Context: As weather patterns grow more unpredictable due to the climate crisis, India has launched Mission Mausam to improve weather understanding and forecasting through expanded observation networks, better modelling and advanced tools like AI and machine learning.
Relevance of the topic:
Prelims: Key facts about Mission Mausam.
Mains: Applications of AI: Weather Forecasting.
Mission Mausam
- Launched in 2024 with a budget of Rs 2000 crores over two years.
- Aim: To improve weather and climate services, and forecast information for multiple sectors, including agriculture, disaster management, and rural development. The long-term goal is to make India weather-ready and climate-smart.
- Initiative by: Ministry of Earth Sciences
Objectives of Mission Mausam:
- Strengthening observations (in-situ & remote sensing) networks with advanced radars, satellites, and automated weather stations.
- Improve Model/ Data Assimilation/ HPC for giving accurate information to the Public and stakeholders (Numerical + Artificial Intelligence and Machine Learning).
- Enhance India's capability in weather forecasting across various scales — short-term, medium-term, extended-range, and seasonal.
- Provide actionable advisories for agriculture, water resources, energy, health, and disaster management sectors.
Mission Mausam Implementation Strategy
Mission Mausam adopts a multi-pronged approach to achieve its objectives:
- Infrastructure Development: Installation of Doppler Weather Radars, Automatic Weather Stations, and rain gauges across the country.
- Supercomputing Power: Leveraging high-performance computing systems like Pratyush and Mihir for advanced climate modelling.
- Collaborative Research: Partnerships with global organisations like the World Meteorological Organisation to enhance forecasting techniques.
- Public Outreach: Dissemination of user-friendly advisories through mobile apps (E.g., Mausam App), SMS services, and Media channels.
Implementation Phases:
- The five-year mission would be implemented in two phases.
- First phase (until March 2026): Focus on expanding the observation network. This includes adding around 70 Doppler radars, high-performance computers and setting up 10 wind profilers and 10 radiometers.
- Second phase: Focus on adding satellites and aircraft to further enhance observational capabilities.
Cloud Chamber:
- Under the mission, a cloud chamber will be established at the Indian Institute of Meteorology (IITM) in Pune, within the next one and a half years.
- Aim: To study the processes occurring within clouds in the context of rising temperatures.
Working:
- Artificial clouds will be created inside a laboratory at the IITM and conduct experiments. This will help the scientists better understand:
- which types of clouds can be seeded (a process where substances are added to clouds to make them produce rain)
- what materials should be used for seeding
- how much seeding is needed to either increase rain or even prevent rain.
- Rising temperatures lead to clouds becoming taller and more electrically active, while their horizontal spread may shrink. This can result in stronger thunderstorms and more frequent lightning events and impact rainfall dynamics. The insights gained from the cloud chamber will help improve the parameterisation of weather models and help to artificially enhance or suppress rain and hail within the next five years.
Mission Mausam envisages augmenting the entire observational network (surface as well as upper-air), numerical modelling framework, incorporating AI/ML techniques, enhancing the computing power to mitigate the impact of climate change-induced extreme weather events. "Mausam GPT" is being designed to provide quick and reliable weather-related information in both text and audio forms.
Traditional vs AI-based Weather Forecasting
- Traditional Weather Forecasting: These models simulate atmospheric processes using equations and data from weather stations and satellites (E.g., temperature, wind). These models are computationally intensive, time-consuming, and sometimes limited in capturing localised phenomena due to the chaotic and non-linear nature of weather systems.
- AI-Based Forecasting: Unlike traditional models, AI/ML techniques adopt a data-first approach. They learn from historical and real-time data, identifying correlations between input variables (E.g., wind, humidity, ocean temperature) and outcomes (E.g., rainfall, cyclones). AI can uncover hidden patterns and non-linear relationships not captured by physics-based models.
Challenges in AI-based Weather Forecasting:
- Data Quality and Availability: AI models need large, consistent, and high-quality datasets. Issues like sensor errors, inconsistent formats, and lack of real-time or historical data complicate training. While data availability has improved tenfold but gaps remain in sensor networks, especially in remote areas.
- Human Resource Gap: A critical shortage of experts skilled in both climate science and AI/ML.
- Interpretability and Trust: AI models are like black boxes - it is hard to explain why they make a certain prediction. This makes it difficult for non-experts to trust or verify the results.
- Infrastructure and Computation: AI models, especially for high-resolution forecasting, require GPU-based computing and significant infrastructure investment.
To bridge the gaps, scientists are increasingly turning towards hybrid models that combine the interpretability of physics-based models and adaptability of AI/ML.