3_data_extra_Reynolds_lab
Bruno S. Carturan, Eric Hertz, Stephanie J. Peacock
1 Import files
1.1 PSE data
#'* Import the cleaned NuSEDS data matched with the cuid and streamid of the PSE *
nuseds_cuid_streamid <- import_mostRecent_file_fun(wd = paste0(wd_output,"/archive"),
pattern = "2_nuseds_cuid_streamid")## [1] "File imported: 2_nuseds_cuid_streamid_2026-03-12.csv ; Date modified: 2026-03-12 16:44:19.196857"# head(nuseds_cuid_streamid)
nuseds_cuid_streamid$source_id <- "NuSEDS_20251103"#'* Import the NuSEDS field definitions *
nuseds_fields_definitions <- nuseds_fields_definitions_fun(wd_references = wd_references_dropbox)#'* Import the shape files for the Region boundaries *
#' Note that se_boundary/se_boundary.shp is used in 0_assign-regions.R. This is a
#' lighter shape file but contains the same regions. The code here works with
#' se_boundary.shp.
# regions_shp <- st_read(paste0(wd_pop_indic_data_gis_dropbox,"/se_boundary_regions/se_boundary_regions.shp")) %>%
# st_transform(crs = 4269)
# unique(regions_shp$regionname)
wd_geo_regions <- gsub("1_PROJECTS","5_DATA/Mapping/study areas/shapefiles/PSE_regions/",wd_X_Drive1_PROJECTS)
regions_shp <- st_read(paste0(wd_geo_regions,"se_boundary_regions_simple/se_boundary_regions_simple.shp")) %>%
st_transform(crs = 4269)## Reading layer `se_boundary_regions_simple' from data source
## `C:\Users\bcarturan\Salmon Watersheds Dropbox\Bruno Carturan\X Drive\5_DATA\Mapping\study areas\shapefiles\PSE_regions\se_boundary_regions_simple\se_boundary_regions_simple.shp'
## using driver `ESRI Shapefile'
## Simple feature collection with 9 features and 4 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: 273611.402 ymin: 368824.74 xmax: 1870608.39 ymax: 1907824.79
## Projected CRS: NAD83 / BC Albers# unique(regions_shp$Region)
sf_use_s2(FALSE) # so that st_intersects() and st_simplify() can be used#'* Import the geodatabase for the CU boundaries *
wd_geo_cus <- gsub("1_PROJECTS","5_DATA/CUs_Master/GDB/",wd_X_Drive1_PROJECTS)
CUs_gdb <- st_read(paste0(wd_geo_cus,"PSF_CUs_Master.gdb")) %>%
st_transform(crs = 4269)## Multiple layers are present in data source C:\Users\bcarturan\Salmon Watersheds Dropbox\Bruno Carturan\X Drive\5_DATA\CUs_Master\GDB\PSF_CUs_Master.gdb, reading layer `PSF_CUs_updatedDec2021'.
## Use `st_layers' to list all layer names and their type in a data source.
## Set the `layer' argument in `st_read' to read a particular layer.## Reading layer `PSF_CUs_updatedDec2021' from data source
## `C:\Users\bcarturan\Salmon Watersheds Dropbox\Bruno Carturan\X Drive\5_DATA\CUs_Master\GDB\PSF_CUs_Master.gdb'
## using driver `OpenFileGDB'## Simple feature collection with 480 features and 18 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: -141.001678 ymin: 48.2968085 xmax: -118.162522 ymax: 68.7059621
## Geodetic CRS: NAD83# remove non-used region values
cond <- ! CUs_gdb$region_name %in% c("Not Assessed","Arctic/Mackenzie")
CUs_gdb <- CUs_gdb[cond,]
CUs_gdb <- st_simplify(x = CUs_gdb, dTolerance = .002) # to reduce computation time1.2 SFU data
#'* Import the SFU data: escapement *
SFU_escap <- read_excel(paste(wd_data_dropbox,"SFU_Escapement_data_Master_PSF.xlsx",sep="/"),
sheet = "Estimates") |>
as.data.frame()
head(SFU_escap)## reynolds.me nuseds.me watershed.code year species estimate.number
## 1 Ada ADA COVE CREEK 915-213000-71100 2024 chum 810
## 2 Ada ADA COVE CREEK 915-213000-71100 2024 coho NA
## 3 Ada ADA COVE CREEK 915-213000-71100 2024 pink NA
## 4 Ada ADA COVE CREEK 915-213000-71100 2024 sockeye NA
## 5 Ada ADA COVE CREEK 915-213000-71100 2023 chum 330
## 6 Ada ADA COVE CREEK 915-213000-71100 2023 coho 8
## estimate.source estimate.method
## 1 NuSEDS Area Under the Curve
## 2 <NA> <NA>
## 3 <NA> <NA>
## 4 <NA> <NA>
## 5 NuSEDS Area Under the Curve
## 6 NuSEDS Expert Opinion# nrow(SFU_escap) # 3853
SFU_escap$source_id <- "Reynolds_20260209"#'* Import the SFU data: stream info *
#' Preious file: SFU_Escapement_PSF.xlsx
SFU_stream <- read_excel(paste(wd_data_dropbox,"SFU_Escapement_data_Master_PSF.xlsx",sep="/"),
sheet = "Coordinates") |>
as.data.frame()
head(SFU_stream)## SFU Stream Name Nuseds Names Area Watershed Code
## 1 Ada ADA COVE CREEK 7 915-213000-71100
## 2 Beales BEALE'S LAGOON CREEK 7 915-233500-13600-03100
## 3 Bullock Main BULLOCK CHANNEL #2 CREEK 7 915-381700-55200
## 4 Bullock Square <NA> 7 915-381700-62200
## 5 Cheenis CHAMISS CREEK 7 910-448100
## 6 Clatse CLATSE CREEK 7 910-385700
## Latitude_Longitude (River Mouth) UTM Easting UTM Northing
## 1 52°03'23.1"N 128°03'04.9"W 565099 5767640
## 2 52°10'59.5"N 127°58'57.3"W 569573 5782313
## 3 52°24'09.1"N 128°04'37.4"W 562791 5806212
## 4 52°21'40.0"N 128°03'52.1"W 563598 5801796
## 5 52°29'16.0"N 128°06'28.9"W 560566 5815666
## 6 52°20'22.1"N 127°50'26.6"W 579193 5798966Some checks and modifications:
# Remove rows with NAs
cond <- is.na(SFU_escap$estimate.number) | SFU_escap$estimate.number == "NA"
SFU_escap <- SFU_escap[!cond,]
sum(cond) # 1428## [1] 1428# CHECK of duplicated rows --> should all be false
any(duplicated(SFU_escap))## [1] FALSEany(duplicated(SFU_escap[,c("reynolds.me","year","species","estimate.number")]))## [1] FALSE# CHECK that the stream names match between the two datasets
all(SFU_escap$reynolds.me %in% SFU_stream$SFU_Stream_Name)## [1] FALSEall(SFU_stream$SFU_Stream_Name %in% SFU_escap$reynolds.me)## [1] TRUEcond <- ! SFU_escap$reynolds.me %in% SFU_stream$`SFU Stream Name`
SFU_escap$reynolds.me [cond] |> unique()## [1] "Beales Left" "Beales Right" "Fell Creek"
## [4] "Mosquito Bay Left" "Mosquito Bay Right"cond <- ! SFU_stream$`SFU Stream Name` %in% SFU_escap$reynolds.me
SFU_stream$`SFU Stream Name`[cond]## [1] "Fell"# "Fell"
# unique(SFU_stream$SFU_Stream_Name)
# "Beales Left" & "Beales Right" --> "Beales
# "Fell Creek" --> "Fell
# "Mosquito Bay Left" & "Mosquito Bay Right" --> "Mosquito Bay"
cond <- SFU_escap$reynolds.me == "Fell Creek"
SFU_escap$reynolds.me[cond] <- "Fell"We remove extra data for Beales Left & Right and Mosquito Bay Left and Right because these counts should be combined and the combined counts are also in the data set, as expressed in Arianne Nickels’ email: Please note that we split both Mosquito bay and Beales into two streams, so the numbers from “Mosquito bay” are a combination of both “Mosquito bay left” and “Mosquito bay right”. This is the same for Beales. The reason is because the streams both share an estuary but then split off once you hit the tree line. DFO considers them one stream, so it might be easiest to stick to that. I thought I’d include the combined data and the split data just in case.”
cond_remove <- SFU_escap$reynolds.me %in% c("Beales Left","Beales Right",
"Mosquito Bay Left","Mosquito Bay Right")
SFU_escap <- SFU_escap[!cond_remove,]
all(SFU_escap$reynolds.me %in% SFU_stream$`SFU Stream Name`)## [1] TRUEall(SFU_stream$`SFU Stream Name` %in% SFU_escap$reynolds.me)## [1] TRUE1.3 Find ESTIMATE_CLASSIFICATION
#' Find for each value in estimate.method the corresponding value in the fields
# https://www.salmonexplorer.ca/methods/analytical-approach.html#data-quality
# correct methods
unique(SFU_escap$estimate.method)## [1] "Area Under the Curve" "Expert Opinion"
## [3] "Peak live + Dead" "Peak Live + Dead"
## [5] "Unknown Estimate Method" "Other Estimate Method"
## [7] "Fixed Site Census" "Peak Live + Cumulative Dead"unique(nuseds_cuid_streamid$ESTIMATE_METHOD)## [1] "Fence Count" "Mark & Recapture: Petersen"
## [3] "Not Applicable" "Peak Live + Dead"
## [5] "Area Under the Curve" "Unknown Estimate Method"
## [7] "Other Estimate Method" "Peak Live * Expansion"
## [9] "Addition/Subtraction" "Multiplication/Division"
## [11] "Redd Count" "Sonar-ARIS"
## [13] "Resistivity Counter" "Combined Methods"
## [15] "Calibrated Time Series" "(Peak Live+Cum Dead)*Expansion"
## [17] "Expert Opinion" "Peak Live + Cumulative Dead"
## [19] "Aerial Survey" "Video Counter"
## [21] "Sonar-DIDSON" "Cumulative New"
## [23] "Mark & Recapture: Bayesian" "Mark & Recapture: Open Model"
## [25] "Lake Expansion"SFU_escap$estimate.method[SFU_escap$estimate.method == "Peak live + Dead"] <- "Peak Live + Dead"
estimate.method_SFU <- unique(SFU_escap$estimate.method)
estimate.method_SFU[! estimate.method_SFU %in% unique(nuseds_cuid_streamid$ESTIMATE_METHOD)]## [1] "Fixed Site Census"SFU_escap$ESTIMATE_CLASSIFICATION <- NA
SFU_escap$stream_survey_quality <- NA
cond <- SFU_escap$estimate.method == "Fixed Site Census"
SFU_escap[cond,]## reynolds.me nuseds.me watershed.code year species
## 1325 Fannie Left FANNIE COVE LEFT HAND CREEK 915-213000-68700 2022 pink
## estimate.number estimate.source estimate.method source_id
## 1325 300 NuSEDS Fixed Site Census Reynolds_20260209
## ESTIMATE_CLASSIFICATION stream_survey_quality
## 1325 NA NA#' For metadata in SFU_Escapement_data_Master_PSF.csv:
#' "Fixed Site Census: Combining one or more raw observations into a single estimate
#' (e.g. add all daily fence observation SIL to create a single annual estimate)."
#' --> Medium-Low: Low to moderate effort (1-4 trips), known survey method --> RELATIVE ABUNDANCE (TYPE-4)
SFU_escap$ESTIMATE_CLASSIFICATION[cond] <- "RELATIVE ABUNDANCE (TYPE-4)"
SFU_escap$stream_survey_quality[cond] <- "Medium-Low"
# for the rest of the values:
methods_SFU_l <- sapply(estimate.method_SFU,function(m){
cond <- nuseds_cuid_streamid$ESTIMATE_METHOD == m
if(any(cond)){
out <- list()
x <- table(nuseds_cuid_streamid$ESTIMATE_CLASSIFICATION[cond])
x <- rev(sort(x))
out[[1]] <- x
x <- table(nuseds_cuid_streamid$stream_survey_quality[cond])
x <- rev(sort(x))
out[[2]] <- x
names(out) <- c("ESTIMATE_CLASSIFICATION","stream_survey_quality")
}else{
out <- NA
}
return(out)
})
val <- "Area Under the Curve"
methods_SFU_l[[val]]$ESTIMATE_CLASSIFICATION##
## RELATIVE ABUNDANCE (TYPE-3) RELATIVE ABUNDANCE (TYPE-4)
## 5081 3213
## RELATIVE ABUNDANCE (TYPE-5) TRUE ABUNDANCE (TYPE-1)
## 643 313
## TRUE ABUNDANCE (TYPE-2) UNKNOWN
## 278 208
## PRESENCE-ABSENCE (TYPE-6) RELATIVE: CONSTANT MULTI-YEAR METHODS
## 174 143
## RELATIVE: VARYING MULTI-YEAR METHODS
## 1methods_SFU_l[[val]]$stream_survey_quality##
## Medium Medium-Low Low High Medium-High Unknown
## 5081 3213 961 313 278 208cond <- SFU_escap$estimate.method == val
SFU_escap$ESTIMATE_CLASSIFICATION[cond] <- "RELATIVE ABUNDANCE (TYPE-4)" # to be conservative
SFU_escap$stream_survey_quality[cond] <- "Medium-Low"
val <- "Expert Opinion"
methods_SFU_l[[val]]$ESTIMATE_CLASSIFICATION##
## PRESENCE-ABSENCE (TYPE-6) RELATIVE ABUNDANCE (TYPE-5)
## 20595 3776
## RELATIVE ABUNDANCE (TYPE-4) RELATIVE ABUNDANCE (TYPE-3)
## 1700 448
## UNKNOWN TRUE ABUNDANCE (TYPE-1)
## 438 101
## TRUE ABUNDANCE (TYPE-2) RELATIVE: CONSTANT MULTI-YEAR METHODS
## 31 24
## RELATIVE: VARYING MULTI-YEAR METHODS NO SURVEY THIS YEAR
## 2 1
##
## 1methods_SFU_l[[val]]$stream_survey_quality##
## Low Medium-Low Medium Unknown High Medium-High
## 24397 1700 448 438 101 31cond <- SFU_escap$estimate.method == val
SFU_escap$ESTIMATE_CLASSIFICATION[cond] <- "PRESENCE-ABSENCE (TYPE-6)"
SFU_escap$stream_survey_quality[cond] <- "Low"
val <- "Peak Live + Dead"
methods_SFU_l[[val]]$ESTIMATE_CLASSIFICATION##
## RELATIVE ABUNDANCE (TYPE-5) RELATIVE ABUNDANCE (TYPE-4)
## 3745 2523
## PRESENCE-ABSENCE (TYPE-6) RELATIVE ABUNDANCE (TYPE-3)
## 680 531
## UNKNOWN TRUE ABUNDANCE (TYPE-1)
## 232 81
## RELATIVE: CONSTANT MULTI-YEAR METHODS TRUE ABUNDANCE (TYPE-2)
## 63 7
## NO SURVEY RELATIVE: VARYING MULTI-YEAR METHODS
## 3 1
## NO SURVEY THIS YEAR
## 1methods_SFU_l[[val]]$stream_survey_quality##
## Low Medium-Low Medium Unknown High Medium-High
## 4489 2523 531 232 81 7cond <- SFU_escap$estimate.method == val
SFU_escap$ESTIMATE_CLASSIFICATION[cond] <- "RELATIVE ABUNDANCE (TYPE-4)"
SFU_escap$stream_survey_quality[cond] <- "Medium-Low"
val <- "Unknown Estimate Method"
methods_SFU_l[[val]]$ESTIMATE_CLASSIFICATION##
## UNKNOWN PRESENCE-ABSENCE (TYPE-6)
## 134282 1575
## RELATIVE: CONSTANT MULTI-YEAR METHODS RELATIVE: VARYING MULTI-YEAR METHODS
## 283 251
## TRUE ABUNDANCE (TYPE-1) NO SURVEY THIS YEAR
## 243 140
## RELATIVE ABUNDANCE (TYPE-4) RELATIVE ABUNDANCE (TYPE-5)
## 132 109
## RELATIVE ABUNDANCE (TYPE-3) TRUE ABUNDANCE (TYPE-2)
## 59 20
## NO SURVEY
## 1methods_SFU_l[[val]]$stream_survey_quality##
## Unknown Low High Medium-Low Medium Medium-High
## 134282 2218 243 132 59 20cond <- SFU_escap$estimate.method == val
SFU_escap$ESTIMATE_CLASSIFICATION[cond] <- "UNKNOWN"
SFU_escap$stream_survey_quality[cond] <- "Unknown"
val <- "Other Estimate Method"
methods_SFU_l[[val]]$ESTIMATE_CLASSIFICATION##
## RELATIVE ABUNDANCE (TYPE-4) RELATIVE ABUNDANCE (TYPE-3)
## 2074 1553
## PRESENCE-ABSENCE (TYPE-6) RELATIVE ABUNDANCE (TYPE-5)
## 275 251
## TRUE ABUNDANCE (TYPE-2) TRUE ABUNDANCE (TYPE-1)
## 165 8
## UNKNOWN
## 7methods_SFU_l[[val]]$stream_survey_quality##
## Medium-Low Medium Low Medium-High High Unknown
## 2074 1553 526 165 8 7cond <- SFU_escap$estimate.method == val
SFU_escap$ESTIMATE_CLASSIFICATION[cond] <- "RELATIVE ABUNDANCE (TYPE-4)"
SFU_escap$stream_survey_quality[cond] <- "Medium-Low"
val <- "Peak Live + Cumulative Dead"
methods_SFU_l[[val]]$ESTIMATE_CLASSIFICATION##
## RELATIVE ABUNDANCE (TYPE-4) RELATIVE ABUNDANCE (TYPE-3)
## 2772 2050
## RELATIVE ABUNDANCE (TYPE-5) PRESENCE-ABSENCE (TYPE-6)
## 218 74
## TRUE ABUNDANCE (TYPE-2) TRUE ABUNDANCE (TYPE-1)
## 5 2methods_SFU_l[[val]]$stream_survey_quality##
## Medium-Low Medium Low Medium-High High
## 2772 2050 292 5 2cond <- SFU_escap$estimate.method == val
SFU_escap$ESTIMATE_CLASSIFICATION[cond] <- "RELATIVE ABUNDANCE (TYPE-4)"
SFU_escap$stream_survey_quality[cond] <- "Medium-Low"
any(is.na(SFU_escap$ESTIMATE_CLASSIFICATION))## [1] FALSE2 Match locations
There are 23 locations to match:
## SFU Stream Name Nuseds Names Latitude_Longitude (River Mouth)
## 1 Ada ADA COVE CREEK 52°03'23.1"N 128°03'04.9"W
## 2 Beales BEALE'S LAGOON CREEK 52°10'59.5"N 127°58'57.3"W
## 3 Bullock Main BULLOCK CHANNEL #2 CREEK 52°24'09.1"N 128°04'37.4"W
## 4 Bullock Square <NA> 52°21'40.0"N 128°03'52.1"W
## 5 Cheenis CHAMISS CREEK 52°29'16.0"N 128°06'28.9"W
## 6 Clatse CLATSE CREEK 52°20'22.1"N 127°50'26.6"W
## 7 Codville <NA> 52°04'38.6"N 127°51'44.5"W
## 8 Fancy Head FANCY COVE HEAD CREEK 52°03'35.1"N 128°00'35.5"W
## 9 Fancy Right <NA> 52°03'40.6"N 128°00'54.9"W
## 10 Fannie Left FANNIE COVE LEFT HAND CREEK 52°02'34.8"N 128°04'03.3"W
## 11 Fell <NA> 52°26'01.9"N 128°04'46.2"W
## 12 Goatbushu GOAT BUSHU CREEK 52°12'46.0"N 127°52'38.0"W
## 13 Hooknose HOOK NOSE CREEK 52°07'25.2"N 127°50'23.3"W
## 14 Kill Creek <NA> 52°25'30.6"N 128°05'34.5"W
## 15 Kunsoot Main KUNSOOT RIVER 52°08'57.3"N 128°00'33.5"W
## 16 Lee LEE CREEK 52°30'44.5"N 127°49'56.9"W
## 17 Mosquito Bay <NA> 52°23'51.3"N 128°10'02.7"W
## 18 Neekas NEEKAS CREEK 52°28'06.3"N 128°09'38.2"W
## 19 Rainbow RAINBOW CREEK 52°27'10.1"N 127°43'44.8"W
## 20 Sagar SAGAR CREEK 52°05'48.8"N 127°50'22.6"W
## 21 Troupe North <NA> 52°17'22.3"N 128°01'42.9"W
## 22 Troupe South <NA> 52°16'49.9"N 128°02'32.1"W
## 23 Webster WEBSTER LAKE CREEK 52°17'02.1"N 127°59'21.9"W2.1 Some modifications
Convert coordinates from degrees to decimals:
## SFU Stream Name Nuseds Names Latitude Longitude
## 1 Ada ADA COVE CREEK 52.0564167 -128.051361
## 2 Beales BEALE'S LAGOON CREEK 52.1831944 -127.982583
## 3 Bullock Main BULLOCK CHANNEL #2 CREEK 52.4025278 -128.077056
## 4 Bullock Square <NA> 52.3611111 -128.064472
## 5 Cheenis CHAMISS CREEK 52.4877778 -128.108028
## 6 Clatse CLATSE CREEK 52.3394722 -127.840722
## 7 Codville <NA> 52.0773889 -127.862361
## 8 Fancy Head FANCY COVE HEAD CREEK 52.0597500 -128.009861
## 9 Fancy Right <NA> 52.0612778 -128.015250
## 10 Fannie Left FANNIE COVE LEFT HAND CREEK 52.0430000 -128.067583
## 11 Fell <NA> 52.4338611 -128.079500
## 12 Goatbushu GOAT BUSHU CREEK 52.2127778 -127.877222
## 13 Hooknose HOOK NOSE CREEK 52.1236667 -127.839806
## 14 Kill Creek <NA> 52.4251667 -128.092917
## 15 Kunsoot Main KUNSOOT RIVER 52.1492500 -128.009306
## 16 Lee LEE CREEK 52.5123611 -127.832472
## 17 Mosquito Bay <NA> 52.3975833 -128.167417
## 18 Neekas NEEKAS CREEK 52.4684167 -128.160611
## 19 Rainbow RAINBOW CREEK 52.4528056 -127.729111
## 20 Sagar SAGAR CREEK 52.0968889 -127.839611
## 21 Troupe North <NA> 52.2895278 -128.028583
## 22 Troupe South <NA> 52.2805278 -128.042250
## 23 Webster WEBSTER LAKE CREEK 52.2839167 -127.989417Add the region field using the PSE’s region shape file:
## region SFU_Stream_Name Nuseds_Names Latitude
## 1 Central Coast Ada ADA COVE CREEK 52.0564167
## 2 Central Coast Beales BEALE'S LAGOON CREEK 52.1831944
## 3 Central Coast Bullock Main BULLOCK CHANNEL #2 CREEK 52.4025278
## 4 Central Coast Bullock Square <NA> 52.3611111
## 5 Central Coast Cheenis CHAMISS CREEK 52.4877778
## 6 Central Coast Clatse CLATSE CREEK 52.3394722
## 7 Central Coast Codville <NA> 52.0773889
## 8 Central Coast Fancy Head FANCY COVE HEAD CREEK 52.0597500
## 9 Central Coast Fancy Right <NA> 52.0612778
## 10 Central Coast Fannie Left FANNIE COVE LEFT HAND CREEK 52.0430000
## 11 Central Coast Fell <NA> 52.4338611
## 12 Central Coast Goatbushu GOAT BUSHU CREEK 52.2127778
## 13 Central Coast Hooknose HOOK NOSE CREEK 52.1236667
## 14 Central Coast Kill Creek <NA> 52.4251667
## 15 Central Coast Kunsoot Main KUNSOOT RIVER 52.1492500
## 16 Central Coast Lee LEE CREEK 52.5123611
## 17 Central Coast Mosquito Bay <NA> 52.3975833
## 18 Central Coast Neekas NEEKAS CREEK 52.4684167
## 19 Central Coast Rainbow RAINBOW CREEK 52.4528056
## 20 Central Coast Sagar SAGAR CREEK 52.0968889
## 21 Central Coast Troupe North <NA> 52.2895278
## 22 Central Coast Troupe South <NA> 52.2805278
## 23 Central Coast Webster WEBSTER LAKE CREEK 52.2839167
## Longitude
## 1 -128.051361
## 2 -127.982583
## 3 -128.077056
## 4 -128.064472
## 5 -128.108028
## 6 -127.840722
## 7 -127.862361
## 8 -128.009861
## 9 -128.015250
## 10 -128.067583
## 11 -128.079500
## 12 -127.877222
## 13 -127.839806
## 14 -128.092917
## 15 -128.009306
## 16 -127.832472
## 17 -128.167417
## 18 -128.160611
## 19 -127.729111
## 20 -127.839611
## 21 -128.028583
## 22 -128.042250
## 23 -127.9894172.2 Match locations
We try to match the stream names in SFU_stream with those in the PSE.
There are 15 locations that matched:
## region SFU_Stream_Name WATERBODY GFE_ID
## 1 Central Coast Ada ADA COVE CREEK 2683
## 2 Central Coast Beales BEALE'S LAGOON CREEK 1803
## 3 Central Coast Bullock Main BULLOCK CHANNEL #2 CREEK 2689
## 5 Central Coast Cheenis CHAMISS CREEK 998
## 6 Central Coast Clatse CLATSE CREEK 989
## 8 Central Coast Fancy Head FANCY COVE HEAD CREEK 2685
## 10 Central Coast Fannie Left FANNIE COVE LEFT HAND CREEK 2687
## 12 Central Coast Goatbushu GOAT BUSHU CREEK 987
## 13 Central Coast Hooknose HOOK NOSE CREEK 1796
## 15 Central Coast Kunsoot Main KUNSOOT RIVER 1801
## 16 Central Coast Lee LEE CREEK 992
## 18 Central Coast Neekas NEEKAS CREEK 999
## 19 Central Coast Rainbow RAINBOW CREEK 990
## 20 Central Coast Sagar SAGAR CREEK 1794
## 23 Central Coast Webster WEBSTER LAKE CREEK 1807There are 6 locations that did not match:
## region SFU_Stream_Name WATERBODY GFE_ID
## 7 Central Coast Codville <NA> NA
## 11 Central Coast Fell <NA> NA
## 14 Central Coast Kill Creek <NA> NA
## 17 Central Coast Mosquito Bay <NA> NA
## 21 Central Coast Troupe North <NA> NA
## 22 Central Coast Troupe South <NA> NAThere are 2 locations for which we are not sure and we show here the
potential matches (distance is the distance between SFU’s
and DFO’s locations in km):
## SFU_Stream_Name GFE_ID WATERBODY distance
## 1 Bullock Square 995 BULLOCK CHANNEL CREEKS 3.379
## 2 Bullock Square 2688 BULLOCK CHANNEL EAST CREEK 2.120
## 3 Bullock Square 2689 BULLOCK CHANNEL #2 CREEK 4.705
## 4 Bullock Square 2690 BULLOCK CHANNEL #3 NORTH CREEK 0.559
## 5 Bullock Square 2691 BULLOCK CHANNEL #3 SOUTH CREEK 4.638
## 6 Fancy Right 2684 FANCY COVE RIGHT HAND CREEK 0.199
## 7 Fancy Right 2685 FANCY COVE HEAD CREEK 0.509To check if any of these location match, we look at the count data. If the counts are the same for several years then it is likely a match (the SFU points are from SFU):
## SFU_Stream_Name Nuseds_Names Area Watershed_Code
## 4 Bullock Square <NA> 7 915-381700-62200
## 9 Fancy Right <NA> 7 915-213000-72700
## Latitude_Longitude_(River_Mouth) UTM_Easting UTM_Northing Latitude
## 4 52°21'40.0"N 128°03'52.1"W 563598 5801796 52.3611111
## 9 52°03'40.6"N 128°00'54.9"W 567446 5768123 52.0612778
## Longitude region GFE_ID in_PSE X_LONGT Y_LAT WATERBODY
## 4 -128.064472 Central Coast NA ? -128.05055 52.0555371 <NA>
## 9 -128.015250 Central Coast NA ? -128.05055 52.0555371 <NA>
There does not seem to be any match, except may be for Bullock Square and BULLOCK CHANNEL #3 SOUTH CREEK but the distances between the two are > 4km (as shown in table above), so we decide that these are different locations and time series.
3 Merge the two datasets
Here is the procedure:
if
IndexId/POP_IDfound (soGFE_IDfound too):if new counts –> add them to NuSEDS
if counts in conflicts (different value) –> replace values in NuSEDS UNLESS THESE POINTS ARE FROM NUSEDS AS WELL, in which case we keep our data assuming our dataset is more up to date.
UPDATE: the counts for coho and sockeye sourced from SFU were collected in September and October, which is not during peak season (source: Arianne Nickels, 2026-03-12); these counts are consequently trumped by NuSEDS counts in case the latte are available, otherwise their
stream_survey_qualityis downgradedif counts are the same –> do nothing
in any cases, do not change info about the location
if
IndexId/POP_IDnot found butGFE_IDfound:add time series to NuSEDS
do not change info about the location
if
IndexId/POP_IDnot found andGFE_IDfound:add time series to NuSEDS
add info about the location
Note that it is essential to appropriately update the value of the variables associated to counts, populations and locations. The SFU data is shown with purple circles, those ones with one circle were sourced from NuSEDS (by Reynolds’ team), the ones with two circles are Reynolds’s own estimates.
#' variables to delete the value when editing nuseds_cuid_streamid_Reynolds with
#' existing IndexId and GFE_ID
var_toDelete <- c("NATURAL_ADULT_SPAWNERS","NATURAL_JACK_SPAWNERS","ADULT_PRESENCE",
"JACK_PRESENCE","NATURAL_SPAWNERS_TOTAL","ADULT_BROODSTOCK_REMOVALS",
"JACK_BROODSTOCK_REMOVALS","TOTAL_BROODSTOCK_REMOVALS","RUN_TYPE",
"OTHER_REMOVALS","TOTAL_RETURN_TO_RIVER","Returns",
"START_DTT","END_DTT","NATURAL_ADULT_FEMALES",
"NATURAL_ADULT_MALES","EFFECTIVE_FEMALES",
"WEIGHTED_PCT_SPAWN","WATERBODY_ID","STREAM_ARRIVAL_DT_FROM",
"STREAM_ARRIVAL_DT_TO","START_SPAWN_DT_FROM","START_SPAWN_DT_TO",
"PEAK_SPAWN_DT_FROM","PEAK_SPAWN_DT_TO","END_SPAWN_DT_FROM",
"END_SPAWN_DT_TO","ACCURACY","PRECISION","INDEX_YN",
"RELIABILITY","ESTIMATE_STAGE","NO_INSPECTIONS_USED",
"CREATED_DTT","UPDATED_DTT","ACT_ID","Source","Spawners",
"SpawnersSource","Broodstock","BroodstockSource","Removals",
"RemovalsSource","CMNTS","EFFECTIVE_DT")
#' variables to delete the value when adding rows to nuseds_cuid_streamid_Reynolds
#' with non-existing IndexId and but existing GFE_ID
var_toDelete_IndexId <- c("IndexId","POP_ID","POPULATION","streamid")
#' variables to delete the value when adding rows to nuseds_cuid_streamid_Reynolds
#' with non-existing GFE_ID
var_toDelete_GFE_ID <- c("GFE_ID","WATERSHED_CDE","FWA_WATERSHED_CDE","WATERBODY","sys_nm",
"GAZETTED_NAME","LOCAL_NAME_1","LOCAL_NAME_2","CENSUS_SITE",
"X_LONGT","Y_LAT","FAZ_ACRO","MAZ_ACRO","JAZ_ACRO",
"AREA","StatArea","IS_INDICATOR","GFE_TYPE","coordinates_changed")
## [1] "The population of species sockeye at location Ada is not in NuSEDS (location is in NuSEDS)"
## [1] "The population of species coho at location Bullock Main is not in NuSEDS (location is in NuSEDS)"
## [1] "The population of species sockeye at location Bullock Main is not in NuSEDS (location is in NuSEDS)"
## [1] "Location Bullock Square is not in NuSEDS"
## [1] "Location Bullock Square is not in NuSEDS"
## [1] "Location Bullock Square is not in NuSEDS"
## [1] "Location Codville is not in NuSEDS"
## [1] "Location Codville is not in NuSEDS"
## [1] "Location Codville is not in NuSEDS"
## [1] "The population of species coho at location Fancy Head is not in NuSEDS (location is in NuSEDS)"
## [1] "Location Fancy Right is not in NuSEDS"
## [1] "Location Fancy Right is not in NuSEDS"
## [1] "Location Fancy Right is not in NuSEDS"
## [1] "Location Fancy Right is not in NuSEDS"
## [1] "Location Fell is not in NuSEDS"
## [1] "Location Fell is not in NuSEDS"
## [1] "Location Fell is not in NuSEDS"
## [1] "Location Fell is not in NuSEDS"
## [1] "The population of species sockeye at location Goatbushu is not in NuSEDS (location is in NuSEDS)"
## [1] "Location Kill Creek is not in NuSEDS"
## [1] "Location Kill Creek is not in NuSEDS"
## [1] "Location Kill Creek is not in NuSEDS"
## [1] "Location Mosquito Bay is not in NuSEDS"
## [1] "Location Mosquito Bay is not in NuSEDS"
## [1] "Location Mosquito Bay is not in NuSEDS"
## [1] "Location Mosquito Bay is not in NuSEDS"
## [1] "The population of species sockeye at location Sagar is not in NuSEDS (location is in NuSEDS)"
## [1] "Location Troupe North is not in NuSEDS"
## [1] "Location Troupe North is not in NuSEDS"
## [1] "Location Troupe North is not in NuSEDS"
## [1] "Location Troupe North is not in NuSEDS"
## [1] "Location Troupe North is not in NuSEDS"
## [1] "Location Troupe South is not in NuSEDS"
## [1] "Location Troupe South is not in NuSEDS"
## [1] "Location Troupe South is not in NuSEDS"
## [1] "Location Troupe South is not in NuSEDS"
## [1] "Location Troupe South is not in NuSEDS"
As mentioned above, we downgrade the
stream_survey_quality for the counts from the SFU lab for
sockeye and coho:
## [1] "BEFORE:"
## SPECIES ESTIMATE_METHOD source_id stream_survey_quality
## 156783 Coho Peak Live + Dead Reynolds_20260209 Medium-Low
## 298017 Sockeye Peak Live + Dead Reynolds_20260209 Medium-Low
## 1162914 Coho Area Under the Curve Reynolds_20260209 Medium-Low
## [1] "AFTER:"
## SPECIES ESTIMATE_METHOD source_id stream_survey_quality
## 156783 Coho Peak Live + Dead Reynolds_20260209 Low
## 298017 Sockeye Peak Live + Dead Reynolds_20260209 Low
## 1162914 Coho Area Under the Curve Reynolds_20260209 Low4 Export dataset
if(export_datasets){
date <- Sys.Date()
write.csv(nuseds_cuid_streamid_Reynolds,
paste0(wd_output,"/archive/3_nuseds_cuid_streamid_Reynolds_",date,".csv"),
row.names = F)
}END