Like it or not, it’s clear: yearly, India should face down intense warmth waves and erratic but in addition typically intense bursts of rainfall. In a bid to search out as some ways out of the results — or no less than their skill to shock governments — as doable, the nation has turned to synthetic intelligence (AI) for assist with modelling and early warnings.
Traditional weather forecasting makes use of numerical weather prediction (NWP) fashions. Such fashions start with physics equations that simulate atmospheric behaviour utilizing the rules of fluid dynamics and thermodynamics. They course of observational information from weather stations and satellites, together with temperature and wind velocity, and carry out their complicated and time-consuming calculations on supercomputers.
AI-based fashions begin with the information as a substitute. AI algorithms can ‘learn’ the relationships between some inputs and an output — e.g. a given set of wind, temperature, and humidity circumstances on one hand and the formation of a cyclone on the opposite — or extract spatial and temporal patterns from massive datasets. And they do that with out prior information of the underlying earth system processes. This makes AI notably helpful for functions that lack an entire concept.
For instance, an AI mannequin can discover hidden hyperlinks between numerous earth system variables, reminiscent of air temperature, stress and humidity or ocean temperature, salinity, and currents, to uncover cause-effect relationships present physics-based fashions don’t seize. AI fashions can additionally think about a wider vary of enter variables, whereas physics-based fashions use enter variables that specialists have historically thought of to be related.
The Indian authorities joined the brand new worldwide race to construct such fashions when it introduced ‘Mission Mausam’ in September 2024 with an allocation of ₹2,000 crore over two years. Its acknowledged targets are to exponentially improve the nation’s weather and local weather observations and to raised perceive modelling and forecasting for extra correct and well timed providers.
The Mission goals to do that by, inter alia, growing higher earth system fashions and data-driven strategies utilizing AI. The Ministry of Earth Sciences has arrange a devoted AI and machine-learning (ML) centre to develop and take a look at totally different methods and fashions AI to enhance short-range rain forecasts, develop high-resolution city meteorological datasets, and discover these applied sciences for nowcasting rainfall and snow utilizing information from Doppler radars.
Indian researchers are additionally making forays in the usage of AI for weather prediction. For instance, teams on the DST Centre of Excellence in Climate Modelling (CECM) at IIT-Delhi; the Indraprastha Institute of Information Technology, New Delhi; the Massachusetts Institute of Technology within the US; and the Japan Agency for Marine Earth Science and Technology have collectively developed a ML mannequin to foretell monsoon rainfall. The mannequin makes use of information from 1901 to 2001 associated to the Indian summer time monsoon, and accounts for the influences of techniques just like the El Nino (a local weather sample that emerges because of uncommon warming of floor waters within the jap Pacific Ocean) and the Indian Ocean Dipole (IOD).
According to the group, this mannequin performs higher than present bodily fashions to foretell monsoon within the nation, with a forecast success charge of 61.9% for the take a look at interval of 2002-2022. The group mentioned it can additionally predict rains months upfront topic to the provision of El Nino and IOD information; can be up to date based mostly on how the El Nino and IOD information evolve; can higher seize nonlinear relationships within the monsoon drivers’ information; and is much less computationally intensive.
Challenges are solely starting
That mentioned, these are early years and the trail forward is difficult, each in India and overseas.
Weather techniques are inherently nonlinear and chaotic, so refined fashions are required to seize their dynamic nature, IIT-Delhi affiliate professor Tanmoy Chakraborty mentioned. AI fashions particularly require massive, high-quality datasets for the fashions to coach on first. But these datasets are hampered by issues like sensor error, inconsistent codecs, and the information being spatially and temporally inconsistent.
Satish Regonda, affiliate professor within the departments of civil engineering and local weather research at IIT-Hyderabad, mentioned AI/ML fashions usually require massive quantities of information — particularly at finer spatial and temporal resolutions — as a result of as weather processes are dominated by randomness. The extra information there’s, the higher it is to search out indicators of order within the chaos.
Moreover, neither AI fashions nor the specialists that constructed them are typically capable of clarify how they had been capable of make sure predictions. This is why in a February 2025 paper in NatureCommunications, researchers from institutes in France, Germany, Greece, Italy, the Netherlands, and Spain wrote that operational challenges in utilizing AI/ML for weather and local weather prediction embody “the complexity of AI outputs, which hinder interpretation by non-experts.”
The scepticism stems from “the near impossibility of explaining the reasons for good or bad performance,” Regonda added. Traditional weather fashions present an intuitive understanding of the underlying processes by way of their equations, and the framework permits the evaluation of mannequin errors and corrections. Nonetheless, efforts at the moment are in place to develop hybrid approaches by combining AI/ML with physics-based modelling for weather forecasting, in response to Regonda.
The two greater issues
In India, many weather forecasters don’t use or run weather fashions that require excessive computing energy and high-quality information; as a substitute they use the data thus generated from different companies, together with the India Meteorological Department (IMD), the US National Oceanic and Atmospheric Administration (NOAA), the European Center for Medium Weather-range Forecasting (ECMWF), and personal corporations — or a mix of information produced by a number of fashions. Then they overlay their native information, together with motion of clouds and previous eventualities. Regonda mentioned these forecasters competed with one another though, “given the growing interest in AI/ML and as finer resolution data becomes increasingly [better] available, and because of high-intensity and short-duration rainfall events, I think AI/ML models will be used extensively in the near future in India.”
The two principal challenges with the usage of AI/ML for predicting what can be more and more erratic weather are (i) the provision of adequate information and (ii) the suitable human assets, and specialists differ on which of the 2 is an even bigger hurdle.
Saroj Kanta Mishra, a professor at CECM in IIT Delhi and the chief of the group that constructed the monsoon mannequin, mentioned it was human assets, particularly on the interface between AI and predicting weather and local weather. “Climate science is not fundamentally an independent discipline and draws scientists from physics, mathematics, certain engineering branches such as mechanical and civil engineering, and computer science,” in response to Mishra. “It is, however, not common for many scientists from these disciplines to come into climate science as it falls somewhere between core natural sciences or core engineering disciplines.”
“For scientists working on climate science, when one does not have the AI/ML expertise required for climate science, it is like a black box, and very superficial in nature,” he continued. “Similarly, for hardcore data, core AI/ML scientists don’t have an adequate background in climate science. So the scope of doing deep research and making groundbreaking progress is highly unlikely in the present situation.”
Chakraborty agreed. “Many powerful AI models, specifically generative AI models, operate as black boxes, hindering the understanding of prediction mechanisms and limiting trust in their outputs,” he mentioned.
“Black box” right here refers back to the inscrutability of the relationships between an AI mannequin’s inputs and outputs. That is, when an AI mannequin accepts sure inputs and produces a specific output, how the inputs and output are linked shouldn’t be clear.
Critical mass
Climate is a really complicated phenomenon and its prediction in India has been a problem for many years, Mishra added. “The physical systems driving India’s climate are challenging, and AI/ML could solve problems that humans find difficult.”
According to Chakraborty, “India’s diverse topography and climate zones demand regionally tailored models, increasing development complexity.” This is additional compounded by insufficient sensor networks and gaps within the meteorological infrastructure, notably in distant areas. The finish result’s sparse and inconsistent information, resulting in subpar mannequin accuracy.
Further, the Indian monsoon’s complicated dynamics and interannual variability current a big problem for long-range and short-range forecasting, Chakraborty added.
However, Mishra didn’t agree that the paucity of information to be used in AI/ML fashions is a significant drawback “as there has been a 10-fold increase in observational data in India over the years.” The want for extra information and extra computing energy ”is a never-satiable demand” that can’t be achieved in a single day, he added.
Instead, he mentioned India wants — and can attain — is the event of a classy mannequin tailor-made to unravel the nation’s issues. “If we get the right talent together, it can be done in very less time,” Mishra mentioned. “For this, active collaborations between the climate scientists and AI/ML scientists are essential, and that will happen if we can keep them under one roof, for example setting up an institute exclusively for applications of AI/ML with a mission to solve the pressing issues the country is facing today. Such an initiative could bind these experts together and groundbreaking research could be done.”
Chakraborty echoed him and mentioned: “A critical shortage of professionals with expertise in both meteorology and machine learning hinders the development and deployment of advanced models.” This consists of information scientists with a superb understanding of the physics of the environment. While extra information is being collected and higher, there are nonetheless challenges in information accessibility, standardisation, and integration from various sources, he mentioned, particularly of historic information and real-time information.
Modelling a altering future
However, Madhavan Nair Rajeevan, former Secretary of the Ministry of Earth Sciences, expressed perception within the reverse: that human assets and experience in engaged on ML-based weather modelling are usually not challenges per se in India whereas the provision of long-term information of top of the range is.
“We should ensure we compile good, reliable data sets for ML-based applications. But we will need a lot of computing resources with graphics processing unit (GPU)-based computers,” he mentioned. While typical residence computer systems use central processing models (CPUs), computer systems that use GPUs as a substitute are adept at performing a number of computations in parallel, and thus extra highly effective. “In India, we have enough expertise to work with ML for weather-modelling.”
In his tenure on the Ministry, Nair had initiated a centre for excellence in AI/ML on the Indian Institute for Tropical Meteorology (IITM), Pune, and supported a number of analysis tasks for weather and local weather modelling. “Hopefully in the next one to two years, some good results will come out,” he added.
Worldwide as effectively, scientists are attempting to beat challenges in utilizing ML for local weather science. At the 2024 Heidelberg Laureate Forum in Germany, scientists identified that whereas they’ve been capable of apply ML in weather forecasting with good success, they haven’t been in a position to take action so readily to issues in local weather science.
“An ML model trained to predict good weather today is not very useful in a much warmer future world with a different state of the atmosphere,” the discussion board heard. The environment can be chaotic and the ensuing random fluctuations intrude with the typical local weather change sign. Thus, it is simpler to foretell the imply future local weather however modelling its full variability may be very tough.
One notable rising enterprise on this regard is hybrid local weather modelling, during which scientists mix the physics-based local weather fashions that remedy differential equations with the instruments of ML.
AI/ML and excessive weather
For all these challenges, some scientists consider AI/ML fashions can be notably helpful to foretell excessive weather occasions reminiscent of warmth waves, droughts, torrential rainfall, and floods. “AI has emerged as a transformative tool for the detection, forecasting, analysis of extreme events, and generation of worst-case events, and promises advances in attribution studies, explanation, and communication of risk,” the February 2025 paper in Nature Communications learn. It added that the skills of ML, and deep studying particularly, along with laptop imaginative and prescient methods are advancing the detection and localisation of occasions.
That mentioned, “accurately predicting and modeling extreme weather events, e.g. cyclones, heat waves, and cloud bursts, is crucial but challenging due to their localised and rapid development,” Chakraborty mentioned.
The Nature Communications paper additionally expressed warning about challenges in information administration points, reminiscent of dealing with dynamic datasets, biases, and excessive dimensionality, i.e. datasets with a lot of covariate variables, and which render computations in addition to extracting helpful info from the evaluation very tough. AI fashions additionally battle with unclear statistical definitions of what’s “extreme”, the paper famous.
Another problem is “trustworthiness concerns” that come up from the complexity and interpretability of ML fashions, the problem of generalising throughout totally different contexts, and the quantification of uncertainty. Nair agreed, saying, “Though ML is a powerful tool, it should be used carefully, with stringent verification processes.”
T.V. Padma is a science journalist in New Delhi.
Published – April 23, 2025 05:30 am IST
