Big data and environment
Green data: Can statistics help the environment?
The application of big data to curb global warming and protect the environment is known as green data. This technology can help optimise the efficiency of the energy sector, make businesses more sustainable and create smart cities, among others.
Life in the 21st century is codified in the form of numbers, keywords and algorithms: a chaotic universe of ever-expanding data. Big data is the set of technologies created to store, analyse and manage this bulk data, a macro-tool created to identify patterns in the chaos of this explosion in information in order to design smart solutions.
Today, big data is used in areas as diverse as medicine, agriculture, gambling and environmental protection.
Big data and the environment
Climate change is the greatest challenge we face as a species and environmental big data is helping us to understand all its complex interrelationships. The application of big data to curb global warming is what is known as green data.
Europe has different green data generating models and one of them is Copernicus. It is a satellite-based Earth observation program capable of calculating, among other things, the influence of rising temperatures on river flows. Copernicus is already providing key information to optimise water resource management, biodiversity, air quality, fishing and agriculture. In recent years green data has evolved thanks to advances in AI, which enables analysts to examine environmental data with greater speed, accuracy and predictive power.
Other international projects that use green data to combat climate change include:
-
Aqueduct
Measures water-related hazards by analysing water quality and quantity and makes interactive risk maps available to the public. It has been deployed globally, with strategic partners in countries such as Sweden and the Netherlands and is used by businesses and supply chains that depend on water as well as in public policies on water management and spatial planning.
-
Global Forest Change
Calculates deforestation by counting trees one by one using high-resolution satellite imagery. It has been used in global studies of forest-cover change and in monitoring tools such as Global Forest Watch, and governments, journalists and researchers utilise it.
-
Danger Map
Determines pollution levels using data provided by millions of citizens. It has been used primarily in China, with the aim of improving air quality, and in cities such as Patna and Gurgaon in India.
Big data and renewable energy
Using big data can strengthen the competitiveness of renewable energies in relation to fossil fuels. Let's look at some of the contributions environmental big data is making to different clean technologies:
-
Wind power
The use of complex algorithms to build predictive models of wind conditions helps to determine the amount of energy that will be generated.
-
Photovoltaic energy
Big data optimises the efficiency of power stations by enabling them to adapt to current light levels.
-
Hydroelectric power
The management of large volumes of data can help, among other advances, to prevent leaks at power stations and to achieve greater control over water flows.
Consumers in the renewables' sector will also benefit from this information revolution. On the one hand, the connection of data from smart meters with weather forecasts will make it possible to adjust demand in real time, favouring the creation of fully customised tariffs. On the other hand, the Internet of Things will make it possible to reduce energy consumption, for example, by adapting lighting and ambient temperature or the consumption of certain household appliances to each and every need.
El “Green Data”, Un aliado para el desarrollo sostenible
- El Green Data
- Contra el cambio climático
- Centrales sostenibles
- Energía eólica
- Consumo energético
- Tarifas personalizadas
- Agricultura sostenible
- Gestión inteligente de residuos
- Economía circular
- Alerta en los océanos
- Calidad del agua
- Sin fugas en las hidroeléctricas
El Green Data
Contra el cambio climático
Facilitará el análisis del consumo instantáneo del agua, las emisiones de CO₂, etc.
Centrales sostenibles
Favorecerá su máximo aprovechamiento con el control de la intensidad lumínica y las circunstancias medioambientales.
Energía eólica
Ayudará a predecir con mayor precisión la producción de generación.
Consumo energético
Ayudará a reducir el 20% del consumo energético de los edificios.
Tarifas personalizadas
Permitirá ajustar la demanda de electricidad de cada cliente.
Agricultura sostenible
Mejorará el rendimiento de las cosechas a través del estudio de las semillas y la meteorología.
Gestión inteligente de los residuos
Optimizará la recuperación y el reciclaje de los residuos a través de la centralización de los datos.
Economía circular
Encontrará modelos más productivos que favorezcan el desarrollo de entornos más saludables y sostenibles.
Alertas en los océanos
Permitirá anticiparse a los tsunamis gracias a la monitorización en tiempo real de la actividad oceánica.
Calidad del agua
Facilitará la marcación de las zonas aptas para el consumo.
Sin fugas en las hidroeléctricas
Reducirá los costes de instalación y realizará diagnósticos inteligentes.
Big data and smart cities
The UN states that by 2030 two-thirds of the world's population will be concentrated in large cities, doubling the urban population in developing countries. Currently more than half of the world's eight billion people already live in urban areas, and the number of megacities (with more than 10 million inhabitants) is expected to rise from 33 to 43 by 2030.
This reality poses critical environmental challenges: increased energy consumption, rising carbon emissions, pressure on water resources and the massive generation of waste. These issues have made green data a powerful tool for adapting to this new global era and, in turn, for trying to mitigate pollution.
Among the initiatives using big data analysis to create smarter and more sustainable cities, the following stand out:
-
Waste management
Such as the Trash Track project, which involves fitting rubbish bins with GPS sensors to better understand recycling routes. It has been trialled in cities such as New York and Seattle to track the journey of the city's waste.
-
Smart mobility
The use of data to achieve more sustainable mobility is now a reality thanks to the AllAboard system, which is capable of optimising public transport planning using mobile phone location data. Since its launch on 1 December 2021, the app has been used by more than 130 users in over 1,500 instances across the United States, Canada, Germany and the United Kingdom.
-
Climate risk prevention
Thanks to the Crisis Mappers Net community, it is possible to analyse data from different sources (satellite imagery, geospatial platforms, simulators, etc.) to issue warnings about natural disasters and facilitate a rapid response. This technology was used during Typhoon Haiyan in 2013 in the Philippines by the Digital Humanitarian Network (DHN).
-
Improving air quality
AI-powered models can monitor and predict air quality in real time, enabling targeted traffic restrictions before pollution reaches its peak. Countries such as China are already using this to measure their pollution peaks.
Big data: towards responsible data use
Due to their activity, companies are one of the agents that produce the greatest negative impact on the environment. Since the turn of the millennium, companies' sustainability reports - published within the framework of the annual report - have been providing details on the strategies and actions they are implementing to minimise this impact. In recent years, green data has been contributing to making companies more sustainable by allowing them to:
-
Efficient use of resources
Through processes such as optimising energy management.
-
Emissions mitigation
Reducing carbon dioxide emissions from production and vehicle fleets by optimising routes.
-
Monitoring
Anticipating the repair and replacement needs of machinery monitored via sensors.
Artificial Intelligence and its contribution to the environment
Advances in Artificial Intelligence (AI) have meant that its contribution to sustainability has grown steadily over the years. However, there are two sides to this that are worth mentioning. On the one hand it enables the processing of large volumes of data to detect pollution, anticipate climate risks and improve the use of natural resources; on the other hand, its growth also increases demand for energy, which may at the same time lead to an increase in carbon emissions if this demand is not met by renewable sources.
Despite this, it is now a crucial tool for the development of various sectors. UNESCO summarises AI's three main contributions to sustainability as follows: making sense of ecological complexity, helping consumers adopt more sustainable habits and reducing the environmental footprint by promoting circularity.
One example of these contributions is its usefulness in sectors such as agriculture, where this technology enables more efficient water use, with automated irrigation systems and a higher level of analysis. Another benefit is the ability to analyse data from satellites, urban sensors and climate models to measure air quality, snowmelt, deforestation or changes in ecosystems with much greater precision than before. This is useful for detecting patterns that would be difficult to spot manually and for improving climate resilience in the face of fires, extreme weather events or pollution hotspots.
However, this technological advance is not without its challenges. According to a new study by the United Nations University (UNU), water consumption linked to AI could equal the basic annual domestic needs of 1.3 billion people by the end of the decade. Added to this is the fact that, according to UNESCO, solutions considered "green" in one sense may cause other problems, particularly in regions already facing resource shortages. For example, the shift towards certain renewable energy sources may reduce carbon emissions but it may also significantly increase water consumption and land use.
In light of this situation one of the key solutions lies in promoting resilient AI: a transition towards smaller, specialised and more resource-efficient systems, which, according to UNESCO, can reduce AI's energy consumption by up to 90% without sacrificing performance.
Challenges in the use of data and AI
With the rise of AI across all sectors of the economy the drive for sustainable and effective solutions has never been more pressing. However, there are new challenges that still need to be overcome. One of the main challenges is the energy consumption of the data centres that support this technology: according to the International Energy Agency, data centres accounted for around 1.5% of global electricity consumption in 2024, and this figure could triple by 2035. Added to this is the water footprint associated with cooling these facilities, which consumes millions of litres of water and has a direct impact on water resources in the countries where they are located.
Another challenge is data privacy and governance. Organisations such as UNESCO point out that the development of AI must be underpinned by an ethical framework regarding the responsible use of data to mitigate the risks of misinformation, disinformation and hate speech as well as the harm caused by the misuse of personal data.
Furthermore, the complex and resource-inefficient infrastructure poses a problem in the drive to reduce the carbon footprint. But according to a study published by UNESCO in 2025, smaller AI models are just as intelligent and accurate as larger ones, and can reduce energy consumption by up to 90%. This, combined with the use of clean energy to meet the energy demands of data centres, can make AI a more sustainable technology, reducing reliance on imported energy or fossil fuels.
Iberdrola's commitment to AI
The advent of AI in the electricity sector is now a reality. This technology has made networks more efficient, safer and more sustainable. Thanks to AI, companies can anticipate problems, optimise the use of resources and ensure that electricity is supplied in the most reliable and cost-effective way. Furthermore, it is a useful tool in the global fight against climate change, as it helps us adapt to its impacts, such as anticipating the risks arising from natural disasters, optimising electricity systems, improving energy efficiency and facilitating the large-scale integration of renewable energy.
The solutions and innovations provided by this technology are key to the Iberdrola Group's objective of reducing its carbon emissions, as they enable us to supply electricity to a greater number of people without the need to build new infrastructure. Furthermore, by analysing satellite imagery and sensor data, AI algorithms help to identify priority areas for electrification and to design microgrids tailored to local needs, playing a vital role in ensuring access to energy.
What’s more, we are working with a wide range of AI and technology start-ups through various open collaboration initiatives such as the Global Smart Grids Innovation Hub, which functions as a large ecosystem focused on creating technology to help make the Spanish electricity system one of the most advanced in Europe and the world by promoting disruptive projects that combine AI, big data, cloud computing and other technologies to improve grid management.