From the sustainability science point of view, sustainable development is a three-dimensional (3D), discretized state transition problem, where the dimension is determined by the core concept of sustainability, which is triple-bottom-line based, and the state transition reflects a fundamental feature of sustainability development. These require continuous sustainability assessment, decision analysis, and action taking. In this paper, we formulate sustainability analysis problems as a general vector-based analysis problem, where the sustainability vector is characterized by the degree of system status change and the direction in a 3D sustainability space. To quantify the balance of triple-bottom-line-based development, we introduce a parameter called the development imbalance angle. We describe a sustainability space partition method, by which a number of zones in the space can be defined and featured. As a sustainability improvement process involves a series of sustainability state transitions, we apply a vector analysis technique to capture key features of state transition options. In addition, we introduce an algorithm to streamline the analysis tasks in a systematic way. A case study on sustainable biodiesel manufacturing is presented to demonstrate the key features and applicability of the proposed methodology.
Image-to-image translation is to learn a mapping between images from a source domain and images from a target domain. In this paper, we introduce the attention mechanism directly to the generative adversarial network (GAN) architecture and propose a novel spatial attention GAN model (SPA-GAN) for image-to-image translation tasks. SPA-GAN computes the attention in its discriminator and use it to help the generator focus more on the most discriminative regions between the source and target domains, leading to more realistic output images. We also find it helpful to introduce an additional feature map loss in SPA-GAN training to preserve domain specific features during translation. Compared with existing attentionguided GAN models, SPA-GAN is a lightweight model that does not need additional attention networks or supervision. Qualitative and quantitative comparison against state-of-the-art methods on benchmark datasets demonstrates the superior performance of SPA-GAN.
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.