GOALS
SDG 15
Protect, restore and promote sustainable use of terrestrial ecosystems, sustainably manage forests, combat desertification, and halt and reverse land degradation and halt biodiversity loss.
The proportion of remaining forest area, desertification and species extinction risk are example indicators of this goal.
Developed in collaboration with 
AI has significantly impacted the progress of Sustainable Development Goal 15 (SDG 15), which focuses on protecting, restoring, and promoting sustainable use of terrestrial ecosystems, managing forests sustainably, combating desertification, halting and reversing land degradation, and halting biodiversity loss. Between 2015 and 2023, there have been 203,592 scientific publications exploring the role of AI in these areas. These studies highlight AI’s potential to monitor and manage natural resources more efficiently, analyze vast datasets for biodiversity conservation, and develop strategies to combat land degradation. AI technologies, such as remote sensing and machine learning, are used to track deforestation, assess ecosystem health, and predict the impacts of climate change on terrestrial habitats. Despite relatively low media exposure, with only 3,156 news articles, there is growing awareness of AI’s potential in environmental conservation. Furthermore, the development of 190 AI policies targeting SDG 15 demonstrates a commitment from policymakers to integrate AI into ecosystem management and conservation efforts, ensuring sustainable and resilient terrestrial ecosystems.
Looking ahead, the next 5 to 10 years are expected to see significant advancements in AI applications for terrestrial ecosystem management. AI-driven remote sensing technologies will become more sophisticated, allowing for real-time monitoring of forests and other critical habitats, enhancing efforts to combat illegal logging and poaching. Machine learning algorithms will be increasingly used to analyze complex ecological data, providing insights into species distribution, habitat connectivity, and the impacts of human activities on biodiversity. These advancements will facilitate more effective conservation planning and policy-making. Additionally, AI can support reforestation and land restoration projects by optimizing the selection of plant species and monitoring the progress of restoration efforts. As AI technologies continue to evolve, collaboration between governments, conservation organizations, and the private sector will be essential to ensure that AI-driven innovations are implemented ethically and effectively. This collaborative effort will accelerate progress towards SDG 15, promoting the sustainable use and restoration of terrestrial ecosystems and biodiversity conservation.
Developed in collaboration with the European Commission project 
Developed in collaboration with the European Commission project 
Avoiding data bias in AI systems is crucial to ensure fair, accurate, and equitable outcomes, preventing the reinforcement of existing inequalities and enabling more trustworthy and inclusive technologies. Here you will see a dashboard analysing the bias related to the data ingested in this observatory for SDG 15.
For analysis we use OECD AI Policy documents. Some of those documents are very large, and we split each document into smaller parts (so called “chunks”), which can contain multiple paragraphs. The reason for this is to prepare data for easier analysis with large language models, so called Retrieval-Augmented Generation (RAG). RAG is an advanced technique that combines retrieval-based methods with generative models to improve the performance of tasks such as question answering, text generation, and other natural language processing (NLP) applications. For each chunk then the sentiment is computed based on VADER (Valence Aware Dictionary and sEntiment Reasoner) methodology. Since VADER is known to have weak multilingual capabilities, all the documents were machine translated into English first.
While the results of this procedure are reliant not only upon the accuracy of the sentiment analysis tool, but also upon the accuracy of machine translation, it is important to stress that sentiment analysis is less sensitive to common machine translation problems than other usages, because sentiment analysis usually focuses on identifying the polarity (positive, negative, neutral) of a text rather than understanding its full semantic content. Also, sentiments in text are often expressed redundantly, which can help mitigate the impact of translation errors. As a result, minor translation errors that do not alter the overall sentiment and do not significantly impact the sentiment analysis is possible.
For the purpose of this analysis, they computed the average sentiment of (chunks of) AI policy documents for each country. We are presenting the visualisation of average sentiment of countries’ AI policy documents on the map. Since AI policy documents are mostly documents of legal nature (acts, policies, regulatory and governance frameworks), the sentiment should be mostly neutral, however, the analysis shows that there are country differences.
VADER computes positive, negative and neutral sentiment. Each of those values are between 0 and 1. The score indicates the proportion of text that is considered positive, negative and neutral. The sum of negative, positive, and neutral sentiment scores always equals 1, however in practice the sum of three sentiment scores can sometimes slightly exceed or fall below 1 due to floating-point precision errors or rounding issues that occur during computation.
Developed in collaboration with the European Commission project 
INDICATORS
Key indicators that report on the status of water sustainability will further understanding of this important topic. With this tool, you can utilize drop-down menus and animations to explore the various aspects of and progress towards SDG 1.
The data is sourced from well-established open data providers such as UN Stats and the World Bank, through the SDG Tracker initiative of Our World in Data.
Note that the insight provided by this visualisation is indicative as the data coverage is not always complete for all world countries. Nevertheless, it allows us to provide a signal that can be explored in what regards the multilevel relations between SDG indicators.
This view offers the perspective to SDG 1 Markov Chain analysis of countries including relation between states and overall hierarchy, using Streamstory.ijs.si.
MEDIA
The media room exhibits insight from world and local news, aiming to identify SDG-related events from millions of worldwide multilingual news, and to exhibit best practices towards solving SDG-related problems. This is offered in collaboration with EventRegistry.
The data is provided by the AI news engine Event Registry with whom we collaborate with. Visit eventregistry.org for more visuallisations on worldwide news queries, and to try their News API.
This is done in collaboration with the AI news engine Event Registry in the context of the European Commission-funded project ELIAS – European Lighthouse of AI for Sustainability.
Review the worldwide news, social media posts and forum discussions published on SDG-related topics, using interactive data visualisation that can help better refine the search parameters.
SCIENCE
This perspective is providing the IRCAI user with the access to text-mining tools to improve effectiveness in reviewing a topic over a large dataset of published science and patented technology.
The data is sourced on OpenAlex including more than 128 million articles published worldwide since the 40’s. This provide us with a view of the main SDG topics to take into consideration across time.
Here we observe the relation between the concepts (edges) relevant to the selected SDG and the relations between those concepts, stronger or weaker according to the amount of articles where these are topics in common.
The data is sourced on OpenAlex including more than 128 million articles published worldwide since the 40’s. It was first developed in the context of the European Commission-funded project NAIADES, now extended from the target SDG 6 to all the 17 SDGs.
Review the published research and submitted patents about SDG-related topics, building global knowledge, using interactive data visualisation that can help better refine the search parameters. Use the search bar and the search pointer to explore the available data. Click on the items to access the original data sources.
This is done in collaboration with the Department of Artificial Intelligence of the Institute Jozef Stefan, in the context of the European Commission-funded project RAIDO.
POLICY
The observation of policies applied worldwide on SDGs is fundamental to better understand the progress of the global action. Explore the topics related to the legal and regulatory landscape from open data using sophisticated data analytics and machine learning methods.
The initial policy data is sourced with OECD.AI in the context of the European Commission-funded project AI4GOV.
The initial policy data is sourced with OECD.AI in the context of the European Commission-funded project AI4GOV.
This is done in collaboration with the Department of Artificial Intelligence of the Institute Jozef Stefan, in the context of the European Commission-funded project RAIDO.
EDUCATION
Education is key for progress and sustainability. Explore in this room the educational resources in several SDG-related knowledge domains that can help educational institutions, local governments and companies can leverage the Observatory to best fit the professionals of the future.
The initial datasource includes the UNESCO award-winning MOOC Videolectures.net with over XX recorded and preprocessed lectures on a variety of SDG-related topics.
The initial datasource includes the UNESCO award-winning MOOC Videolectures.net with over XX recorded and preprocessed lectures on a variety of SDG-related topics.
This is done in collaboration with the Department of Artificial Intelligence of the Institute Jozef Stefan, in the context of the European Commission-funded project RAIDO.
INNOVATION
The heart beat of entrepreneurship can be the driver for sustainability. Explore in this room the innovation initiatives, from start-ups to living labs, focusing in several SDG-related topics building an ecosystem of initiatives that will enrich the sustainability-focused industrial landscape.
This visualisation is fed by IRCAI’s Top 100 using sophisticated data analytics and machine learning methods.
The initial data is sourced at IRCAI’s Top100 initiative, depicting the most relevant AI & SDG initiatives during 2022-24.