Lære Time Series Analysis in Environmental Science | Modeling and Predicting Environmental Phenomena

Time series data plays a central role in environmental science, as many environmental variables are recorded over regular intervals. Examples include daily rainfall amounts, hourly air pollution readings, or monthly average temperatures. Analyzing these time series helps you understand how environmental conditions change over time, detect patterns, and make forecasts. However, time series analysis comes with challenges:

Environmental data often show strong seasonality (such as higher rainfall in certain months);
Trends (like gradual warming);
Can include missing values, outliers, or sudden events due to natural variability.

Understanding these challenges is essential for effective analysis and accurate predictions.


              123456789101112131415161718
            
import pandas as pd
import matplotlib.pyplot as plt

# Sample daily rainfall data for two weeks
data = {
    "date": pd.date_range(start="2024-06-01", periods=14, freq="D"),
    "rainfall": [0.0, 2.1, 0.5, 0.0, 5.2, 3.3, 0.0, 0.0, 1.8, 0.0, 4.0, 0.0, 2.5, 0.0]
}
df = pd.DataFrame(data)

plt.figure(figsize=(10, 4))
plt.plot(df["date"], df["rainfall"], marker="o", linestyle="-", color="b")
plt.title("Daily Rainfall (mm)")
plt.xlabel("Date")
plt.ylabel("Rainfall (mm)")
plt.grid(True)
plt.tight_layout()
plt.show()

When you examine a time series plot like the daily rainfall above, you are looking for patterns that can give insight into environmental processes. Two of the most important features to identify are trends and seasonality. A trend is a long-term increase or decrease in the data, such as a gradual rise in average temperatures. Seasonality refers to repeating patterns at regular intervals, such as more rainfall during certain months or higher ozone levels in summer. Distinguishing these features helps you understand underlying processes and prepares the data for forecasting.


              12345678910111213
            
# Calculate a 3-day moving average to smooth the rainfall data
df["rainfall_ma3"] = df["rainfall"].rolling(3).mean()

plt.figure(figsize=(10, 4))
plt.plot(df["date"], df["rainfall"], marker="o", linestyle="-", color="b", label="Daily Rainfall")
plt.plot(df["date"], df["rainfall_ma3"], marker="s", linestyle="--", color="orange", label="3-Day Moving Average")
plt.title("Daily Rainfall with 3-Day Moving Average")
plt.xlabel("Date")
plt.ylabel("Rainfall (mm)")
plt.legend()
plt.grid(True)
plt.tight_layout()
plt.show()

1. What is a moving average and why is it useful in time series analysis?

2. How can seasonality be detected in environmental time series data?

3. Fill in the blank: To calculate a 7-day moving average in pandas, use df['rainfall'].rolling(7).____().

Var alt klart?

Tak for dine kommentarer!

Sektion 3. Kapitel 4

Spørg AI

Spørg om hvad som helst eller prøv et af de foreslåede spørgsmål for at starte vores chat

Stryg for at vise menuen

Environmental data often show strong seasonality (such as higher rainfall in certain months);
Trends (like gradual warming);
Can include missing values, outliers, or sudden events due to natural variability.