Global CO₂ Emissions: Linear Regression Model Prediction 2030-2039

Given the limitations and uncertainties associated with any predictive model, it’s advisable to treat the predictions as one possible scenario rather than a definitive outcome. However, I would hope for the predictions to be closer to reality than not.

library(ggplot2)

# Load data from CSV file
data <- read.csv("GlobalCO2Emissions.csv")

# Ensure variables are named correctly 
names(data)[names(data) == "Year"] <- "year"  
names(data)[names(data) == "Emissions"] <- "emissions"  

# Fit quadratic model
model <- lm(emissions ~ year + I(year^2), data = data)

# Make predictions for 2030-2039
future_years <- 2030:2039
predictions <- predict(model, newdata = data.frame(year = future_years))

# Create a data frame for historical data
historical_data <- data.frame(year = data$year, emissions = data$emissions, type = "Historical")

# Create a data frame for predicted data
predicted_data <- data.frame(year = future_years, emissions = predictions, type = "Predicted")

# Combine data frames
combined_data <- rbind(historical_data, predicted_data)

# Create the plot
ggplot(combined_data, aes(x = year, y = emissions, color = type)) +
  geom_point() +
  geom_line() +
  labs(title = "Global CO₂ Emissions: Linear Regression Model Prediction 2030-2039",
       x = "Year", y = "Emissions GtCO₂",
       color = "Data Type")