The purpose of the MANILA24 Workshop on information retrieval for climate impact was to bring together researchers from academia, industry, governments, and NGOs to identify and discuss core research problems in information retrieval to assess climate change impacts. The workshop aimed to foster collaboration by bringing communities together that have so far not been very well connected -- information retrieval, natural language processing, systematic reviews, impact assessments, and climate science. The workshop brought together a diverse set of researchers and practitioners interested in contributing to the development of a technical research agenda for information retrieval to assess climate change impacts.

UNESCO World Heritage (WH) properties are increasingly vulnerable to challenges caused by climate change, which requires them to balance the needs of heritage management with sustainable urban growth and climate change adaptation (CCA). CCA strategies are being developed by stakeholders at all levels. It is, however, not customary to generalise strategies developed in one property to another, since they are assumed to be highly localised. This paper takes the WH properties in the Netherlands as an example and showcases that topics relevant to CCA, such as climate change challenges and water management strategies, are being shared among properties in their heritage management plans, aiming to safeguard their Outstanding Universal Value. Sentence embeddings computed with cutting-edge Natural Language Processing models are used to retrieve similar topics among the properties and evaluate their associations. Common challenges (such as low groundwater level) and strategies (such as coastal dunes and dykes) are found to be mentioned in different properties. The methodological framework proposed in this paper, bridging CCA with WH management, can be repeated in other countries, and eventually at the global level, providing a generalisable integrated knowledge system beneficial and easily applicable in heritage properties from broad geographical and cultural contexts.

Diasporic communities and their heritage are vital in shaping cultural diversity in urban planning and management. However, diasporic heritage management overlooked cross-geographical networks that constitute cultural significance. This study develops a workflow to explore diasporic heritage’s spatial and semantic networks. Global social media data about Chinatowns on Flickr is collected and analysed through Named Entity Recognition, and Spatial and Semantic Network Analysis. Findings reveal the diasporic flows based on places frequently recognised as origin and destination of Chinese diasporic heritage, and the distribution of places, zooming in from worldwide to the Netherlands. Semantic networks in different Dutch cities are compared.

Sea level rise (SLR) is a global concern under climate change. Understanding how SLR is discussed, depicted, and framed helps urban management and public governance make more informed decisions towards climate actions and communicate more effectively. A multimodal dataset of tweets containing visuals and texts is collected, mapped, and analysed with multimodal topic modelling. It shows that SLR discussion mainly concentrates on coastal cities from the West and that complex themes are brought to the spotlight, including but not limited to risks, actions, and doubtful objections. The framework can be extended for other climate impacts, informative for climate-responsive urban management.

The purpose of the MANILA24 Workshop on information retrieval for climate impact was to bring together researchers from academia, industry, governments, and NGOs to identify and discuss core research problems in information retrieval to assess climate change impacts. The workshop aimed to foster collaboration by bringing communities together that have so far not been very well connected - information retrieval, natural language processing, systematic reviews, impact assessments, and climate science. The workshop brought together a diverse set of researchers and practitioners interested in contributing to the development of a technical research agenda for information retrieval to assess climate change impacts.

The concept of historic gardens has gradually expanded to encompass a broader range of landscape meanings. UNESCO's cultural landscape categories have significantly influenced land policy improvements in the context of globalization, with historic gardens being classified as Category 1 cultural landscapes. The other categories are organically evolved landscapes (Category 2) and associative cultural landscapes (Category 3). While existing studies have primarily focused on each of these categories individually, it remains unclear how to characterize a cultural landscape when all three categories coexist and influence each other, as seen in complex cases such as the Chengde Mountain Resort (CMR). Furthermore, strategies for improving sustainable land management based on this understanding are still lacking. This study uses landscape mapping to collect data, digitally reconstruct, and characterize cultural landscapes in the CMR based on four environmental factors: topography, accessibility, visibility, and land use changes. Based on this, we illustrate the evolution of the CMR through reconstruction, capturing four phases detailed in 144 scenes. From this, we identify six distinct groups of scenes with six targeted indicators, each reflecting specific spatial attributes of Category 1. Additionally, statistical and comparative analyses of land use changes illuminate various landscape dynamics of these scenes that correspond to Categories 2 and 3. The discussion presents a systematic sustainable pathway to characterize the interdependencies among UNESCO’s three cultural landscape categories. Based on these findings, this research proposes a three-level management model that connects dynamic authenticity and modern functionality, offering insights for urban policymakers navigating pluralistic cultural landscapes.

Climate change adaptation occurs within a complex interplay of science, media, politics, policy, and the public. Using comparative longitudinal data (2012–2021) from online newspaper articles, parliamentary debates, policy documents, and social media, we analyze agenda-setting dynamics in the United Kingdom and the Netherlands. Vector autoregression models, incorporating scientific output as an exogenous variable, reveal traditional agenda-setting effects in both countries. In the Netherlands, however, social media positively influences traditional media, while in the United Kingdom, traditional media negatively affects social media. These findings enrich our understanding of the factors shaping public awareness and policy responses to this critical global issue.

The Netherlands has established climate-adaptive strategies shaped by its long history of water-related climate events, such as the floods in 1421 and 1953. UNESCO World Heritage (WH) properties in The Netherlands reflect centuries of human intervention and natural processes to adapt and mitigate climate challenges, including spatial design and hydraulic engineering. The Dutch Climate Research Initiative also highlights cultural heritage as an integral component in preparing for the 2026 National Climate Adaptation Strategy. This article aims to unveil climate-adaptive World Heritage management strategies (CAWHMSs), using WH properties in The Netherlands as a case study. It collects textual data from Statements of Outstanding Universal Value, State of Conservation Reports by the State Parties and management plans. Through qualitative coding and keywords aggregation of the documents, the visualised results of a Sankey diagram and two semantic networks confirmed two CAWHMSs: conservation and developing WH properties as collaborative knowledge hubs. Conservation supports regulating urban climate and sustainable water management. As collaborative knowledge hubs, multidisciplinary sectors explore opportunities to align WH properties with broader sustainable development initiatives. They also deepen younger generations’ awareness of cultural and natural significance relevant to mitigating climate threats. The results emphasise WH as a contributor to climate adaptation. Cross-sectoral stakeholders can advance holistic climate adaptation efforts using CAWHMSs.

We propose a mathematical framework for developing social-choice games that are designed to mediate decision-making processes for city planning, urban area redevelopment, and architectural configuration of urban housing complexes. The proposed framework features a digital serious gaming approach for participatory design to support transparency and inclusion in the process of decision-making and ensure an equitable balance of sustainable development goals in spatial design outcomes. The mathematical process consists of a Markovian design machine for balancing the design decisions of actors, a massing configurator equipped with fuzzy logic and multi-criteria decision analysis, algebraic graph-theoretical accessibility evaluators, and automated solar-climatic evaluators using geospatial computational geometry. We demonstrate the effectiveness of the framework by implementing a multi-player online game that facilitates a participatory decision-making workshop for forming multi-functional building complexes by providing a generative configurator equipped with automated appraisal/scoring mechanisms for revealing the aggregate impact of alternatives. The EquiCity game empowers a group of decision-makers to reach a fair consensual spatial design by mathematically simulating many rounds of reasonable trade-offs between their decisions, with different levels of interest or control over various types of investments. The novelty of the framework is in its capability to encompass decision-making about the most idiosyncratic aspects of a site related to its heritage status and cultural significance to the most generic aspects such as balancing access to sunlight for the site while respecting ‘the right to sunlight’ of the neighbours of the site, ensuring coherence of the entire configuration with regards to a network of desired closeness ratings, the satisfaction of a programme of requirements, and intricately balancing individual development goals in conjunction with communal goals and environmental design codes.

Climate change is a heated discussion topic in public arenas such as social media. Both texts and visuals play key roles in the debate, as they can complement, contradict, or reinforce each other in nuanced ways. It is therefore urgently needed to study the messages as multimodal objects to better understand the polarized debate about climate change impacts and policies. Multimodal representation models such as CLIP are known to be able to transfer knowledge across domains and modalities, enabling the investigation of textual and visual semantics together. Yet they are not directly able to distinguish the nuances between supporting and sceptic climate change stances. This paper explores a simple but effective strategy combining modality fusion and domain-knowledge enhancing to prepare CLIP-based models with knowledge of climate change stances. A multimodal Dutch Twitter dataset is collected and experimented with the proposed strategy, which increased the macro-average F1 score across stances from 51% to 86%. The outcomes can be applied in both data science and public policy studies, to better analyse how the combined use of texts and visuals generates meanings during debates, in the context of climate change and beyond.

How can we assess the ergonomic comfort of a sizeable spatial configuration such as the indoor space of a complex building or an urban landscape when we design, plan, and manage the space? Is there a fundamental difference between indoor [architectural] spatial configurations and outdoor [urban] spatial configurations with respect to ergonomics? Can we have a unified approach to the computational study of spatial ergonomics? This paper addresses these fundamental questions while providing a brief taxonomic review of the scholarly literature on these matters from a mathematical point of view, including a brief introduction to the modelling-based approaches to the computational ways of studying the fundamental effects of spatial configuration on human behaviours. Furthermore, the paper proposes a computational approach for ergonomic assessment of spatial configurations that explicitly allows for combined accessibility and visibility analyses in the built environment. The gist of this approach is the conceptualisation of spatial configurations as rasterised (voxelated) 2D manifold walkable terrains whose voxels have 3D vistas, unifying the simulations and analyses of accessibility and visibility. The paper elaborates on how such a representation of space can provide for conducting various sorts of computational queries, analyses, and simulation experiments for research in spatial ergonomics. The paper concludes with a mapping of the computational modelling approaches pertinent to the study and assessment of spatial ergonomics; and marks avenues of future research on various categories of exploratory, generative, and associative models for ex-ante and ex-post assessment of ergonomic matters at spatial scales.

This chapter presents methodological reflections on the necessity and utility of artificial intelligence (AI) in generative design. Specifically, the chapter discusses how generative design processes can be augmented by AI to deliver in terms of a few outcomes of interest or performance indicators while dealing with hundreds or thousands of small decisions. The core of the performance-based generative design paradigm is about making statistical or simulation-driven associations between these choices and their consequences for mapping and navigating such a complex decision space. This chapter will discuss promising directions in AI for augmenting decision-making processes in architectural design for mapping and navigating complex design spaces.

Cultural heritage, especially those inscribed on the UNESCO World Heritage List, is meant to be valued by mankind and protected for future generations. Triggered by radical and sometimes disastrous Heritage-Related Events (HREs), communities around the world are actively involved on social media to share their opinions and emotional attachments. This paper presents exploratory data analyses on a dataset collected from Twitter concerning HREs in World Heritage that triggered global concerns, with cases of the Notre Dame Paris fire and the Venice flood, both in 2019. The spatiotemporal patterns of tweeting behaviours of online communities before, during, and after the event demonstrate a clear distinction of activation levels caused by the HREs. The dominant emotions and topics of people during the online debate are detected and visualized with pre-trained deep-learning models and unsupervised clustering algorithms. Clear spatiotemporal dynamics can be observed from the data collected in both case studies, while each case also demonstrated its specific characteristics due to the different severity. The methodological framework proposed and the analytical outcomes obtained in this paper could be used both in urban studies to mine the public opinions about HREs and other urban events for reducing risks, and by the Geo-AI community to test spatiotemporal clustering algorithms.

Social Inclusion has been growing as a goal in heritage management. Whereas the 2011 UNESCO Recommendation on the Historic Urban Landscape (HUL) called for tools of knowledge documentation, social media already functions as a platform for online communities to actively involve themselves in heritage-related discussions. Such discussions happen both in “baseline scenarios” when people calmly share their experiences about the cities they live in or travel to, and in “activated scenarios” when radical events trigger their emotions. To organize, process, and analyse the massive unstructured multi-modal (mainly images and texts) user-generated data from social media efficiently and systematically, Artificial Intelligence (AI) is shown to be indispensable. This thesis explores the use of AI in a methodological framework to include the contribution of a larger and more diverse group of participants with user-generated data. It is an interdisciplinary study integrating methods and knowledge from heritage studies, computer science, social sciences, network science, and spatial analysis. AI models were applied, nurtured, and tested, helping to analyse the massive information content to derive the knowledge of cultural significance perceived by online communities. The framework was tested in case study cities including Venice, Paris, Suzhou, Amsterdam, and Rome for the baseline and/or activated scenarios. The AI-based methodological framework proposed in this thesis is shown to be able to collect information in cities and map the knowledge of the communities about cultural significance, fulfilling the expectation and requirement of HUL, useful and informative for future socially inclusive heritage management processes.

Mapping cultural significance of heritage properties in urban environment from the perspective of the public has become an increasingly relevant process, as highlighted by the 2011 UNESCO Recommendation on the Historic Urban Landscape (HUL). With the ubiquitous use of social media and the prosperous developments in machine and deep learning, it has become feasible to collect and process massive amounts of information produced by online communities about their perceptions of heritage as social constructs. Moreover, such information is usually inter-connected and embedded within specific socioeconomic and spatiotemporal contexts. This paper presents a methodological workflow for using semi-supervised learning with graph neural networks (GNN) to classify, summarize, and map cultural significance categories based on user-generated content on social media. Several GNN models were trained as an ensemble to incorporate the multi-modal (visual and textual) features and the contextual (temporal, spatial, and social) connections of social media data in an attributed multi-graph structure. The classification results with different models were aligned and evaluated with the prediction confidence and agreement. Furthermore, message diffusion methods on graphs were proposed to aggregate the post labels onto their adjacent spatial nodes, which helps to map the cultural significance categories in their geographical contexts. The workflow is tested on data gathered from Venice as a case study, demonstrating the generation of social perception maps for this UNESCO World Heritage property. This research framework could also be applied in other cities worldwide, contributing to more socially inclusive heritage management processes. Furthermore, the proposed methodology holds the potential of diffusing any human-generated location-based information onto spatial networks and temporal timelines, which could be beneficial for measuring the safety, vitality, and/or popularity of urban spaces.

During the rural [re]vitalization process in China, national strategies required rural public spaces with cultural significance to be identified before planning decision-making. However, places identified as culturally significant by planners and visitors can differ from the ones mostly used and valued by locals. Even if there is a growing interest in integrating local perspectives and experiences in planning, studies seldom discuss and compare openly the adequacy of spatial configuration, cognition and behaviour to support it. This study took Anyi Historic Village Cluster as a case study to empirically investigate rural public spaces with three distinct, yet related approaches: (1) Morphological: spatial network centralities based on space syntax; (2) Cognitive: Lynchian village images with semi-structured interviews; (3) Behavioural: spatiotemporal occupation patterns using Wi-Fi positioning tracking. Significant places valued and used by locals and non-locals were detected with the multi-source data. Furthermore, multivariant regression models managed to characterize the relationship among different aspects of investigated rural public spaces, which also helped diagnose places of interest to prioritize in planning, demonstrating the advantage of integrating the sources of information in practice instead of studying them apart. Results can also assist rural planning on how to identify what to preserve, what to enhance, and how to develop such spaces, without overlooking the local needs or losing the rural identity.

The UNESCO 2011 Recommendation on the Historic Urban Landscape promotes to map cultural significance of urban heritage from the perspectives of the general public in pursuit of social inclusion in heritage management. The user-generated information already available on social media platforms in the form of images, comments, and ratings can be considered a rich source for collecting data concerning the tourists’ image of destinations and their collective perception of urban cultural heritage. Considering the large amount of unstructured data, artificial intelligence (AI) can construct structured feature vectors therefrom and significantly aid the analysis and collation processes compared to the traditional manual approach for mapping public perception of cultural heritage. This paper presents an exploratory case study conducted in the area of Testaccio, Rome, showcasing the use of AI to map the perceived and narrated urban heritage images using social media data. An image-sharing platform, Flickr, is used to collect thousands of posts containing images and comments in the area, which are further analysed with pre-trained image recognition, natural language processing, and dimensionality reduction algorithms. Results as the urban heritage images are visualised, showing the most significant elements from a public perspective. Such a methodology provides an alternative perspective of viewing the urban heritage attributes as a collection of depicted and posted content. It can contribute as a tool for the documentation of collective attention for inclusive heritage management and local development planning during the designing and policy-making processes.

Values (why to conserve) and Attributes (what to conserve) are essential concepts of cultural heritage. Recent studies have been using social media to map values and attributes conveyed by the public to cultural heritage. However, it is rare to connect heterogeneous modalities of images, texts, geo-locations, timestamps, and social network structures to mine the semantic and structural characteristics therein. This study presents a methodological framework for constructing such multi-modal datasets using posts and images on Flickr for graph-based machine learning (ML) tasks concerning heritage values and attributes. After data pre-processing using pre-trained ML models, the multi-modal information of visual contents and textual semantics are modelled as node features and labels, while their social relationships and spatio-temporal contexts are modelled as links in Multi-Graphs. The framework is tested in three cities containing UNESCO World Heritage properties—Amsterdam, Suzhou, and Venice— which yielded datasets with high consistency for semi-supervised learning tasks. The entire process is formally described with mathematical notations, ready to be applied in provisional tasks both as ML problems with technical relevance and as urban/heritage study questions with societal interests. This study could also benefit the understanding and mapping of heritage values and attributes for future research in global cases, aiming at inclusive heritage management practices. Moreover, the proposed framework could be summarized as creating attributed graphs from unstructured social media data sources, ready to be applied in a wide range of use cases.

Focusing on the quality of reuse of buildings with respect to the efficiency of human movement patterns and the effectiveness of allocation of functional spaces with respect to their needs for social encounter and avoidance reveals the configurative nature and the human impact of architectural design. By comparing such functionality assessments before and after a redesign process for retrofitting, a clearer grasp of the effect of the spatial configuration on the efficiency and the effectiveness of a design can be explicated. In configurational analysis the focal point of attention is the structure of the walkable space in the building, detached and abstracted from the shape of the building. In configurational functionality assessment, the focus is to synthesize multiple analyses, aggregate the results, and derive indicators of quality with respect to either quantitative objectives or qualitative ideals. Does the structure of the space and the allocation of functional spaces to various locations in the spatial network of a building have an effect on its overall functionality/utility? How can we study these effects? Are the functional spaces placed in their best-fitting locations? Do the design operations like adding an external staircase or tearing down an interior wall make a difference in the accessibility of functional spaces? By digging into this topic, you will gain a methodology with which you can describe and analyse a spatial configuration in a reproducible way.

The UNESCO World Heritage List (WHL) includes the exceptionally valuable cultural and natural heritage to be preserved for mankind. Evaluating and justifying the Outstanding Universal Value (OUV) is essential for each site inscribed in the WHL, and yet a complex task, even for experts, since the selection criteria of OUV are not mutually exclusive. Furthermore, manual annotation of heritage values and attributes from multi-source textual data, which is currently dominant in heritage studies, is knowledge-demanding and timeconsuming, impeding systematic analysis of such authoritative documents in terms of their implications on heritage management. This study applies state-of-the-art NLP models to build a classifier on a new dataset containing Statements of OUV, seeking an explainable and scalable automation tool to facilitate the nomination, evaluation, research, and monitoring processes of World Heritage sites. Label smoothing is innovatively adapted to improve the model performance by adding prior interclass relationship knowledge to generate soft labels. The study shows that the best models fine-tuned from BERT and ULMFiT can reach 94.3% top-3 accuracy. A human study with expert evaluation on the model prediction shows that the models are sufficiently generalizable. The study is promising to be further developed and applied in heritage research and practice.