Due to the rapid urbanization in the context of the conventional linear economy, the vulnerability of the urban ecosystem to climate change has increased. As a result, connecting urban ecosystem services of different urban land uses is imperative for urban sustainability and resilience. In conventional land use planning, urban agriculture (UA) and urban stormwater management are treated as separate economic sectors with different-disconnected-ecosystem services. Furthermore, few studies have synthesized knowledge regarding the potential impacts of integration of UA and stormwater green infrastructures (GIs) on the quantity and quality of urban ecosystem services of both economic sectors. This study provides a detailed analysis of the imperative question—how should a city integrate the developments of both urban agriculture and stormwater green infrastructure to overcome barriers while enhancing the ecosystem services? To answer this question, we conducted an extensive literature review. The results show that integrating UA with GIs can enhance urban food production while protecting urban water quality. This paper provides an initial context and mechanisms for future researchers and city planners regarding the manner in which the synergies between UA and stormwater GIs can create greater value for the wellbeing of urban ecosystems and resilience in the circular economy.
1 January 2021 in Computational Intelligence and Neuroscience
Hyperspectral imaging is an area of active research with many applications in remote sensing, mineral exploration, and environmental monitoring. Deep learning and, in particular, convolution‐based approaches are the current state‐of‐the‐art classification models. However, in the presence of noisy hyperspectral datasets, these deep convolutional neural networks underperform. In this paper, we proposed a feature augmentation approach to increase noise resistance in imbalanced hyperspectral classification. Our method calculates context‐based features, and it uses a deep convolutional neuronet (DCN). We tested our proposed approach on the Pavia datasets and compared three models, DCN, PCA + DCN, and our context‐based DCN, using the original datasets and the datasets plus noise. Our experimental results show that DCN and PCA + DCN perform well on the original datasets but not on the noisy datasets. Our robust context‐based DCN was able to outperform others in the presence of noise and was able to maintain a comparable classification accuracy on clean hyperspectral images.