The management of stormwater runoff via distributed green infrastructures delivers a number of environmental services that go beyond the reduction of flood risk, which has been the focus of conventional stormwater systems. Not all of these services may be equally valued by the public, however. This paper estimates households' willingness to pay (WTP) for improvements in water security, stream health, recreational and amenity values, as well as reduction in flood risk and urban heat island effect. We use data from nearly 1000 personal interviews with residential homeowners in Melbourne and Sydney, Australia. Our results suggest that the WTP for the highest levels of all environmental services is A$799 per household per year. WTP is mainly driven by residents valuing improvements in local stream health, exemptions in water restrictions, the prevention of flash flooding, and decreased peak urban temperatures respectively at
This study examines how research on smart water is contributing to climate-resilient municipal water systems around the globe. We identify smart water research trends over time, relationships with climate adaptation and mitigation goals, and applicability to places with developed or developing water and electrical infrastructure. To do so, we systematically review the literature, identifying research on Information Communication Technology-enabled technologies related to water supply, wastewater, and stormwater management. We assess the relationship between each study and climate adaptation and mitigation objectives: managing greater variation in water quantity, leading to scarcity and increased stormwater; managing declining water quality; and low-carbon water systems. We find 96 relevant studies and identify five major categories of research addressing climate adaptation and mitigation: monitoring, modeling, system design, system feedbacks, and uptake and implementation. We find there is a recent acceleration in smart water research, with a concentration of studies focused on modeling. There is an emphasis on water efficiency using data from Advanced Metering Infrastructure, which is most applicable to cities with developed water grids and consistent electrical supplies. Secondarily, there is a concentration of work using distributed sensors for early detection of water quality degradation, which is being done in all municipal contexts. There is far less research on uptake and implementation of smart approaches, especially at the institutional level. In addition, there is relatively little work that explicitly relates smart water technologies to reducing greenhouse gas emissions. While smart water approaches are applicable everywhere, there is a need to for expanded focus on areas without developed water grids or consistent electricity for smart water to meaningfully contribute to Sustainable Development Goal 6.
To analyze types and patterns of greening trends across a city, this study seeks to identify a method of creating very high-resolution urban vegetation maps that scales over space and time. Vegetation poses unique challenges for image segmentation because it is patchy, has ragged boundaries, and high in-class heterogeneity. Existing and emerging public datasets with the spatial resolution necessary to identify granular urban vegetation lack a depth of affordable and accessible labeled training data, making unsupervised segmentation desirable. This study evaluates three unsupervised methods of segmenting urban vegetation: clustering with k-means using k-means++ seeding; clustering with a Gaussian Mixture Model (GMM); and an unsupervised, backpropagating convolutional neural network (CNN) with simple iterative linear clustering superpixels. When benchmarked against internal validity metrics and hand-coded data, k-means is more accurate than GMM and CNN in segmenting urban vegetation. K-means is not able to differentiate between water and shadows, however, and when this segment is important GMM is best for probabilistically identifying secondary land cover class membership. Though we find the unsupervised CNN shows high degrees of accuracy on built urban landscape features, its accuracy when segmenting vegetation does not justify its complexity. Despite limitations, for segmenting urban vegetation, k-means has the highest performance, is the simplest, and is more efficient than alternatives.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.