Digital Intelligence Weekly丨Artificial intelligence makes the weather 'barometer' closer to reality

AI draws a weather “barometer”

Editor’s Note

The World Meteorological Organization (WMO) released data last week (May 17) showing that "the probability that the global annual average temperature will temporarily increase by 1.5 degrees Celsius compared with pre-industrial levels in the next five years reaches 66%." Just now. At the same time that the warning was issued to the world, an artificial intelligence (AI) prediction published in the Proceedings of the National Academy of Sciences of the United States that "global warming will exceed the critical threshold (1.5 degrees Celsius) in 10 to 12 years" once again attracted attention. The argument that "forecast results generated by artificial intelligence are consistent and more accurate than those produced by traditional forecast methods" has triggered a new round of discussion on the relationship between artificial intelligence and traditional weather forecasts.

Shu Zhi Interview

——Interview with Ma Zhuguo, a researcher at the Institute of Atmospheric Physics, Chinese Academy of Sciences

■ China Economic Times reporter Li Hainan

Recently, the news that "the World Meteorological Organization (WMO) announced that the global annual average temperature in the next five years has a 66% chance of temporarily rising 1.5 degrees Celsius compared with pre-industrial levels" has caused people to wonder whether artificial intelligence will affect traditional meteorology. Forecasting methods pose a challenge or even replace the focus on discussion.

Ma Zhuguo, a researcher at the Institute of Atmospheric Physics, Chinese Academy of Sciences, has long been focused on research in the field of climate change. As a climate model expert, he has a deeper understanding of the close relationship between computing power, algorithms and information data processing. From the perspective of an observer, he expressed to the China Economic Times reporter his positive feedback on the current application of artificial intelligence technology in the field of meteorology and climate, including the positive changes brought about by weather forecasting and future application prospects.

"Artificial Intelligence brings improvements in technical methods to weather forecasting"

Ma Zhuguo believes that the WMO’s announcement is intended to serve as a warning. After all, the economic losses and personal safety caused by extreme weather and climate performance cannot be ignored. This is also a major reason why human society has continued to strengthen technical support to improve the accuracy of weather forecasts.

"Everyone is paying attention to improving technical means to achieve higher-accuracy early warnings, and then maximizing the losses caused by extreme weather and meteorological disasters." Ma Zhuguo said, "Artificial intelligence can bring technology and innovation to weather forecasting. Improvement of methods will improve forecast efficiency and accuracy, making more accurate early warning possible."

The application of artificial intelligence in the field of meteorology essentially uses the in-depth integration of big data, high computing power and other technologies with meteorological forecasting to form an intelligent cross-domain, multi-scale, and accurate meteorological system to significantly increase the speed of weather forecasting. Enhance the timeliness of forecasts, and discover complementary patterns and mathematical equations from data.

The technical means used in weather forecasting have experienced rapid iteration and progress. Ma Zhuguo himself has personally experienced the iterative changes from the use of early microcomputers to today's artificial intelligence in the field of climate research. He said that in the early 1980s, a programmable pocket computer, commonly known as the PC-1500, could integrate the experience information and professional data of meteorological analysts to form an indicator reference for forecasting meteorological conditions such as rainfall, hail, and strong winds. .

The technological progress brought about by the passage of more than 40 years is particularly amazing. "Extracting useful and comprehensive information efficiently and accurately from a large amount of information requires increasingly strengthened computing power support. The large model algorithms and high computing power behind artificial intelligence are aimed at improving data information processing capabilities and can quickly extract available information ."He said.

"Limitations are difficult to break through, artificial intelligence is not omnipotent"

The development of new technologies is often difficult to break through its own limitations. Ma Zhuguo believes that even with artificial intelligence technology with big data and high computing power, it can only process "large enough existing information data." He said that using this kind of "past data" to speculate on the future is based on a basic premise: there is a certain correlation and similarity between the development rules of the future and the past. Only then can an algorithm model be formed based on "past data", and then the prediction can be realized. Future predictions. "But predicting the future, there is a lot of unpredictability."

Combined with the recent continued popularity of ChatGPT, Ma Zhuguo gave an intuitive comparison to illustrate the limitations of artificial intelligence. Suppose a user enters the information "2 8=12" into ChatGPT, and it will reply "Incorrect". The user then asks "Is this right?" It will reply "2 8=12 data does not exist in my database, maybe you are right".

"This implicitly reflects that the artificial intelligence represented by this obviously also has certain limitations." Ma Zhuguo believes that the large language model represented by ChatG?PT and the artificial intelligence technology derived from it have the same essential core. Not a creator, but a very skilled information processor and integrator.

"To a certain extent, meteorological and climate predictions also have such problems." Ma Zhuguo said, taking the latest climate model for climate prediction as an example, once the data accuracy in a certain link of the model is insufficient, the results will definitely be affected. causing errors.

Climate models use mathematical methods to simulate weather changes. "Currently, people do not fully understand the process of climate change, because research on certain climate phenomena has to make assumptions, and more accurate models require more observational data." Ma Zhuguo believes that the application of artificial intelligence technology in the field of meteorology includes The substantial improvement in information and data processing capabilities brought about by large computing power and algorithms is worthy of recognition, but it still has limitations.

Just like "no matter how thoroughly you read history books, it is difficult to plan for the future." Ma Zhuguo said that no matter how well meteorologists understand the past climate development patterns, it is difficult to completely accurately predict the weather.

“Artificial intelligence and traditional mainstream forecasting methods promote each other”

In Ma Zhuguo's view, artificial intelligence entering weather forecasting and atmospheric physics application scenarios essentially brings about the integration of big data and other information through computing power and algorithms, and provides more new technical support and models for models. methods, and then improve the accuracy and efficiency of forecasts, "but we cannot expect or simply say that artificial intelligence will replace the traditional mainstream forecasting methods, at least the conditions are not yet met."

Taking the familiar satellite cloud images as an example, Ma Zhuguo explained that in weather forecasting, satellite monitoring is very effective and can intuitively see the trajectory and speed of clouds. Once digital model algorithms are used to replace manual observation, The actual changes brought about are also obvious.

The conventional method for current weather forecasting is to use weather forecasting models for quantitative forecasting. Ma Zhuguo introduced that the model is essentially a mathematical model, which uses the changing motion laws of fluid mechanics to establish a motion equation for atmospheric fluids, and then generates a forecast equation that changes with time. For example, if the weather at this moment is known, the weather conditions in the next time period can be determined based on the equation of motion.

“However, many assumptions must be made during the operation of the equation. This process will result in the selection of data, which will bring certain errors, because only certain assumptions must be made under the conditions of fluid dynamics to make speculations and calculations. Calculation." Ma Zhuguo believes that once big data and artificial intelligence technology are cited and applied, a large amount of data information can be input, and all information that can be digitized, such as the relationship between the movements of satellite clouds, can be statistically input into artificial intelligence. More accurate information will be generated.

Currently, human research in the field of meteorology still has limitations, and more new cognitions rely on scientific research exploration and breakthrough constraints. Ma Zhuguo believes that artificial intelligence-related technology will definitely benefit scientific research and help achieve new scientific results. In the field of meteorology and climate prediction, artificial intelligence and traditional mainstream prediction methods promote each other.

Digital Intelligence Outlook

“AI weather” may become a new blue ocean for business

■ China Economic Times reporter Lin Chunxia

As the core driving force of a new round of technological revolution and industrial transformation, artificial intelligence (AI) is not only a national strategy and a new growth engine, but also the core competitiveness of industry competition. In recent years, while artificial intelligence has improved the accuracy of weather forecasts, it has also made the application of weather data more diversified.

The International Meteorological Organization (WMO) recently released data showing that there is a 66% chance that the global annual average temperature will temporarily rise 1.5 degrees Celsius compared with pre-industrial levels in the next five years. Although this is different in time from previous artificial intelligence predictions, the direction of climate warming is consistent. For a time, the market began a new round of attention to "AI weather".

Weather services actively embrace artificial intelligence

In recent years, my country’s meteorological departments and related enterprises have actively embraced artificial intelligence and continuously explored artificial intelligence meteorological application fields and methods.

For example, the Shenzhen Meteorological Bureau has carried out in-depth cooperation with Huawei Cloud. The two parties have worked together to create a full-field in-depth cooperation model of "Meteorological Cloud AI 5G" to promote breakthrough innovations in accurate weather forecasting for megacities and smart city weather services.

Moji Weather, which has been deeply involved in meteorological services for many years, is also constantly using AI technology to expand the blue ocean market in the meteorological field. Moji Weather started exploring the B-side as early as 2016, exerting commercial value in many fields such as urban construction, transportation services, agricultural meteorology, disaster prevention, etc., and gradually opening up the hundreds of billions of "meteorology" blue ocean market.

Take the transportation industry as an example. Under complex meteorological conditions, the probability of traffic accidents on expressways is very high. The road traffic product portfolio service launched by Moji uses refined data products such as kilometer grid forecast and warning, minute-level short-term Prominent radar, real-time cloud images, typhoon path forecasts, etc. are combined with traffic visual chart analysis to send early warning prompts for dangerous road sections, greatly reducing the incidence of traffic accidents.

The blue ocean of "AI climate services" is in the ascendant, and its prospects are promising. According to the "China Meteorological Industry Development Report", the scale of China's meteorological service industry will reach 300 billion yuan in 2025, with strong subsequent growth potential. Of course, its development potential is based on accurate forecasts.

Huo Zhiguo, a researcher at the Chinese Academy of Meteorological Sciences, said in an interview with a reporter from China Economic Times that with the help of high-tech means such as digital technology and artificial intelligence, weather forecasts are more accurate and refined than in the past.

High accuracy of weather forecasts plays a great role in empowering economic and social development. For example, during agricultural sowing, some targeted measures can be taken based on weather forecasts, and irrigation can be reduced if there is rain. If there is no rain for a long time, some remedial measures such as irrigation can be taken. For another example, disaster forecasts, such as typhoon forecasts, can allow fishermen to return to the harbor in time to take shelter, which can greatly reduce losses.

Exploring the cutting-edge technology position of "weather" services

In 2022, the "Outline for High-Quality Development of Meteorology (2022-2035)" clearly states that "strengthening the deep integration and application of artificial intelligence, big data, quantum computing and meteorology." In the AI ​​era, smart weather has become one of the foundations of China's new digital economic infrastructure.

Jiang Qiping, director of the Information Research Center of the Chinese Academy of Social Sciences, said in an interview with a reporter from China Economic Times that artificial intelligence will play an increasingly important role in services in the future, including the industrial Internet, including applications in various industries, including meteorological applications. . Meteorological applications are large, complex systems. Improving the efficiency of complex systems is exactly what artificial intelligence is good at.

How will artificial intelligence be deeply integrated and applied with meteorology in the future, bringing new changes and new explorations to the field of meteorology?

On May 18, at the Artificial Intelligence Meteorological Application Development Seminar held by the China Meteorological Administration, experts and scholars from universities, scientific research institutes, enterprises, etc., held an in-depth discussion on the theme of "Artificial Intelligence Empowering Meteorology" Discuss new ideas and measures for artificial intelligence meteorological applications.

Zhang Jun, secretary of the Party Committee of Beijing Institute of Technology and academician of the Chinese Academy of Engineering, said at the meeting that artificial intelligence and meteorological work are methodologically similar, and there is huge room for artificial intelligence to help high-quality development of meteorology. Through the in-depth integration of artificial intelligence technology and meteorology, a global intelligent cross-domain, multi-scale, and accurate meteorological system will be established. Artificial intelligence can play a role in sensing, transmission, computing, services and other fields.

Chen Yunji, deputy director and researcher of the Institute of Computing Technology, Chinese Academy of Sciences, believes that the focus of intelligent-based meteorological scientific research is to improve the forecasting capabilities of seasonal forecasts and long-range spatial connection modeling across multiple time scales, so as to This enables accurate forecasting and control of meteorological systems.

Xie Lingxi, a senior researcher at Huawei Cloud Computing Company, pointed out that the entry of artificial intelligence into the field of weather forecasting has brought many new ideas and paths. For example, it can greatly increase the speed of weather forecasting and enhance the timeliness of forecasts. Mining patterns and mathematical equations from data complement each other. The rapid development of new methods will help break the original forecast technology monopoly.

numerical wisdom lecture hall

The focus and direction of artificial intelligence to help mankind cope with climate change

■ Zhou Hongchun

Climate change is a common challenge facing all mankind. Humanity is a passenger on the "ship" of the earth and a community with a shared future. We must work together to address the challenge of climate change.

"Artificial intelligence predicts that the earth's temperature will rise above the 1.5 degree Celsius mark between 2033 and 2035" is still lingering, the World Meteorological Organization (WMO) on "the global annual average temperature in the next five years will increase by 1.5% compared with pre-industrial levels" degree Celsius is 66%; the probability that at least one year from 2023 to 2027 will be the hottest year on record is as high as 98%." The warning is deafening.

Currently, the use of artificial intelligence to help mankind deal with climate change issues is bringing us great opportunities: it can be reflected in the implementation of carbon emission reduction action plans, climate change adaptation, and public understanding.

Artificial intelligence, with the iterative progress of big data models, is increasingly considered to be the next generation of general technology and has become a breakthrough technology in the technological revolution and industrial revolution. Artificial intelligence is having an increasing impact through data analysis, modeling and prediction, as well as optimizing production processes and improving supply chain efficiency and productivity.

In response to climate change, artificial intelligence has broad application space and will play an increasingly important role.

Artificial intelligence can improve the accuracy of weather forecasts. Relevant research shows that 87% of artificial intelligence experts confirm that artificial intelligence will become an effective tool to combat climate change. Specifically, artificial intelligence can play an important role in the following aspects: first, predicting areas with a high probability of floods, droughts, fires and other risks; second, predicting disastrous climate (meteorological events) and issuing early warnings to reduce labor costs; The third is to better allocate water resources to land for different uses within the administrative jurisdiction; the fourth is to choose investment in infrastructure projects such as dams and fire protection projects with better effectiveness.

The "How Artificial Intelligence Can Be a Powerful Tool to Fight Climate Change" report released by the Boston Consulting Group shows that the use of artificial intelligence can help an organization reduce greenhouse gas emissions by 5% to 10%. If expanded globally, it will reduce 2.6 billion to 5.3 billion tons of carbon dioxide equivalent greenhouse gas emissions.

Relevant research shows that artificial intelligence can help humans cope with climate change, including improving energy efficiency, reducing emissions in important areas, public participation, data center energy conservation, and formulating and implementing climate change adaptation plans.

For improving energy efficiency.

In the next 3 to 5 years, artificial intelligence will improve energy efficiency in related fields by 15%. Machine learning can support many aspects from automatic maintenance, to leakage monitoring, to process optimization, facility management, and even power generation and distribution efficiency. Some artificial intelligence tools can predict wind direction 36 hours in advance, thereby optimizing wind farm operations and reducing wind curtailment. Artificial intelligence can select and optimize the development and utilization of renewable energy, link various types of renewable energy power generation nodes, bases and other links to adjust and balance supply and demand.

Industrial manufacturing, transportation, construction, consumer goods, public utilities and other fields can all use artificial intelligence to achieve carbon reduction effects.

The specific approach is to first conduct carbon emission monitoring. Use artificial intelligence data analysis to track the carbon footprint of its own operations, suppliers, users and other value chain links, and supplement missing data to improve the accuracy of monitoring. Through detailed analysis and insights into all aspects of the value chain, AI can improve the efficiency of enterprises in production, transportation and other aspects, reduce carbon emissions and reduce costs. Artificial intelligence can optimize traffic routes and traffic signals, continuously reduce operating emissions, and contribute to mitigating climate change.

In terms of agriculture and carbon sinks, voluntary emission reduction projects such as forestry carbon sinks are an indispensable component of the construction drawings of the carbon peak and carbon neutral roadmap. AI research and computing can also significantly improve crop yields, efficiency and sustainability by analyzing and modeling conditions such as atmospheric temperature, soil, bird migration, and planting, irrigation, pesticide and fertilizer use, and harvesting cycle.

Carbon Footprint and Climate Change Advocacy. Climate change has had a clear impact on the global ecological environment, social and economic systems. "Achieving carbon peak and carbon neutrality is an extensive and profound economic and social systemic change." In response to climate change, artificial intelligence can help people build a platform to track the carbon footprint of individuals and even enterprises, and design targeted countermeasures to reduce carbon emissions in people's daily life such as food, clothing, housing, and transportation, and achieve a more sustainable development. Low energy consumption and carbon emission reduction support the improvement of people's living standards and well-being.

Artificial Intelligence can help develop climate change adaptation plans. For example, countries most vulnerable to the effects of climate change have systematically used artificial intelligence to initiate their adaptation actions; some countries have used artificial intelligence to initiate precise mapping of crop distribution and predict the impact of climate change on crop harvests.

The carbon footprint brought about by the development of computing-intensive technologies such as machine learning cannot be ignored. Therefore, in addition to using renewable energy as much as possible, we should also design general neural networks, artificial intelligence or machine learning models with universal applicability, and use best practices and tools to measure carbon efficiency to reduce carbon emissions. Start small; use the lowest-cost concept to design an AI solution, and iterate, integrate, and improve the solution in a timely manner. Strengthen capacity building, develop enabling technology platforms, and implement new governance models to maximize the benefits of artificial intelligence in carbon emission reduction.

(The author is a researcher at the Development Research Center of the State Council)

The copyright of this public account belongs to China Economic Times. If you reprint or quote the content of this article, you must obtain permission and indicate that it is from China Economic Times.

hot link

●How long will international oil prices continue to fall?

●Hot Topics丨What does "zero breakthrough" mean when forced delisting of A-share convertible bonds

●Green and low-carbon丨What hurdles need to be overcome for new energy vehicles to go to the countryside

● Han DM comes with a new look and the B-class car market is ushering in “tremendous changes”

Director Producer丨 Wang Hui Wang Chengxi

Producer丨Li Piguang Wang Yu Liu Weimin

Chief Editor丨Mao Jinghui Editor丨Gu Yun

【China Economic Times--China Economic News Network http://www.cet.com.cn】

The above is the detailed content of Digital Intelligence Weekly丨Artificial intelligence makes the weather 'barometer' closer to reality. For more information, please follow other related articles on the PHP Chinese website!