To meet the 2030 Agenda for Sustainable Development, all Sustainable Development Goals (SDGs) must receive adequate and balanced funding. This study applies artificial intelligence to analyze research proposals accepted between 2015 and 2023 in the European Union and the United States, focusing on datasets from the European Research Council and the National Science Foundation, respectively. Despite the growing application of Artificial Intelligence (AI) in various domains, there remains a lack of comprehensive analysis that applies AI to examine funding allocation across SDGs and gender disparities in scientific research. This study addresses this unmet need by using AI to uncover imbalances in funding distribution, offering insights into current funding instruments. We reveal critical coverage disparities across SDGs, with both funding instruments prioritizing SDG 9 (Industry, Innovation, and Infrastructure), highlighting a potential overemphasis on this goal. Additionally, we document pronounced gender imbalances among principal investigators across nearly all SDGs, except for SDG 5 (Gender Equality), in which female researchers are comparatively better represented. Our results indicate an urgent need for more inclusive and balanced approaches to achieve sustainable development, starting with allocation of research funding. By providing a nuanced understanding of funding dynamics and advocating strategic reallocations, this study offers actionable policy design and planning insights to foster a more equitable and comprehensive support system for sustainability-focused research endeavours.

Accurate, reliable and updated information support effective decision-making by reducing uncertainty and enabling informed choices. Multiple crises threaten the sustainability of our societies and pose at risk the planetary boundaries, hence requiring usable and operational knowledge. Natural-language processing tools facilitate data collection, extraction and analysis processes. They expand knowledge utilization capabilities by improving access to reliable sources in shorter time. They also identify patterns of similarities and contrasts across diverse contexts. We apply general and domain-specific large language models (LLMs) to two case studies and we document appropriate uses and shortcomings of these tools for two tasks: classification and sentiment analysis of climate and sustainability documents. We study both statistical and prompt-based methods. In the first case study, we use LLMs to assess whether climate pledges trigger cascade effects in other sustainability dimensions. In the second use case, we use LLMs to identify interactions between the sustainable development goals and detects the direction of their links to frame meaningful policy implications. We find that LLMs are successful at processing, classifying and summarizing heterogeneous text-based data helping practitioners and researchers accessing. LLMs detect strong concerns from emerging economies in addressing food security, water security and urban challenges as primary issues. Developed economies, instead, focus their pledges on the energy transition and climate finance. We also detect and document four main limits along the knowledge production chain: interpretability, external validity, replicability and usability. These risks threaten the usability of findings and can lead to failures in the decision-making process. We recommend risk mitigation strategies to improve transparency and literacy on artificial intelligence (AI) methods applied to complex policy problems. Our work presents a critical but empirically grounded application of LLMs to climate and sustainability questions and suggests avenues to further expand controlled and risk-aware AI-powered computational social sciences.

Assessing the information provided by coproduced climate services is a timely challenge, given the continuously evolving scientific knowledge and its increasing translation to address societal needs. Here, we propose a joint evaluation and verification framework to assess prototype services that provide seasonal forecast information based on the experience from the Horizon 2020 (H2020) Climate forecasts enabled knowledge services (CLARA) project. The quality and value of the forecasts generated by CLARA services were first assessed for five climate services utilizing the Copernicus Climate Change Service seasonal forecasts and responding to knowledge needs from the water resources management, agriculture, and energy production sectors. This joint forecast verification and service evaluation highlights various skills and values across physical variables, services, and sectors, as well as a need to bridge the gap between verification and user-oriented evaluation. We provide lessons learned based on the service developers’ and users’ experience and recommendations to consortia that may want to deploy such verification and evaluation exercises. Last, we formalize a framework for joint verification and evaluation in service development, following a transdisciplinary (from data purveyors to service users) and interdisciplinary chain (climate, hydrology, economics, and decision analysis). SIGNIFICANCE STATEMENT: Tools to communicate climate-related information to users, typically dam managers, irrigation consortia, or energy producers, are fast evolving to answer societal needs. It is crucial to estimate the quality of the provided information, along with economic, environmental, and/or societal gains. Here, we exemplify how to assess information quality and potential gains in five services that provide data and information for hydropower, solar power, irrigation, and water reservoirs in Europe and South America. Based on this work, we recommend 1) service developers to well anticipate such quality and value assessments, due to the number of actors to be involved; 2) flexibility when screening how to quantify quality and gain to account for decision contexts; and 3) sustained funding or collaborating platforms to ensure the iterative coevaluation process.

Background: This study performs an exploratory analysis of current-future sustainability challenges for ocean planning for the regional seas of Catalonia located in the Western Mediterranean (Spain). Methods: To address the challenges we develop an Maritime Spatial Planning (MSP)-oriented geodatabase of maritime activities and deploy three spatial models: 1) an analysis of regional contribution to the 30% protection commitment with Biodiversity Strategy 2030; 2) a spatial Maritime Use Conflict (MUC) analysis to address current and future maritime activities interactions and 3) the StressorGenerator QGIS application to locate current and anticipate future sea areas of highest anthropogenic stress. Results & Conclusions: Results show that the i) study area is one of the most protected sea areas in the Mediterranean (44–51% of sea space protected); ii) anthropogenic stressors are highest in 1–4 nautical miles coastal areas, where maritime activities agglomerate, in the Gulf of Roses and Gulf of Saint Jordi. iii) According to the available datasets commercial fishery is causing highest conflict score inside protected areas. Potential new aquaculture sites are causing highest conflict in Internal Waters and the high potential areas for energy cause comparably low to negligible spatial conflicts with other uses. We discuss the added value of performing regional MSP exercises and define five challenges for regional ocean sustainability, namely: Marine protection beyond percentage, offshore wind energy: a new space demand, crowded coastal areas, multi-level governance of the regional sea and MSP knowledge gaps.

Loss and Damage benefits from the inclusion of Artificial Intelligence systems to support prevention and assessment. As AI research and development is highly dominated by western and private-led powers, the effectiveness of its use is limited for vulnerable countries. We call for an accessible, inclusive and locally-grounded AI to serve the needs of the most vulnerable, support Article 8 of the Paris Agreement and democratise innovation.

Low-carbon finance markets are complex systems of heterogeneous actors operating across the globe. They have diverse investment preferences and risk appetites, and their collective interactions and dynamics shape investment flows into low-carbon assets. Using the case of solar, wind and hydro energy technologies, this chapter explores the complexity in low-carbon finance markets, defined as markets that direct capital flows towards low-carbon technologies, using network approaches to study their structure and dynamics. Identifying key actors and their interactions, and understanding the evolutionary and adaptive processes which shape flows of low-carbon investments will be critical to design effective public finance and policy instruments for accelerating the deployment of low-carbon assets and realizing the climate transition.

Research in sustainability aims at reshaping the way our society functions and has the power to transform existing approaches, tools and models. When engaged in university courses, students are exposed to established concepts. However, the interaction with professors, researchers and fellow colleagues produces novel ideas and contribute to advancements in the knowledge production chain. Rather than integrating accepted disciplinary processes, this interaction leads to transdisciplinary science, meant as the creation of novel conceptual and theoretical framework. Learning from a selected number of students developing their MSc theses as a quasi-natural experiment, this work defines, documents and discusses the path towards transdisciplinarity in sustainability and energy research. First, this work frames transdisciplinary research surveying existing literature on co-production and collaboration. Second, it discusses the complementarities and tensions between different conceptual and empirical models by documenting a 2-h workshop with a selected cohort of students in their final stage of the MSc. Finally, it discusses the implications of co-production and the advantages of interaction and discussion when diverse backgrounds are included in the conversation. This work suggests that both students and members of the academic community benefits from this collaborative process and call the community to include these approaches in the teaching practices.

A timely and well-managed phase-out of bank lending to the fossil fuel sector is critical if Paris climate targets are to remain within reach. Using a systems lens to explore over $7 trillion of syndicated fossil fuel debt, we show that syndicated debt markets are resilient to uncoordinated phase-out scenarios without regulatory limits on banks’ fossil fuel lending. However, with regulation in place, a tipping point emerges as banks sequentially exit the sector and phase-out becomes efficient. The timing of this tipping point depends critically on the stringency of regulatory rules. It is reached sooner in scenarios where systemically important banks lead the phase-out and is delayed without regional coordination, particularly between US, Canadian and Japanese banks.