No abstract

No abstract

Due to the large volume of sewage in China, the efficiency of water consumption evaluated by the traditional model may be inaccurate. This paper evaluates the water consumption efficiency more scientifically. First, this paper uses the CCR model to evaluate the resource efficiency and environmental efficiency separately. The latter is generally lower than the former, which means the issue of water pollution is more serious than the problem of water resource consumption. Then, the water consumption efficiency is integrally evaluated by an eco-inefficiency model which focuses on undesirable outputs. The results are in good agreement with the results of the CCR model: (1) Only Beijing, Tianjin, and Shanghai are eco-efficient in terms of water consumption, water consumption efficiency in the southeastern coastal areas is higher than in the Midwest, and the overall water environment is bad; (2) China needs to focus on reducing industrial wastewater; (3) the output of water consumption has a lot of room for improvement; and (4) the output improvement schemes of all provinces have some similarities and are related to many features. So, this paper has made a clustering analysis of the improvement schemes and given detailed suggestions for improving the eco-efficiency of water consumption in China according to the clustering result.

No abstract

Traditional remote sensing (RS) image classification methods heavily rely on labeled samples for model training. When labeled samples are unavailable or labeled samples have different distributions from that of the samples to be classified, the classification model may fail. The cross-domain or crossscene remote sensing image classification is developed for this case where an existing image for training and an unknown image from different scenes or domains for classification. The distribution inconsistency problem may be caused by the differences in acquisition environment conditions, acquisition scene, acquisition time or/and changing sensors. To cope with the cross-domain remote sensing image classification problem, many domain adaptation (DA) techniques have been developed. In this article, we review DA methods in the fields of RS, especially hyperspectral image classification, and provide a survey of DA methods into traditional shallow DA methods (e.g., instance-based, featurebased, and classifier-based adaptations) and recently developed deep DA methods (e.g., discrepancy-based and adversarial-based adaptations).