Dataset Information

Phenotyping urban built and natural environments with high-resolution satellite images and unsupervised deep learning.

ABSTRACT: Cities in the developing world are expanding rapidly, and undergoing changes to their roads, buildings, vegetation, and other land use characteristics. Timely data are needed to ensure that urban change enhances health, wellbeing and sustainability. We present and evaluate a novel unsupervised deep clustering method to classify and characterise the complex and multidimensional built and natural environments of cities into interpretable clusters using high-resolution satellite images. We applied our approach to a high-resolution (0.3 m/pixel) satellite image of Accra, Ghana, one of the fastest growing cities in sub-Saharan Africa, and contextualised the results with demographic and environmental data that were not used for clustering. We show that clusters obtained solely from images capture distinct interpretable phenotypes of the urban natural (vegetation and water) and built (building count, size, density, and orientation; length and arrangement of roads) environment, and population, either as a unique defining characteristic (e.g., bodies of water or dense vegetation) or in combination (e.g., buildings surrounded by vegetation or sparsely populated areas intermixed with roads). Clusters that were based on a single defining characteristic were robust to the spatial scale of analysis and the choice of cluster number, whereas those based on a combination of characteristics changed based on scale and number of clusters. The results demonstrate that satellite data and unsupervised deep learning provide a cost-effective, interpretable and scalable approach for real-time tracking of sustainable urban development, especially where traditional environmental and demographic data are limited and infrequent.

SUBMITTER: Metzler AB

PROVIDER: S-EPMC7615085 | biostudies-literature | 2023 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Phenotyping urban built and natural environments with high-resolution satellite images and unsupervised deep learning.

Metzler A Barbara AB Nathvani Ricky R Sharmanska Viktoriia V Bai Wenjia W Muller Emily E Moulds Simon S Agyei-Asabere Charles C Adjei-Boadi Dina D Kyere-Gyeabour Elvis E Tetteh Jacob Doku JD Owusu George G Agyei-Mensah Samuel S Baumgartner Jill J Robinson Brian E BE Arku Raphael E RE Ezzati Majid M

The Science of the total environment 20230613

Cities in the developing world are expanding rapidly, and undergoing changes to their roads, buildings, vegetation, and other land use characteristics. Timely data are needed to ensure that urban change enhances health, wellbeing and sustainability. We present and evaluate a novel unsupervised deep clustering method to classify and characterise the complex and multidimensional built and natural environments of cities into interpretable clusters using high-resolution satellite images. We applied ...[more]

PMID: 37315611

Similar Datasets

Project description:BackgroundAedes aegypti is the main vector of the dengue, Zika and several other arboviruses. It is highly adapted to urbanized environments and can be found worldwide. Mosquito population control is considered the best strategy for fighting mosquito-borne diseases, making an understanding of their population dynamics vital for the development of more effective vector control programs. This study therefore sought to investigate how different levels of urbanization affect Aedes aegypti populations and modulate population structure in this species with the aid of wing geometric morphometrics.MethodsSpecimens were collected from eleven locations in three areas with distinct levels of urbanization in the city of São Paulo, Brazil: conserved, intermediate and urbanized. The right wings of female mosquitoes collected were removed, and photographed and digitized. Canonical variate analysis and Mahalanobis distance were used to investigate the degree of wing-shape dissimilarity among populations. Thin-plate splines were calculated by regression analysis of Canonical Variation Analysis scores against wing-shape variation, and a cross-validated reclassification was performed for each individual; a neighbor-joining tree was then constructed.ResultsMetapopulation and individual population analysis showed a clear segregation pattern in the Canonical Variation Analysis. Pairwise cross-validated reclassification yielded relatively high scores considering the microgeographical scale of the study and the fact that the study populations belong to the same species. The neighbor-joining tree showed that mosquitoes in the intermediate urban area segregated in the metapopulation and individual population analyses. Our findings show significant population structuring in Aedes aegypti mosquitoes in the areas studied. This is related to the different degrees of urbanization in the areas where the specimens were collected along with their geographical location.ConclusionsUrbanization processes in the study areas appear to play an important role in microevolutionary processes triggered by man-made modifications in the environment, resulting in a previously unknown population structuring pattern of major epidemiological importance.

Project description:ImportanceEnvironments associated with smoking increase a smoker's craving to smoke and may provoke lapses during a quit attempt. Identifying smoking risk environments from images of a smoker's daily life provides a basis for environment-based interventions.ObjectiveTo apply a deep learning approach to the clinically relevant identification of smoking environments among settings that smokers encounter in daily life.Design, setting, and participantsIn this cross-sectional study, 4902 images of smoking (n = 2457) and nonsmoking (n = 2445) locations were photographed by 169 smokers from Durham, North Carolina, and Pittsburgh, Pennsylvania, areas from 2010 to 2016. These images were used to develop a probabilistic classifier to predict the location type (smoking or nonsmoking location), thus relating objects and settings in daily environments to established smoking patterns. The classifier combines a deep convolutional neural network with an interpretable logistic regression model and was trained and evaluated via nested cross-validation with participant-wise partitions (ie, out-of-sample prediction). To contextualize model performance, images taken by 25 randomly selected participants were also classified by smoking cessation experts. As secondary validation, craving levels reported by participants when viewing unfamiliar environments were compared with the model's predictions. Data analysis was performed from September 2017 to May 2018.Main outcomes and measuresClassifier performance (accuracy and area under the receiver operating characteristic curve [AUC]), comparison with 4 smoking cessation experts, contribution of objects and settings to smoking environment status (standardized model coefficients), and correlation with participant-reported craving.ResultsOf 169 participants, 106 (62.7%) were from Durham (53 [50.0%] female; mean [SD] age, 41.4 [12.0] years) and 63 (37.3%) were from Pittsburgh (31 [51.7%] female; mean [SD] age, 35.2 [13.8] years). A total of 4902 images were available for analysis, including 3386 from Durham (mean [SD], 31.9 [1.3] images per participant) and 1516 from Pittsburgh (mean [SD], 24.1 [0.5] images per participant). Images were evenly split between the 2 classes, with 2457 smoking images (50.1%) and 2445 nonsmoking images (49.9%). The final model discriminated smoking vs nonsmoking environments with a mean (SD) AUC of 0.840 (0.024) (accuracy [SD], 76.5% [1.6%]). A model trained only with images from Durham participants effectively classified images from Pittsburgh participants (AUC, 0.757; accuracy, 69.2%), and a model trained only with images from Pittsburgh participants effectively classified images from Durham participants (AUC, 0.821; accuracy, 75.0%), suggesting good generalizability between geographic areas. Only 1 expert's performance was a statistically significant improvement compared with the classifier (α = .05). Median self-reported craving was significantly correlated with model-predicted smoking environment status (ρ = 0.894; P = .003).Conclusions and relevanceIn this study, features of daily environments predicted smoking vs nonsmoking status consistently across participants. The findings suggest that a deep learning approach can identify environments associated with smoking, can predict the probability that any image of daily life represents a smoking environment, and can potentially trigger environment-based interventions. This work demonstrates a framework for predicting how daily environments may influence target behaviors or symptoms that may have broad applications in mental and physical health.

Dataset Information

Phenotyping urban built and natural environments with high-resolution satellite images and unsupervised deep learning.

Publications

Phenotyping urban built and natural environments with high-resolution satellite images and unsupervised deep learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets