NDVI Threshold-Based Urban Green Space Mapping from Sentinel-2A at the Local Governmental Area (LGA) Level of Victoria, Australia

Unraveling nonlinear effects of environment features on green view index using multiple data sources and explainable machine learning

Urban greening plays a crucial role in maintaining environmental sustainability and enhancing people's well-being. However, limited by the shortcomings of traditional methods, studying the heterogeneity and nonlinearity between environmental factors and green view index (GVI) still faces many challenges. To address the concerns of nonlinearity, spatial heterogeneity, and interpretability, an interpretable spatial machine learning framework incorporating the Geographically Weighted Random Forest (GWRF) model and the SHapley Additive exPlanation (Shap) model is proposed in this paper. In this paper, we combine multi-source big data, such as Baidu Street View data and remote sensing images, and utilize semantic segmentation models and geographic data processing techniques to study the global and local interpretation of the Beijing region with GVI as the key indicator. Our research results show that: (1) Within the Sixth Ring Road of Beijing, GVI shows significant spatial clustering phenomenon and positive correlation linkage, and at the same time exhibits significant spatial differences; (2) Among many environmental variables, the increase of green coverage rate has the most significant positive effect on GVI, while the increase of building density shows a strong negative correlation with GVI; (3) The performance of the GWRF model in predicting GVI is excellent and far exceeds that of comparison models.; (4) Whether it is the green coverage rate, urban built environment or socioeconomic factors, their influence on GVI shows non-linear characteristics and a certain threshold effect. With the help of these non-linear influences and explicit threshold effects, quantitative analyses of greening are provided, which can help to assist urban planners in making more scientific and rational decisions when allocating greening resources.

Are area-level socioeconomic inequalities in obesity moderated by neighbourhood greenery?

BACKGROUND

Reducing socioeconomic inequalities in obesity is a public health priority. Limited research exists on the role of neighbourhood environmental attributes in mitigating these inequalities. However, it has been shown that neighbourhoods with more greenery tend to have lower levels of socioeconomic inequalities in non-obesity health outcomes. We examined whether neighbourhood greenery moderates the association of area-level socioeconomic status (SES) with waist circumference.

METHODS

Data from 3,261 middle-aged and older adults who participated in a national cohort study conducted in Australia (2011-12) were used. The outcome was objectively measured waist circumference. For area-level SES, a composite index of disadvantage based on census data was used. We used two measures of neighbourhood greenery: mean greenness and geographic size of greenspace. They were assessed using the Normalized Difference Vegetation Index (NDVI) within 0.5, 1, and 2 km radius buffers around participants' homes. The mean NDVI value within each buffer area was used for the former, and the geographic size of the area with NDVI ≥ 0.6 (dense greenery) was used for the latter.

RESULTS

There was a significant negative association between area-level SES and waist circumference: one standard deviation higher score in the area-level SES indicator (less disadvantage) was associated with 1.76 cm (95% CI: -2.68, -0.83) lower waist circumference. Analyses stratified by greenery levels found similar significant associations in the areas with low and high levels of greenery but not in the areas with medium levels of greenery for both greenery measures within 1 km and 2 km buffers.

CONCLUSIONS

Consistent with previous studies, our study found that participants living in disadvantaged suburbs were likely to have a larger waist circumference than those living in advantaged suburbs. However, we also found that such socioeconomic inequalities in obesity were mitigated in the areas with medium levels of greenery for this sample of Australian adults. Our findings suggest that there may be an optimum level of greenery where inequalities in obesity are alleviated. Further research is needed to understand the mechanisms underlying these findings.

A local perspective on the links between flora biodiversity and ecosystem services in the northwest highlands of Ethiopia

The main concern that this study attempts to address is the reason that the local people sustainably conserve church forests while aggressively exploiting biodiversity in common forests, shrublands, and grasslands. The study assesses the local perspective on the links between flora biodiversity and ecosystem services across a range of management options in the typical watershed of the Northwest highlands of Ethiopia. A mixed study design that included questionnaires, remote sensing, and hermeneutics was used because of the multidisciplinary character of the research. There has been a perceptible decline in flora biodiversity in the open-access shrublands, forests, and grasslands as a result of increased settlement encroachment, unchecked and continuous overgrazing, excessive firewood collection, and the cutting of living and dead tree and shrub biomass. Because of this, it was noticed that the availability of wild edible plants, medicinal plants, trees to produce tools, habitat for wild animals, and lumber production is drastically reduced. Alternatively, the church forests were preserved with responsive caring, which enables the outstanding performance of the majority of ecosystem services (except for collecting firewood and fibers) for the local community with the principles of equality and inclusiveness. Therefore, to restore open-access communal grazing ecosystems and the synergy of many ecosystem services in a given watershed, an effective institutional structure must be developed at the local administration level. To offer a range of ecosystem services and socioeconomic benefits, reforestation and planting of both exotic and native plants with enclosure management established on the values of justice, equality, inclusivity, and well-managed local governance with strict laws, sanctions, and enforcement must be the cornerstones of the management plan.

Joint associations of neighbourhood walkability and greenery with walking among middle-aged and older adults: Findings from diverse urban settings in Australia

There is evidence that neighbourhood walkability and greenery are associated with walking, but less is known about their joint associations. We investigated this using data from the AusDiab3 study (2011/12) with 3032 adults (mean age 60 years). Two-level logistic regression models were used with binary walking outcomes. There was an inverse relationship (r = -0.5) between walkability (a composite measure of residential, destinations and intersections densities) and greenery (the size of densely vegetated areas). However, both walkability and greenery were independently positively associated with odds of walking. Regarding joint associations, in low-walkability neighbourhoods, greenery was positively associated with walking. In high-walkability neighbourhoods, greenery was not associated with walking.

Land use and land cover (LULC) performance modeling using machine learning algorithms: a case study of the city of Melbourne, Australia

Accurate spatial information on Land use and land cover (LULC) plays a crucial role in city planning. A widely used method of obtaining accurate LULC maps is a classification of the categories, which is one of the challenging problems. Attempts have been made considering spectral (Sp), statistical (St), and index-based (Ind) features in developing LULC maps for city planning. However, no work has been reported to automate LULC performance modeling for their robustness with machine learning (ML) algorithms. In this paper, we design seven schemes and automate the LULC performance modeling with six ML algorithms-Random Forest, Support Vector Machine with Linear kernel, Support Vector Machine with Radial basis function kernel, Artificial Neural Network, Naïve Bayes, and Generalised Linear Model for the city of Melbourne, Australia on Sentinel-2A images. Experimental results show that the Random Forest outperforms remaining ML algorithms in the classification accuracy (0.99) on all schemes. The robustness and statistical analysis of the ML algorithms (for example, Random Forest imparts over 0.99 F1-score for all five categories and p value [Formula: see text] 0.05 from Wilcoxon ranked test over accuracy measures) against varying training splits demonstrate the effectiveness of the proposed schemes. Thus, providing a robust measure of LULC maps in city planning.