Presentation - INTROMET 2025

DETERMINATION OF TREND OF WEATHER PARAMETERS,CLIMATE EXTREMES, ANOMALIES AND FORECASTING OF NEXT YEAR TREND BY AI/ML ANALYSIS.

Research Objective. Key Highlights: Station under analysis ‘Alipore, station code 42807’, period of analysis is 1969 to August 2025. The data is obtained from online data supply platform IMD PUNE. 🌡️ Trends: Analyse over historical years of temperature, precipitation, and sunshine patterns. ⚠️ Extremes: Detect heatwaves, cold spells, and heavy rainfall events. 🔮 Forecasting: Use Model Prophet to predict temperature and precipitation for the next year. 🛠️ Machine Learning Features: Generate advanced features for ML models. 📈 Visuals: Visualization of heat maps, trends, and scatter plots to uncover relationships. 🔗 Comparisons: save derived weather file obtained from analysis for the purpose of comparison with other research area..

1. Descriptive Statistics and Trends Analysis Temperature Trends: Analyse daily, monthly, or annual trends for maximum (TX), minimum (TN), and mean temperatures (TG) over the years. If there is a noticeable warming trend (climate change indicator)? Precipitation Patterns: Identify periods of drought or heavy rainfall (RF) and analyse seasonal and annual averages.

2. Time-Series Analysis Seasonality and Cyclic Patterns: Decompose weather parameters into trend, seasonality, and residuals to understand cyclical changes (e.g., monthly temperature variations). Rolling Averages: Calculate moving averages for temperature or rainfall to smooth out daily fluctuations and identify long-term trends. Anomaly Detection: Detect unusual weather events like heatwaves, cold spells, or sudden increases in precipitation..

3. Correlation and Relationships Analyse relationships between different weather variables: Humidity and Precipitation: Explore the link between humidity (RH) and rainfall (RF) for different seasons..

4. Climate Extremes and Outliers Identify extreme weather events: Heatwaves (e.g., consecutive high TX values) Cold spells (e.g., consecutive low TN values) Heavy rainfall days (RF > threshold) Analyse yearly frequencies of extreme events to assess whether extreme weather is becoming more common..

5. Seasonal Analysis Study seasonal variations in temperature, precipitation, cloud cover, and sunshine. Compare winters, summers, springs, and autumns across years to see if seasonal weather patterns have shifted. Example: Is summer arriving earlier based on rising TG values?.

6. Visualization Line Plots: Visualize trends in temperature, precipitation, and sunshine duration. Heat maps: Show correlations between variables (e.g., TX, TN, Boxplots: Summarize distributions of temperature or precipitation by month or year. Histograms: Understand frequency distributions for variables like temperature. Scatter Plots: Visualize relationships between variables.

7. Forecasting Use time-series forecasting models (like ARIMA or Prophet) to predict future temperature, rainfall, or sunshine hours. Train machine learning models (e.g., regression models) to predict TX, TN, or TG based on variables like humidity (RH), cloud cover (TC).

8. Comparing Climate Change Indicators Compare early years (1979-1999) to recent years (2000-2025) to assess the impact of climate change on: Average temperature (TX, TN, TG) Frequency of extreme weather events Sunshine duration (SSH).

9. Feature Engineering for Machine Learning Various derived parameters thus obtained during feature engineering and python analysis ,such as temperature range, rolling statistics features ,such as rolling mean and standard deviation for 7 days and 30 days window ,lag features for temperature and precipitation for 1,3,7 day ,the cyclical ,seasonal encoding for understanding of cyclical and seasonal nature ,define new feature column with extreme events such as heatwave, cold spells, heavy rainfall ..

Thanks For Watching.