Biodiversity Conservation: Correlation and prediction of blotching in sharks by environment and frequency of capture
Author
Qiuyang Zhang
Published
January 24, 2025
Title
Biodiversity Conservation: Correlation and prediction of blotching in sharks by environment and frequency of capture
Abstract
The stress response faced by sharks during capture is of great significance to ecological balance and animal welfare.(Skomal, 2011) We aims to explore the effects of environmental factors and physiological indicators on shark stress response during capture by analyzing the blotching phenomenon of Caribbean reef sharks. Using sharks and sharksub datasets respectively, shark research employed methods including Pearson and Spearman correlation analysis, linear regression, random forest, and paired sample t-test to assess the correlation between air temperature and water temperature, the influence of multiple captures on blotching time, and the predictive capacity of blotching time. The results revealed that the relationship between air temperature and water temperature was slightly negatively correlated but not significant; multiple captures significantly extended the duration of the blotching of sharks, indicating that the number of captures had a cumulative effect on the stress response of sharks; also, physiological and environmental indicators could effectively run dual prediction of blotching time. These results offer a uniquely different lens to examine physiological stress responses in sharks following capture.
Is there a correlation between the variables air and water?
library(tidyverse)
Warning: package 'tidyr' was built under R version 4.4.2
Warning: package 'dplyr' was built under R version 4.4.2
── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr 1.1.4 ✔ readr 2.1.5
✔ forcats 1.0.0 ✔ stringr 1.5.1
✔ ggplot2 3.5.1 ✔ tibble 3.2.1
✔ lubridate 1.9.3 ✔ tidyr 1.3.1
✔ purrr 1.0.2
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag() masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(randomForest)
Warning: package 'randomForest' was built under R version 4.4.2
randomForest 4.7-1.2
Type rfNews() to see new features/changes/bug fixes.
Attaching package: 'randomForest'
The following object is masked from 'package:dplyr':
combine
The following object is masked from 'package:ggplot2':
margin
library(neuralnet)
Warning: package 'neuralnet' was built under R version 4.4.2
Attaching package: 'neuralnet'
The following object is masked from 'package:dplyr':
compute
library(caret)
Warning: package 'caret' was built under R version 4.4.2
Loading required package: lattice
Attaching package: 'caret'
The following object is masked from 'package:purrr':
lift
library(survival)
Warning: package 'survival' was built under R version 4.4.2
Attaching package: 'survival'
The following object is masked from 'package:caret':
cluster
'data.frame': 500 obs. of 10 variables:
$ ID : chr "SH001" "SH002" "SH003" "SH004" ...
$ sex : chr "Female" "Female" "Female" "Male" ...
$ blotch: num 37.2 34.5 36.3 35.3 37.4 ...
$ BPM : int 148 158 125 161 138 126 166 135 132 127 ...
$ weight: num 74.7 73.4 71.8 104.6 67.1 ...
$ length: num 187 189 284 171 264 ...
$ air : num 37.7 35.7 34.8 36.2 33.6 ...
$ water : num 23.4 21.4 20.1 21.6 21.8 ...
$ meta : num 64.1 73.7 54.4 86.3 108 ...
$ depth : num 53.2 49.6 49.4 50.3 49 ...
summary(sharks)
ID sex blotch BPM
Length:500 Length:500 Min. :30.78 Min. :119.0
Class :character Class :character 1st Qu.:34.16 1st Qu.:129.0
Mode :character Mode :character Median :35.05 Median :142.0
Mean :35.13 Mean :141.8
3rd Qu.:36.05 3rd Qu.:153.2
Max. :40.08 Max. :166.0
weight length air water
Min. : 65.10 Min. :128.3 Min. :33.00 Min. :20.01
1st Qu.: 75.68 1st Qu.:172.0 1st Qu.:34.42 1st Qu.:21.55
Median : 87.82 Median :211.1 Median :35.43 Median :23.11
Mean : 87.94 Mean :211.0 Mean :35.54 Mean :23.02
3rd Qu.:100.40 3rd Qu.:251.8 3rd Qu.:36.71 3rd Qu.:24.37
Max. :110.94 Max. :291.0 Max. :38.00 Max. :25.99
meta depth
Min. : 50.03 Min. :44.64
1st Qu.: 67.39 1st Qu.:48.90
Median : 82.45 Median :50.14
Mean : 82.04 Mean :50.14
3rd Qu.: 95.97 3rd Qu.:51.35
Max. :112.45 Max. :56.83
str(sharksub)
'data.frame': 50 obs. of 4 variables:
$ ID : chr "SH269" "SH163" "SH008" "SH239" ...
$ sex : chr "Female" "Female" "Female" "Female" ...
$ blotch1: num 36.1 33.4 36.3 35 35.7 ...
$ blotch2: num 37.2 34.4 36.5 36 36.8 ...
summary(sharksub)
ID sex blotch1 blotch2
Length:50 Length:50 Min. :32.49 Min. :33.47
Class :character Class :character 1st Qu.:34.38 1st Qu.:35.31
Mode :character Mode :character Median :34.94 Median :35.94
Mean :35.03 Mean :35.96
3rd Qu.:35.90 3rd Qu.:36.78
Max. :37.07 Max. :38.18
ggplot(sharks, aes(x = air, y = water)) +geom_point(color ="blue", alpha =0.6) +labs(title ="Scatter plot of air temperature and water temperature",x ="AIR TEMP (°C)",y ="WATER TEMP (°C)") +theme_minimal()+theme(axis.text =element_text(size =14),axis.title =element_text(size =14))
ggplot(sharks, aes(x = air, y = water)) +geom_point(color ="blue", alpha =0.6) +geom_smooth(method ="lm", color ="red", se =TRUE) +labs(title ="Linear regression diagram of air temperature and water temperature",x ="AIR TEMP (°C)",y ="WATER TEMP (°C)") +theme_minimal()+theme(axis.text =element_text(size =14),axis.title =element_text(size =14))
`geom_smooth()` using formula = 'y ~ x'
ggplot(sharks, aes(x = air, y = water)) +geom_point(position =position_jitter(width =0.2), size =2,) +geom_smooth(method ="loess", color ="green") +labs(title ="A smooth graph of air temperature and water temperature",x ="AIR TEMP (°C)",y ="WATER TEMP (°C)")+theme_minimal()+theme(axis.text =element_text(size =14),axis.title =element_text(size =14))
`geom_smooth()` using formula = 'y ~ x'
set.seed(123)train_index <-createDataPartition(sharks$water, p =0.8, list =FALSE)train_data <- sharks[train_index, ]test_data <- sharks[-train_index, ]rf_model <-randomForest(water ~ air, data = train_data, ntree =500, importance =TRUE)print(rf_model)
Call:
randomForest(formula = water ~ air, data = train_data, ntree = 500, importance = TRUE)
Type of random forest: regression
Number of trees: 500
No. of variables tried at each split: 1
Mean of squared residuals: 3.600593
% Var explained: -30.09
Paired t-test
data: sharksub$blotch1 and sharksub$blotch2
t = -17.39, df = 49, p-value < 2.2e-16
alternative hypothesis: true mean difference is not equal to 0
95 percent confidence interval:
-1.037176 -0.822301
sample estimates:
mean difference
-0.9297384
Wilcoxon signed rank test with continuity correction
data: sharksub$blotch1 and sharksub$blotch2
V = 12, p-value = 1.606e-09
alternative hypothesis: true location shift is not equal to 0
'data.frame': 500 obs. of 10 variables:
$ ID : chr "SH001" "SH002" "SH003" "SH004" ...
$ sex : chr "Female" "Female" "Female" "Male" ...
$ blotch: num 37.2 34.5 36.3 35.3 37.4 ...
$ BPM : int 148 158 125 161 138 126 166 135 132 127 ...
$ weight: num 74.7 73.4 71.8 104.6 67.1 ...
$ length: num 187 189 284 171 264 ...
$ air : num 37.7 35.7 34.8 36.2 33.6 ...
$ water : num 23.4 21.4 20.1 21.6 21.8 ...
$ meta : num 64.1 73.7 54.4 86.3 108 ...
$ depth : num 53.2 49.6 49.4 50.3 49 ...
summary(shark_data)
ID sex blotch BPM
Length:500 Length:500 Min. :30.78 Min. :119.0
Class :character Class :character 1st Qu.:34.16 1st Qu.:129.0
Mode :character Mode :character Median :35.05 Median :142.0
Mean :35.13 Mean :141.8
3rd Qu.:36.05 3rd Qu.:153.2
Max. :40.08 Max. :166.0
weight length air water
Min. : 65.10 Min. :128.3 Min. :33.00 Min. :20.01
1st Qu.: 75.68 1st Qu.:172.0 1st Qu.:34.42 1st Qu.:21.55
Median : 87.82 Median :211.1 Median :35.43 Median :23.11
Mean : 87.94 Mean :211.0 Mean :35.54 Mean :23.02
3rd Qu.:100.40 3rd Qu.:251.8 3rd Qu.:36.71 3rd Qu.:24.37
Max. :110.94 Max. :291.0 Max. :38.00 Max. :25.99
meta depth
Min. : 50.03 Min. :44.64
1st Qu.: 67.39 1st Qu.:48.90
Median : 82.45 Median :50.14
Mean : 82.04 Mean :50.14
3rd Qu.: 95.97 3rd Qu.:51.35
Max. :112.45 Max. :56.83
shark_data <-na.omit(shark_data)set.seed(123) train_index <-createDataPartition(shark_data$blotch, p =0.8, list =FALSE)train_data <- shark_data[train_index, ]test_data <- shark_data[-train_index, ]cat("Training data rows:", nrow(train_data), "\n")
Training data rows: 400
cat("Testing data rows:", nrow(test_data), "\n")
Testing data rows: 100
lm_model <-lm(blotch ~ BPM + weight + length + air + water + meta + depth + sex, data = train_data)summary(lm_model)
Call:
lm(formula = blotch ~ BPM + weight + length + air + water + meta +
depth + sex, data = train_data)
Residuals:
Min 1Q Median 3Q Max
-2.83160 -0.65735 -0.03399 0.65674 2.84243
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 10.3242015 2.0482091 5.041 7.11e-07 ***
BPM -0.0008375 0.0034588 -0.242 0.8088
weight -0.0010884 0.0036394 -0.299 0.7650
length 0.0018266 0.0010588 1.725 0.0853 .
air -0.0130284 0.0349766 -0.372 0.7097
water 0.0136424 0.0289796 0.471 0.6381
meta -0.0015427 0.0029479 -0.523 0.6010
depth 0.4944716 0.0244901 20.191 < 2e-16 ***
sexMale 0.1869687 0.0985288 1.898 0.0585 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.9804 on 391 degrees of freedom
Multiple R-squared: 0.516, Adjusted R-squared: 0.506
F-statistic: 52.1 on 8 and 391 DF, p-value: < 2.2e-16
rf_model <-randomForest(blotch ~ BPM + weight + length + air + water + meta + depth + sex, data = train_data, ntree =500)print(rf_model)
Call:
randomForest(formula = blotch ~ BPM + weight + length + air + water + meta + depth + sex, data = train_data, ntree = 500)
Type of random forest: regression
Number of trees: 500
No. of variables tried at each split: 2
Mean of squared residuals: 1.099551
% Var explained: 43.35
