Mental health disorders, such as depression, have been estimated to account for the largest proportion of global disease burden. Existing research has established significant correlations between the built environment and mental health. This research, however, has relied on traditional statistical methods that are not amenable to working with large remote sensing image-based datasets. This research addresses this challenge and contributes new knowledge and a novel method for using generative deep learning for urban analysis and synthesis tasks involving mental health. The research specifically investigates three mental state measures: depression, anxiety, and the perception of safety. The experimental results demonstrate the efficacy of the process—providing a new method to find correlational signals, while providing insights on the correlation between specific urban design features and the incidence of depression.
WHO. World Health Statistics 2016: Monitoring Health for the SDGs Sustainable Development Goals. Geneva: World Health Organization, 2016.
2.
WhitefordHAAlizeFerrariJDegenhardtL, et al. The global burden of mental, neurological and substance use disorders: an analysis from the global burden of disease study 2010. PloS one2015; 10(2): e0116820.
3.
CreswellAWhiteTVincentD, et al. Generative adversarial networks: An overview. IEEE Signal Processing Magazine2018; 35(1): 53–65.
4.
MarshallWEPiatkowskiDPGarrickNW. Community design, street networks, and public health. Journal of Transport & Health2014; 1(4): 326–340.
5.
DumbaughERaeR. Safe urban form: revisiting the relationship between community design and traffic safety. Journal of the American Planning Association2009; 75(3): 309–329.
6.
PapasMAAnthonyJAReidE, et al. The built environment and obesity. Epidemiologic Reviews2007; 29(1): 129–143.
7.
ForsythAKrizekKJ. Promoting walking and bicycling: assessing the evidence to assist planners. Built Environment2010; 36(4): 429–446.
8.
MaharanaANsoesieEO. Use of deep learning to examine the association of the built environment with prevalence of neighborhood adult obesity. JAMA Network Open2018; 1(4): e181535.
9.
PiaggesiSGauvinLTizzoniM, et al. Predicting city poverty using satellite imagery. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, June 16-20, 2019, Long Beach, California, 2019.
10.
SuelEPolakJWBennettJE, et al. Measuring social, environmental and health inequalities using deep learning and street imagery. Scientific Reports2019; 9(1): 6229.
11.
SimonsEDellSDMoineddinR, et al. Associations between neighborhood walkability and incident and ongoing asthma in children. Annals of the American Thoracic Society2018; 15(6): 728–734.
12.
LiFHarmerPBradleyCJ, et al. Built environment and changes in blood pressure in middle aged and older adults. Preventive Medicine2009; 48(3): 237–241.
13.
MüllerGRolandHRaheC, et al. Inner-city green space and its association with body mass index and prevalent type 2 diabetes: a cross-sectional study in an urban German city. BMJ Open2018; 8(1): e019062.
14.
MelisGGelorminoEMarraG, et al. The effects of the urban built environment on mental health: a cohort study in a large northern Italian city. International journal of environmental research and public health2015; 12(11): 14898–14915.
15.
MilesRCouttsCMohamadiA. Neighborhood urban form, social environment, and depression. Journal of Urban Health2012; 89(1): 1–18.
16.
BeyerKMMKaltenbachASzaboA, et al. Exposure to neighborhood green space and mental health: evidence from the survey of the health of Wisconsin. International Journal of Environmental Research and Public Health2014; 11(3): 3453–3472.
17.
PatelVBurnsJKDhingraM, et al. Income inequality and depression: a systematic review and meta-analysis of the association and a scoping review of mechanisms. World Psychiatry2018; 17(1): 76–89.
18.
JeanNBurkeMXieM, et al. Combining satellite imagery and machine learning to predict poverty. Science2016; 353(6301): 790–794.
19.
VerebesT. Experiments in associative urbanism. Architectural Design2009; 79(4): 24–33.
20.
ZawidzkiM. Discrete optimization in architecture: Architectural & urban layout. In: Briefs in Architectural Design and Technology. Berlin: Springer; 2016.
21.
DounasTBenjaminASWuH, et al. Speculative urban types: a cellular automata evolutionary approach. JanssenP.LohP.RaonicA.SchnabelM. A. (eds.), Protocols, Flows, and Glitches - Proceedings of the 22nd CAADRIA Conference, Xi’an Jiaotong-Liverpool University, Suzhou, China, 5-8 April 2017, pp. 313–322.
22.
Noronha Pinto de Oliveira E SousaMCelaniMGC. Towards urban densification using shape grammar to develop components for retrofitting street design. LeeJi-Hyun (Eds.) “Hello, Culture!” - 18th International Conference, CAAD Futures 2019, Proceedings / ISBN 978-89-89453-05-5, Daejeon, Korea, June 26-282019, p. 505.
23.
SwahnE. Markovian Drift - Iterative substitutional synthesis of 2D and 3D design data using Markov models of source data. In: Computing for a Better Tomorrow - Proceedings of the 36th eCAADe Conference, Łódź, Poland, 19–21 September 2018. Lodz, Poland: Lodz University of Technology, 2018.
24.
ZhuJ-YParkTIsolaP, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017.
25.
ZhangZYangLZhengY. Translating and segmenting multimodal medical volumes with cycle- and shape- consistency generative adversarial network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, 19–21 June 2018.
26.
ZhengH. Drawing with bots: Human-computer collaborative drawing experiments. In: Learning, Prototyping and Adapting, Short Paper Proceedings of the 23rd International Conference on Computer-Aided Architectural Design Research in Asia. Beijing, China: CAADRIA, 2018.
27.
ZhaoHWijnandsJSKerryAN, et al. Unsupervised deep learning to explore streetscape factors associated with urban cyclist safety. In: Smart Transportation Systems. Berlin: Springer; 2019, pp. 155–164.
28.
NewtonD. Generative deep learning in architectural design. Technology Architecture Design2019; 3(2): 176–189.
29.
AsIPalSBasuP. Artificial intelligence in architecture: generating conceptual design via deep learning. International Journal of Architectural Computing2018; 16(4): 306–327.
30.
HuangWZhengH. Architectural drawings recognition and generation through machine learning re calibration. On Imprecision and Infidelity. In: Proceedings of the 38th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA), Mexico City, Mexico, 18–20 October 2018.
31.
RautioNFilatovaSLehtiniemiHMiettunenJ. Living environment and its relationship to depressive mood: a systematic review. International Journal of Social Psychiatry2018; 64(1): 92–103.
32.
Cohen-ClineHTurkheimerEDuncanGE. Access to green space, physical activity and mental health: a twin study. Journal Epidemiol Community Health2015; 69(6): 523–529.
33.
SaelensBEHandySL. Built environment correlates of walking: a review. Medicine and science in sports and exercise2008; 40 (7 Suppl):S550.
34.
DinasPCKoutedakisYFlourisAD. Effects of exercise and physical activity on depression. Irish journal of medical science2011; 180 (2): 319–325.
35.
WenMZhangXCarmenHarrisD, et al. Spatial disparities in the distribution of parks and green spaces in the USA. Annals of Behavioral Medicine2013; 45(suppl_1): S18–S27.
36.
LanYRobertsHKwanM-P, et al. Transportation Noise Exposure and Anxiety: A Systematic Review and Meta-Analysis. Environmental Research, 2020; 191: 110118.
37.
VentimigliaISeedatS. Current evidence on urbanicity and the impact of neighbourhoods on anxiety and stress-related disorders. Current Opinion in Psychiatry2019; 32(3): 248–253.
38.
MouratidisK. The impact of urban tree cover on perceived safety. Urban Forestry & Urban Greening2019; 44: 126434.
39.
HarveyCAultman-HallLHurleySE, et al. Effects of skeletal streetscape design on perceived safety. Landscape and Urban Planning2015; 142: 18–28.
40.
Survey California Health Interview. CHIS 2003 benchmarking of key estimates with those from the national health interview survey and the medical expenditure panel survey. In: CHIS Working Paper Series. Los Angeles, CA: UCLA Center for Health Policy Research; 2008.
41.
GrovesRMFowlerFJJrCouperMP, et al. Survey Methodology. Hoboken, NJ: John Wiley & Sons; 2011, p. 561.
42.
GuidottiRAnnaMRuggieriS, et al. A survey of methods for explaining black box models. ACM Computing Surveys (CSUR)2018; 51(5): 1–42.
43.
HilberseimerL. The New City: Principles of Planning. Hilberseimer, Ludwig: Theobald; 1944.
44.
PopeA. Ladders, Houston, Texas, Rice School of Architecture. Nueva YorN: Princeton Architectural Press; 1996.
