.72 1.79 1.87 1.98
## 5 2.09 2.20 2.28 2.39 2.54 2.65 2.80
## 6 15.35 16.09 16.84 17.52 18.04 18.53 19.05
## 7 2.80 2.92 3.03 3.18 3.33 3.44 3.59
## gedi.rh91 gedi.rh92 gedi.rh93 gedi.rh94 gedi.rh95 gedi.rh96 gedi.rh97
## 1 2.73 2.84 2.99 3.14 3.29 3.48 3.70
## 3 2.09 2.20 2.32 2.47 2.62 2.80 3.03
## 4 2.05 2.17 2.28 2.43 2.54 2.73 2.92
## 5 2.95 3.10 3.25 3.44 3.66 3.89 4.15
## 6 19.58 20.14 20.70 21.22 21.71 22.20 22.68
## 7 3.74 3.93 4.08 4.26 4.45 4.68 4.94
## gedi.rh98 gedi.rh99 gedi.rh100 algorithmrun.flag l2b.quality.flag
## 1 4.00 4.41 5.12 1 1
## 3 3.33 3.74 4.41 1 1
## 4 3.14 3.48 4.11 1 1
## 5 4.45 4.86 5.54 1 1
## 6 23.21 23.81 24.67 1 1
## 7 5.24 5.65 6.29 1 1
## latitude.lastbin latitude.bin0 longitude.bin0 longitude.lastbin gedi.pai
## 1 37.85712 37.85712 -110.2303 -110.2303 0.07016369
## 3 37.77660 37.77660 -110.1106 -110.1106 0.10241848
## 4 37.73627 37.73627 -110.0509 -110.0509 0.01360321
## 5 37.69590 37.69590 -109.9912 -109.9912 0.18111534
## 6 37.65550 37.65550 -109.9315 -109.9315 0.51559538
## 7 37.61505 37.61505 -109.8719 -109.8719 0.32282248
## gedi.fhd.normal gedi.omega gedi.pgap.theta gedi.cover
## 1 1.5531045 1 0.9655033 0.034473203
## 3 1.4749274 1 0.9500467 0.049919281
## 4 0.6365142 1 0.9932169 0.006778512
## 5 1.5353090 1 0.9133653 0.086575717
## 6 3.1434364 1 0.7726158 0.227229327
## 7 1.6502810 1 0.8508484 0.149049968Now to the fun part! Took a while to get here, but hopefully the journey thus far has been somewhat painless. So, the process here is (1) run a for loop with 100 iterations; (2) on each loop select a random tree from the 10,000 original trees; (3) use the decision tree-based biomass predictions from that random tree as the values for the regional-scale predictive model’s training data; (4) build random forest model; (5) apply random forest model to all GEDI footprins at the regional scale; (6) add results to a data frame where each column represents the ith prediction (where i is in [1…100]).
# begin uncertainty loop
for (i in seq(1,100)){
# print status
print(paste0(Sys.time(), " Iteration: ", i, "/100"))
# random tree selection
rand.tree <- sample(seq(1,10000), 1)
# add biomass column to table
df.train$biomass <- biomass.all$individual[,rand.tree]
y.col.gd <- grep("biomass", colnames(df.train))
# generate random forest model
rf.gd.i <- ranger(x = df.train[,x.cols.gd],
y = df.train[,y.col.gd],
num.threads = 24)
# generate prediction
pred.gd.i <- predict(object = rf.gd.i,
data = df.gd,
num.threads = 24)
# create results data frame
if (i == 1){
results.df <- data.frame(bio = pred.gd.i$predictions)
colnames(results.df) <- paste0("bio.", str_pad(i, 3, "left", "0"))
} else {
results.df.temp <- data.frame(bio = pred.gd.i$predictions)
colnames(results.df.temp) <- paste0("bio.", str_pad(i, 3, "left", "0"))
results.df <- cbind(results.df, results.df.temp)
}
}## [1] "2021-02-15 18:05:18 Iteration: 1/100"
## [1] "2021-02-15 18:05:20 Iteration: 2/100"
## [1] "2021-02-15 18:05:22 Iteration: 3/100"
## [1] "2021-02-15 18:05:24 Iteration: 4/100"
## [1] "2021-02-15 18:05:26 Iteration: 5/100"
## [1] "2021-02-15 18:05:28 Iteration: 6/100"
## [1] "2021-02-15 18:05:30 Iteration: 7/100"
## [1] "2021-02-15 18:05:31 Iteration: 8/100"
## [1] "2021-02-15 18:05:33 Iteration: 9/100"
## [1] "2021-02-15 18:05:35 Iteration: 10/100"
## [1] "2021-02-15 18:05:36 Iteration: 11/100"
## [1] "2021-02-15 18:05:38 Iteration: 12/100"
## [1] "2021-02-15 18:05:40 Iteration: 13/100"
## [1] "2021-02-15 18:05:42 Iteration: 14/100"
## [1] "2021-02-15 18:05:43 Iteration: 15/100"
## [1] "2021-02-15 18:05:45 Iteration: 16/100"
## [1] "2021-02-15 18:05:47 Iteration: 17/100"
## [1] "2021-02-15 18:05:49 Iteration: 18/100"
## [1] "2021-02-15 18:05:50 Iteration: 19/100"
## [1] "2021-02-15 18:05:52 Iteration: 20/100"
## [1] "2021-02-15 18:05:54 Iteration: 21/100"
## [1] "2021-02-15 18:05:56 Iteration: 22/100"
## [1] "2021-02-15 18:05:58 Iteration: 23/100"
## [1] "2021-02-15 18:05:59 Iteration: 24/100"
## [1] "2021-02-15 18:06:01 Iteration: 25/100"
## [1] "2021-02-15 18:06:03 Iteration: 26/100"
## [1] "2021-02-15 18:06:05 Iteration: 27/100"
## [1] "2021-02-15 18:06:07 Iteration: 28/100"
## [1] "2021-02-15 18:06:08 Iteration: 29/100"
## [1] "2021-02-15 18:06:10 Iteration: 30/100"
## [1] "2021-02-15 18:06:12 Iteration: 31/100"
## [1] "2021-02-15 18:06:14 Iteration: 32/100"
## [1] "2021-02-15 18:06:15 Iteration: 33/100"
## [1] "2021-02-15 18:06:17 Iteration: 34/100"
## [1] "2021-02-15 18:06:19 Iteration: 35/100"
## [1] "2021-02-15 18:06:21 Iteration: 36/100"
## [1] "2021-02-15 18:06:22 Iteration: 37/100"
## [1] "2021-02-15 18:06:24 Iteration: 38/100"
## [1] "2021-02-15 18:06:26 Iteration: 39/100"
## [1] "2021-02-15 18:06:28 Iteration: 40/100"
## [1] "2021-02-15 18:06:30 Iteration: 41/100"
## [1] "2021-02-15 18:06:31 Iteration: 42/100"
## [1] "2021-02-15 18:06:33 Iteration: 43/100"
## [1] "2021-02-15 18:06:35 Iteration: 44/100"
## [1] "2021-02-15 18:06:37 Iteration: 45/100"
## [1] "2021-02-15 18:06:38 Iteration: 46/100"
## [1] "2021-02-15 18:06:40 Iteration: 47/100"
## [1] "2021-02-15 18:06:42 Iteration: 48/100"
## [1] "2021-02-15 18:06:44 Iteration: 49/100"
## [1] "2021-02-15 18:06:46 Iteration: 50/100"
## [1] "2021-02-15 18:06:47 Iteration: 51/100"
## [1] "2021-02-15 18:06:49 Iteration: 52/100"
## [1] "2021-02-15 18:06:51 Iteration: 53/100"
## [1] "2021-02-15 18:06:53 Iteration: 54/100"
## [1] "2021-02-15 18:06:55 Iteration: 55/100"
## [1] "2021-02-15 18:06:56 Iteration: 56/100"
## [1] "2021-02-15 18:06:58 Iteration: 57/100"
## [1] "2021-02-15 18:07:00 Iteration: 58/100"
## [1] "2021-02-15 18:07:02 Iteration: 59/100"
## [1] "2021-02-15 18:07:04 Iteration: 60/100"
## [1] "2021-02-15 18:07:05 Iteration: 61/100"
## [1] "2021-02-15 18:07:07 Iteration: 62/100"
## [1] "2021-02-15 18:07:09 Iteration: 63/100"
## [1] "2021-02-15 18:07:11 Iteration: 64/100"
## [1] "2021-02-15 18:07:13 Iteration: 65/100"
## [1] "2021-02-15 18:07:14 Iteration: 66/100"
## [1] "2021-02-15 18:07:16 Iteration: 67/100"
## [1] "2021-02-15 18:07:18 Iteration: 68/100"
## [1] "2021-02-15 18:07:20 Iteration: 69/100"
## [1] "2021-02-15 18:07:22 Iteration: 70/100"
## [1] "2021-02-15 18:07:23 Iteration: 71/100"
## [1] "2021-02-15 18:07:25 Iteration: 72/100"
## [1] "2021-02-15 18:07:27 Iteration: 73/100"
## [1] "2021-02-15 18:07:29 Iteration: 74/100"
## [1] "2021-02-15 18:07:31 Iteration: 75/100"
## [1] "2021-02-15 18:07:33 Iteration: 76/100"
## [1] "2021-02-15 18:07:35 Iteration: 77/100"
## [1] "2021-02-15 18:07:37 Iteration: 78/100"
## [1] "2021-02-15 18:07:39 Iteration: 79/100"
## [1] "2021-02-15 18:07:40 Iteration: 80/100"
## [1] "2021-02-15 18:07:42 Iteration: 81/100"
## [1] "2021-02-15 18:07:44 Iteration: 82/100"
## [1] "2021-02-15 18:07:46 Iteration: 83/100"
## [1] "2021-02-15 18:07:48 Iteration: 84/100"
## [1] "2021-02-15 18:07:49 Iteration: 85/100"
## [1] "2021-02-15 18:07:51 Iteration: 86/100"
## [1] "2021-02-15 18:07:53 Iteration: 87/100"
## [1] "2021-02-15 18:07:55 Iteration: 88/100"
## [1] "2021-02-15 18:07:57 Iteration: 89/100"
## [1] "2021-02-15 18:07:59 Iteration: 90/100"
## [1] "2021-02-15 18:08:01 Iteration: 91/100"
## [1] "2021-02-15 18:08:03 Iteration: 92/100"
## [1] "2021-02-15 18:08:04 Iteration: 93/100"
## [1] "2021-02-15 18:08:06 Iteration: 94/100"
## [1] "2021-02-15 18:08:08 Iteration: 95/100"
## [1] "2021-02-15 18:08:10 Iteration: 96/100"
## [1] "2021-02-15 18:08:12 Iteration: 97/100"
## [1] "2021-02-15 18:08:14 Iteration: 98/100"
## [1] "2021-02-15 18:08:15 Iteration: 99/100"
## [1] "2021-02-15 18:08:17 Iteration: 100/100"# print the first few rows
head(results.df)## bio.001 bio.002 bio.003 bio.004 bio.005 bio.006 bio.007 bio.008
## 1 22.27942 14.69435 16.29243 24.42585 18.63741 13.52442 21.48355 15.99506
## 2 19.67346 18.06148 22.78708 22.23714 20.96765 18.66953 21.30550 21.61167
## 3 22.32043 15.29182 17.27637 26.80939 27.09408 21.93075 24.48354 19.91888
## 4 38.30301 50.68184 42.09266 44.64103 43.00299 43.12307 55.97270 42.71188
## 5 93.18372 91.91603 100.42045 92.81934 69.93090 101.17317 102.64011 94.75933
## 6 61.79691 63.59656 58.69741 61.35101 51.17896 68.92859 69.92156 57.42127
## bio.009 bio.010 bio.011 bio.012 bio.013 bio.014 bio.015 bio.016
## 1 13.96174 15.55612 10.23473 13.17932 19.67915 20.55815 16.30947 14.71733
## 2 21.69136 16.35749 16.17454 18.43933 20.84688 22.89881 16.57677 16.07537
## 3 29.26300 18.49460 20.06500 17.80887 18.68490 22.36958 20.17746 19.05247
## 4 40.08709 61.37381 39.24650 41.57294 50.04086 36.43035 43.74516 43.02401
## 5 95.67208 119.61810 92.86856 71.45976 57.44527 87.54457 97.52655 84.97316
## 6 64.90551 61.80667 58.60606 55.18776 62.27910 60.61659 64.19792 65.05772
## bio.017 bio.018 bio.019 bio.020 bio.021 bio.022 bio.023 bio.024
## 1 17.79169 13.54247 10.59542 12.51206 10.41354 18.70886 15.77924 10.82601
## 2 22.43536 19.10542 14.64626 18.01027 16.52926 17.79113 20.63946 17.32949
## 3 28.16950 18.98964 17.08459 21.87694 14.13509 19.27543 24.38472 21.70721
## 4 52.81015 40.36746 35.21710 52.02150 34.04377 37.50186 37.34300 51.25030
## 5 98.10719 104.29236 70.67203 88.40856 93.70741 92.23106 98.29841 114.92519
## 6 74.00279 69.74147 60.55424 61.12187 57.18725 50.40022 57.99546 60.74018
## bio.025 bio.026 bio.027 bio.028 bio.029 bio.030 bio.031 bio.032
## 1 21.11047 14.91864 19.94166 13.62953 12.41264 19.63164 16.86713 16.02432
## 2 17.67301 20.09337 18.08309 18.26131 19.13612 22.60352 23.61832 19.19966
## 3 20.04320 19.70440 21.70357 15.23396 22.04460 26.10356 23.33769 23.17656
## 4 47.95770 30.22659 40.69955 32.36373 46.90784 58.18023 39.13856 41.47660
## 5 107.08367 116.80866 114.46630 105.25831 100.26027 120.80177 61.52974 70.19684
## 6 69.89214 52.46016 55.03279 55.72411 63.66523 68.52009 59.59483 68.28460
## bio.033 bio.034 bio.035 bio.036 bio.037 bio.038 bio.039 bio.040
## 1 16.12001 15.09365 17.92440 15.04401 14.46048 16.25425 13.36001 17.01762
## 2 18.52417 19.50970 23.35378 23.35836 18.10660 17.76099 22.84247 20.17864
## 3 24.31364 24.28219 33.78836 26.16699 16.72675 22.20043 23.91846 19.51582
## 4 43.78143 45.85303 65.22213 41.33831 38.49141 46.68495 45.69466 42.51943
## 5 91.98395 95.12019 96.84261 111.27543 101.91780 102.15168 91.05243 97.07201
## 6 51.62628 62.27898 56.57526 65.48147 59.50346 49.60086 58.41665 59.35197
## bio.041 bio.042 bio.043 bio.044 bio.045 bio.046 bio.047 bio.048
## 1 15.32653 17.83774 14.98512 13.23351 19.71306 14.18766 19.19883 22.07051
## 2 21.54980 21.20763 17.49358 19.93035 18.40353 16.97543 21.80805 16.51714
## 3 24.38711 21.80136 15.86516 16.98510 20.81463 22.48475 21.90159 25.00329
## 4 42.29064 40.39438 38.76559 41.47974 41.76744 42.42495 42.50748 43.36957
## 5 95.94444 75.80407 109.99540 112.56553 100.15087 93.79495 95.32137 92.30963
## 6 80.82509 63.08265 63.20048 72.41501 43.42142 66.14537 66.06722 64.19578
## bio.049 bio.050 bio.051 bio.052 bio.053 bio.054 bio.055 bio.056
## 1 15.60341 12.85010 13.85454 14.99372 20.61366 15.70558 14.03981 19.76506
## 2 17.01641 20.27299 19.03070 16.16495 17.46214 21.51782 20.97093 22.58615
## 3 28.99752 20.95218 23.15393 17.64862 27.50688 17.85761 22.92188 28.49433
## 4 35.93395 42.64741 54.58366 38.59008 43.43309 35.77066 37.88066 52.59915
## 5 94.24258 115.97963 103.57497 92.11172 113.45427 72.31846 92.75175 97.75204
## 6 67.55216 45.72222 45.13451 69.62119 64.73214 64.87823 60.30550 70.42214
## bio.057 bio.058 bio.059 bio.060 bio.061 bio.062 bio.063 bio.064
## 1 12.65260 15.94730 20.18167 21.41485 21.03852 17.93279 14.24408 22.78163
## 2 20.65803 20.68827 19.56374 19.91202 16.37755 21.20169 21.19216 17.70838
## 3 17.91187 20.58456 23.16687 27.29638 22.34213 24.61986 23.39299 16.81495
## 4 38.16268 43.85243 38.80042 48.52832 48.92231 53.66292 40.88470 36.29896
## 5 91.27437 100.18869 97.61591 76.73630 83.02156 91.60900 115.91778 90.23199
## 6 58.37456 75.95444 53.26628 53.11362 73.26924 57.10876 46.63388 51.74185
## bio.065 bio.066 bio.067 bio.068 bio.069 bio.070 bio.071 bio.072
## 1 12.50898 13.31710 18.99229 16.04515 16.21263 15.48293 15.11614 15.16355
## 2 19.56605 16.58078 17.04673 17.87390 17.99271 22.61681 16.67882 20.00172
## 3 23.18931 15.12274 24.00154 21.37842 21.54464 23.85917 24.34550 18.48380
## 4 37.29983 46.87274 44.73380 37.60421 50.45423 40.86087 42.52895 56.74804
## 5 90.35514 105.07277 119.47328 101.82945 80.21257 93.56618 103.93218 103.32690
## 6 55.56784 56.35817 71.74525 50.91766 63.36610 58.89260 73.94270 68.51988
## bio.073 bio.074 bio.075 bio.076 bio.077 bio.078 bio.079 bio.080
## 1 15.63544 11.32852 13.76141 12.58680 15.86381 20.80643 16.96262 18.94878
## 2 18.59388 17.63387 18.58002 20.87530 16.80975 19.98526 17.90559 17.62397
## 3 21.32837 16.86766 18.81511 28.05110 19.04308 26.64106 20.92642 22.46722
## 4 49.35506 37.13137 44.55576 64.79188 36.60140 56.69034 44.79138 39.49292
## 5 103.44050 93.82135 89.20792 100.28633 101.40723 79.98124 103.83589 108.13968
## 6 58.51923 61.26432 44.55950 62.92634 41.95543 68.64588 58.73192 59.73399
## bio.081 bio.082 bio.083 bio.084 bio.085 bio.086 bio.087 bio.088
## 1 15.50052 13.64986 17.88680 11.66330 14.53277 14.57883 22.58310 25.07212
## 2 23.92169 16.85074 21.35305 16.42704 20.66761 20.41321 25.36220 22.02092
## 3 20.91271 18.54515 25.45126 21.20827 20.35056 26.99380 25.43650 21.98372
## 4 36.97373 46.38558 56.92459 36.08261 38.66915 40.37893 40.98408 42.74167
## 5 84.19984 100.84547 84.67672 105.88689 84.86401 99.40741 87.80978 105.97454
## 6 58.01823 65.13457 60.76739 67.17963 54.64972 66.81767 60.25108 50.48793
## bio.089 bio.090 bio.091 bio.092 bio.093 bio.094 bio.095 bio.096
## 1 18.59785 22.22894 16.20806 14.20707 14.02582 18.52680 15.55398 7.48998
## 2 21.98616 19.41517 18.96764 23.55896 16.85858 22.09469 17.07118 16.53038
## 3 20.54857 22.78202 23.96982 22.02145 29.03539 17.40119 20.61280 18.25974
## 4 42.14656 39.84997 44.00885 44.27109 40.39790 49.67918 40.62339 36.34454
## 5 84.27423 91.42249 96.14705 116.90336 98.52951 98.94345 84.66121 102.24258
## 6 69.76470 67.33392 64.39218 54.34470 57.85073 56.04324 58.13443 61.94140
## bio.097 bio.098 bio.099 bio.100
## 1 11.60516 18.13500 19.54418 23.48656
## 2 17.51103 22.25513 17.25299 20.91889
## 3 21.57258 27.92126 19.54092 34.58831
## 4 53.07158 43.40369 45.67832 45.90342
## 5 87.27844 91.90942 118.45712 82.70336
## 6 60.62625 59.20814 66.20542 59.68364Using that results data frame (“results.df”) generate a new dataframe with summary statistics. And write the outputs to a shapefile.
# create results data frame
summary.df <- df.gd[,c("shot.num", "latitude.bin0", "longitude.bin0")]
summary.df$bio.pred <- predict(rf.gd, df.gd)
summary.df$uc.mean <- apply(results.df, 1, mean)
summary.df$uc.sd <- apply(results.df, 1, sd)
summary.df$uc.cv <- summary.df$uc.sd / summary.df$uc.mean
summary.df$uc.q05 <- apply(results.df, 1, FUN = function(x) quantile(x, 0.05))
summary.df$uc.q95 <- apply(results.df, 1, FUN = function(x) quantile(x, 0.95))
# write results to shapefile
summary.spdf <- SpatialPointsDataFrame(coords = summary.df[,c("longitude.bin0",
"latitude.bin0")],
data = summary.df,
proj4string = CRS("+init=epsg:4326"))
writeOGR(summary.spdf, uc.dir, "gedi_biomass_pred_pts_summary_lidar_boxes_top_4", "ESRI Shapefile", overwrite_layer = T)## Warning in writeOGR(summary.spdf, uc.dir,
## "gedi_biomass_pred_pts_summary_lidar_boxes_top_4", : Field names abbreviated for
## ESRI Shapefile driverThat’s it!