This paper aims at discussing the ongoing research activities that are being conducted on the use of AI-based solutions to promote walkability indexes in the Italian inner areas. Although social sustainability is an expected outcome of the walkability concept, the literature has focused on urban social sustainability and the development of socially sustainable urban communities, while attention to pedestrian-friendly rural areas is lacking. The paper examines existing research on the subject and emphasises the potential of agent-based simulation to create indicators that promote service accessibility and inclusion, specifically in terms of sustainable walkability in rural areas with a high density of older people.
1. Introduction the influence of walkability on socially sustainable com- demographic fragility caused by an ageing population, munities should take into account the local conditions physical and ecological instability resulting from insufof accessibility, i.e. broaden the focus to include rural ficient handling of semi-natural resources, and undercommunities as well. utilization of a significant amount of land resources in
Furthermore, a recent systematic review of the liter- numerous localities. ature [27] on the role of AI-powered and sensor-based Walkability metrics gauge the level of pedestriantechnologies in assisting informal carers (often volun- friendly in a neighborhood’s built environment, and walkteers or relatives) who provide care for older adults, re- ability evaluation is employed to evaluate this friendlivealed a lack in the reviewed literature concerning the ap- ness [35]. Several walkability indices have been created plication of location-based technologies for older adults to objectively assess the features of the built environment residing in remote regions, suggesting to focus on ex- that promote walking habits [36]. These indices range ploring the integration of emerging technologies, such from ones that concentrate on urban form factors at the as AI and Geographic Information System (GIS) [28], to neighbourhood level (such as population density, land improve healthcare for informal carers and older adults use diversity, and street connectivity) to those that focus in rural regions. Similarly, a second systematic review on urban design factors at the street level (such as the by the authors [29] determined that employing innova- size and layout of streets, the design and condition of tive strategies to create outdoor spaces that cater to the buildings, and street furniture) [36]. However, walkabilneeds of adults in need of care, while also providing addi- ity in rural communities presents a unique challenge as tional support to their informal carers, has the potential its theoretical and practical basis has not been thoroughly to provide significant assistance to these carers. examined in this specific context [ 25]. This presents a
This article aims to discuss the ongoing research on substantial opportunity for the Italian territory, as inthe use of AI-based technologies to enhance a sustain- ner areas comprise over 4,000 municipalities and over able walkability in inner areas of Italy. This research is a 20 percent of the country’s resident population, or apcomponent of the ongoing project called “Care provision proximately 60 percent of the national territory [37]. On across diferent territorial contexts” 1. Its objective is to the other hand, there is a clear need for more research address the current lack of walkability indexes for inner focused on rural older adults and their connection to the areas by investigating the potential of AI-based tech- community, as the current evidence is insuficient [ 38, 39]. nologies and promoting the achievement of a sustainable The high occurrence of residential proximity, with family walkability in inner areas within an ageing society. members living together and multigenerational households, has created a strong intergenerational exchange and family support system for older adults requiring 2. Walkability and Inner Areas care in rural areas [33]. This makes these areas highly promising for the development of new walkability indices aimed at creating socially sustainable communities.
Our research activity is indeed being focused on studying how AI-based solution can aid in developing sustainable walkability indexes in Italian inner areas.
The term rural is commonly understood to refer to areas with a small population, few settlements, and remoteness [30]. However, there is no consensus among academics on whether all of these characteristics need to be present together in order to define a settlement as rural, or if it is enough for just one of these elements to be present [30]. A significant portion of the Italian territory 3. AI-based solutions to improve is organised spatially according to “minor centres", which are commonly of small size and frequently provide resi- walkability in Italian inner dents with limited access to essential services [31]. The areas: the intended value of characteristics of this territory can be summarised using using agent-based simulations the term “inner areas" [31] which overlap with the identification of rural regions that face a notable deficiency Scholarly literature provides several examples of using in the provision of essential services [32, 33]. However, Artificial Intelligence (AI) techniques to assess walkabilinner areas exhibit three primary attributes [34]: socio- ity. For instance, scholars employed machine learning (ML) techniques to evaluate the state of sidewalks, as a substantial predictor of a pedestrian-friendly neighbourhood, through the analysis of pedestrians’ physiological responses as gathered by wearable accelerometers [35].
Several studies have examined the integration of deep learning (DL) with environmental sensors to evaluate the walkability of urban streets [40], have explored the 1This publication was produced with the co-funding of European Union – Next Generation EU, in the context of the National Recovery and Resilience Plan, PE8 Conseguenze e sfide dell’invecchiamento", Project Age-It (AGE - IT - A Novel Publicprivate Alliance to Generate Socioeconomic, Biomedical and Technological Solutions for an Inclusive Italian Ageing Society- Ageing Well in an Ageing Society) - AGE-IT- PE00000015 CUP: H43C22000840006 utilisation of Streetview Image and semantic segmenta- models into Digital Twins environments with GIS-based tion to create a walkability evaluation index [41] or have analysis, maybe allowing for a deeper understanding of estimated walkability measures at a street level [42]. Fur- older adults personal mobility also in inner areas. In thermore, a few studies have suggested a network-based this regard, Liu et al [49] recently examined the benefits measure of walkability that incorporates road network of employing agent-based models (ABM) as a quantitastructure and user opinions using machine learning tech- tive tool for assessing walkability due to their inclusion niques with the aim to get predictive models that yield of subjective aspects, integration of many parameters, comprehensive walkability scores at a spatial level [43]. and capacity to distinguish between various populations. Other studies have suggested novel methods for utilis- Similarly, Bandini et al [50] conducted a study with the ing pre-trained models to create adaptable models that purpose to evaluate the walkability of the city of Milan can predict walkability scores for cities that were not by simulating the age-driven pedestrian dynamics, which included in the original training process [44]. involve various behaviours such as diferent speeds and
The scientific publications on walkability studies have crossing behaviour. Badland et al. [51], instead, devised significantly expanded over the past twenty years [ 45]. an agent-based modelling tool that integrated the advanHowever, our current study is revealing that scholarly tages of Service Area Approach mapping to examine the research on the use of AI algorithms to evaluate walkabil- correlation between amenity access and neighbourhood ity in rural areas, and especially in the Italian inner areas, walkability while also enabling the testing of various is under-investigated. Nonetheless, AI has significant planning scenarios. Therefore, given that agent-based potential for evaluating the pedestrian-friendliness of simulation models simulate the actions and interactions inner areas. Geographical information, socio-economic of individual agents from various demographic groups data, and pedestrian behavioural patterns can be utilised in a specific environment, the incorporation of AI techthrough the application of ML algorithms to provide niques may have the potential to accurately depict the walkability scores that are specifically customised for pedestrians’ mobility patterns or the barriers for their the distinct attributes of inner areas and ageing pop- personal mobility at each age categories, contributing to ulation. Some existing studies in urban context have attain our goal to define a sustainable walkability concept highlighted the need of using Geographical Information in Italian inner areas for older population. Systems (GIS) to define an index that measures the walkability of older people and supports the creation of advanced simulation models based on AI [46]. In a similar 4. Conclusions vein, another study assessed the emotional experience of pedestrians, specifically focusing on older adults, propos- Although social sustainability is an expected outcome ing an “afective walkability” indicator [ 47]. The aim was of the walkability concept, the literature has focused on to investigate how safe, comfortable, and walkable an urban social sustainability and the development of soenvironment was, within the context of promoting social cially sustainable urban communities, while attention and active inclusion of older adults in urban areas. Based to pedestrian-friendly rural areas is lacking. Moreover, on this, our research activity is being focused on studying there exists a dearth of scholarly publications both in villages in Italian inner areas, including Premeno (VB) walkability metrics targeted to rural communities and and Petrella Tifernina (CB), with a high aged population in the use of AI-based techniques to promote pedestrian density. Our goal is to understand the factors that af- friendliness in rural areas. The article reviews some of fect walkability in inner areas and its accessibility, and the currently available contributions on the topic and how the integration of AI techniques can promote so- highlights the potential of agent-based simulation to decial inclusion and equity of access to healthcare services, velop indicators that facilitate service accessibility and ie a sustainable walkability in these areas. Indeed, one inclusivity, i.e., sustainable walkability in rural areas with potential benefit of integrating AI-based tools, such as a significant older population density. Further research remote sensing or GIS technologies, is the provision of will be carried out using multiple case studies to derive a comprehensive mapping and geographical analysis. This generalised research methodology for the specific context information can be utilised to guide targeted measures of Italian inner areas. that improve the walkability of inner areas by revealing crucial details regarding pedestrian access, connectivity, References and safety. In addition, according to a recent systematic review of the literature [48] the combination of wear- [1] A. Baobeid, M. Koç, S. G. Al-Ghamdi, Walkability able sensors and GIS-based approach shows potential and its relationships with health, sustainability, and as a method for accurately capturing older people’s im- livability: elements of physical environment and mediate physical reactions to environmental stressors. evaluation frameworks, Frontiers in Built EnvironThis could lead to the integration of simulation-based ment 7 (2021) 721218. [2] S. H. Rogers, K. H. Gardner, C. H. Carlson, Social Health 62 (2008) e9–e9.
capital and walkability as social aspects of sustain- [16] S. Cinderby, H. Cambridge, K. Attuyer, M. Bevan, ability, Sustainability 5 (2013) 3473–3483. K. Croucher, R. Gilroy, D. Swallow, Co-designing [3] S. Bahadure, R. Kotharkar, Social sustainability and urban living solutions to improve older people’s mixed land use, in: Proceedings of International mobility and well-being, Journal of urban health Conference on Advances in Architecture and Civil 95 (2018) 409–422.
Engineering (AARCV 2012), volume 21, 2012, p. 725. [17] B. Aguiar, R. Macário, The need for an elderly [4] Y. Gul, The efectiveness of walkability index for centred mobility policy, Transportation research social sustainability in developing countries using procedia 25 (2017) 4355–4369. geographical information system, Journal of Design [18] R. Bayar, M. Yılmaz, Measuring age-friendliness Sciences and Applied Arts 2 (2021) 141–154. based on the walkability indices of older people [5] N. Dempsey, G. Bramley, S. Power, C. Brown, The to urban facilities, Urban Design International 28 social dimension of sustainable development: Defin- (2023) 35–51. ing urban social sustainability, Sustainable devel- [19] L. Cheng, M. Yang, J. De Vos, F. Witlox, Examining opment 19 (2011) 289–300. geographical accessibility to multi-tier hospital care [6] W. Sabir Abdullah, Optimizing social sustainabil- services for the elderly: A focus on spatial equity, ity in walkable university campus: A comparison Journal of Transport & Health 19 (2020) 100926. between the old and new campuses of sulaimani [20] J.-F. Levesque, M. F. Harris, G. Russell, Patientuniversity, Amazonia Investiga 9 (2020) 44–56. centred access to health care: conceptualising ac[7] K. M. Leyden, Social capital and the built environ- cess at the interface of health systems and populament: the importance of walkable neighborhoods, tions, International journal for equity in health 12 American journal of public health 93 (2003) 1546– (2013) 1–9.
1551. [21] H. Wang, P. C. Coyte, W. Shi, X. Zong, R. Zhong, [8] P. Morales-Flores, C. Marmolejo-Duarte, Can we Social governance and sustainable development in build walkable environments to support social cap- elderly services: Innovative models, strategies, and ital? towards a spatial understanding of social capi- stakeholder perspectives, Sustainability 15 (2023) tal; a scoping review, Sustainability 13 (2021) 13259. 15414. [9] S. Rogers, S. Aytur, K. Gardner, C. Carlson, Mea- [22] C. Tacoli, The links between urban and rural develsuring community sustainability: Exploring the in- opment, 2003. tersection of the built environment & social capital [23] R. C. Brownson, C. M. Hoehner, K. Day, A. Forsyth, with a participatory case study, Journal of Environ- J. F. Sallis, Measuring the built environment for mental Studies and Sciences 2 (2012) 143–153. physical activity: state of the science, American [10] A. N. Mohamed, A. A. E. Elmokadem, S. M. Ali, journal of preventive medicine 36 (2009) S99–S123.
N. Badawey, Improve urban form to achieve high [24] S. S. Frost, R. T. Goins, R. H. Hunter, S. P. Hooker, social sustainability in a residential neighborhood L. L. Bryant, J. Kruger, D. Pluto, Efects of the salam new city as a case study, Buildings 12 (2022) built environment on physical activity of adults 1935. living in rural settings, American journal of health [11] A. Sonta, X. Jiang, Rethinking walkability: Ex- promotion 24 (2010) 267–283. ploring the relationship between urban form and [25] C. I. Nykiforuk, K. Coupland, L. M. Nieuwendyk, neighborhood social cohesion, Sustainable Cities J. Ann McGetrick, Universal design for the rural and Society 99 (2023) 104903. walks of life: operationalizing walkability in bon[12] K. Komp-Leukkunen, J. Sarasma, Social sustainabil- nyville, alberta, canada, Critical Public Health 28 ity in aging populations: A systematic literature (2018) 213–224.
review, The Gerontologist (2023) gnad097. [26] L. G. Hart, E. H. Larson, D. M. Lishner, Rural def[13] F. Alves, S. Cruz, A. Ribeiro, A. Bastos Silva, J. Mar- initions for health policy and research, American tins, I. Cunha, Walkability index for elderly health: journal of public health 95 (2005) 1149–1155.
A proposal, Sustainability 12 (2020) 7360. [27] F. Milella, D. D. Russo, S. Bandini, How artificial [14] N. Shellito, N. V. Roldan, Walking away from lone- intelligence can support informal caregivers in their liness: The mediating role of social isolation, Inno- caring duties to elderly? a systematic review of vation in Aging 3 (2019) S836. the literature, in: AIxIA 2023 Italian Workshop [15] T. Sugiyama, E. Leslie, B. Giles-Corti, N. Owen, As- on Artificial Intelligence for an Ageing Society, cosociations of neighbourhood greenness with physi- located with the 22nd International Conference of cal and mental health: do walking, social coherence the Italian Association for Artificial Intelligence and local social interaction explain the relation- (AIxIA 2023), 2023, pp. 6–9. ships?, Journal of Epidemiology & Community [28] B. Mullachery, S. Alismail, A smart healthcare framework: Opportunities for integrating emerging Journal of the Korean Cartographic Association 22 technologies (5g, iot, ai, and gis), in: Proceedings (2022) 53–68. of the Future Technologies Conference, Springer, [42] M. M. Hasan, V. Kwigizile, J.-S. Oh, Automated mea2022, pp. 325–340. surement of walkability applying artificial intelli[29] F. Milella, D. D. Russo, S. Bandini, Ai-powered gence (ai) and spatial analysis techniques, Journal solutions to support informal caregivers in their of Transport & Health 22 (2021) 10. decision-making: A systematic review of the litera- [43] A. M. S. Alfosool, Y. Chen, D. Fuller, Alf–score—a ture 1, OBM Geriatrics 7 (2023) 1–11. novel approach to build a predictive network–based [30] N. Morelli, S. Barello, M. Mayan, G. Grafigna, Sup- walkability scoring system, Plos one 17 (2022) porting family caregiver engagement in the care e0270098. of old persons living in hard to reach communi- [44] A. M. Alfosool, Y. Chen, D. Fuller, Alf-score++, ties: A scoping review, Health & social care in the a novel approach to transfer knowledge and precommunity 27 (2019) 1363–1374. dict network-based walkability scores across cities, [31] UVAL, Strategia Nazionale per le aree interne: Scientific Reports 12 (2022).
definizione, obiettivi, strumenti e governance, [45] X. Li, D. Xie, Z. Zhou, X. Zhang, R. Li, J. Li, Z. Chen, https://www.agenziacoesione.gov.it/wp-content/ J. Zhang, Visualization analysis of research progress uploads/2020/07/MUVAL_31_Aree_interne.pdf , for walkability, Scientific Reports 14 (2024) 1989. 2014. [46] A. Gorrini, S. Bandini, Elderly walkability index [32] P. Bertolini, F. Pagliacci, Quality of life and territo- through gis: Towards advanced ai-based simulation rial imbalances. a focus on italian inner and rural models., in: AI* AAL@ AI* IA, 2018, pp. 67–82. areas., Bio-Based & Applied Economics 6 (2017). [47] S. Bandini, F. Gasparini, Social and active inclusion [33] M. Arlotti, Older people and care networks in rural of the elderly in the city through afective walkaareas: An exploratory study in italy, Sociologia bility, The Review of Socionetwork Strategies 15 Ruralis (2024). (2021) 557–573. [34] G. Basile, A. Cavallo, Rural identity, authenticity, [48] F. Milella, M. Oltolini, S. Bandini, Can wearable and sustainability in italian inner areas, Sustain- technologies contribute to an age-friendly walkaability 12 (2020) 1272. bility environment? First insights from a systematic [35] H. R. Ng, I. Sossa, Y. Nam, J.-H. Youn, Machine review of the literature. In Conferenza PErvasive learning approach for automated detection of irreg- Technologies Related to Assistive Environments ular walking surfaces for walkability assessment (PETRA) (PETRA ’24), 26- 28 giugno 2024, Creta , with wearable sensor, Sensors 23 (2022) 193. Grecia. ACM, New York, NY, USA, 7 pages. https: [36] B. W. Koo, S. Guhathakurta, N. Botchwey, How are //doi.org/10.1145/3652037.3652046, 2024. In press. neighborhood and street-level walkability factors [49] Y. Liu, D. Song, Z. Wang, X. Yu, R. Wang, Walkaassociated with walking behaviors? a big data ap- bility assessment using agent-based model: Why it proach using street view images, Environment and becomes an advantageous way, in: World Congress Behavior 54 (2022) 211–241. of Architects, Springer, 2023, pp. 367–374. [37] G. Dematteis, Montagna e aree interne nelle [50] S. Bandini, L. Crociani, A. Gorrini, K. Nishinari, politiche di coesione territoriale italiane ed europee, G. Vizzari, et al., Walkability assessment for the elMontagna e aree interne nelle politiche di coesione derly through simulations: The longevicity project., territoriale italiane ed europee (2013) 7–15. in: AI* AAL@ AI* IA, 2018, pp. 83–91. [38] P. R. Baker, D. P. Francis, J. Soares, A. L. Weight- [51] H. Badland, M. White, G. MacAulay, S. Eagleson, man, C. Foster, Community wide interventions for S. Mavoa, C. Pettit, B. Giles-Corti, Using agentincreasing physical activity, Cochrane database of based modelling to inform neighbourhood walkabilsystematic reviews (2015). ity, Spatial Data Access and Integration to support [39] A. Klann, L. Vu, M. Ewing, M. Fenton, R. Pojed- liveability (2013) 23.
nic, Translating urban walkability initiatives for older adults in rural and under-resourced communities, International journal of environmental research and public health 16 (2019) 3041. [40] Y. Li, N. Yabuki, T. Fukuda, J. Zhang, A big data evaluation of urban street walkability using deep learning and environmental sensors (????). [41] J. of the Korean Cartographic Association, et al.,
Development of walkability evaluation index using streetview image and semantic segmentation,