Abstract. The absence of a compiled large-scale catchment characteristics dataset is a key obstacle limiting the development of large-sample hydrology research in China. We introduce the first large-scale catchment attribute dataset in China. We compiled diverse data sources, including soil, land cover, climate, topography, and geology, to develop the dataset. The dataset also includes catchment-scale 31-year meteorological time series from 1990 to 2020 for each basin. Potential evapotranspiration time series based on Penman's equation are derived for each basin. The 4911 catchments included in the dataset cover all of China. We introduced several new indicators that describe the catchment geography and the underlying surface differently from previously proposed datasets. The resulting dataset has a total of 125 catchment attributes and includes a separate HydroMLYR (hydrology dataset for machine learning in the Yellow River Basin) dataset containing standardized weekly averaged streamflow for 102 basins in the Yellow River Basin. The standardized streamflow data should be able to support machine learning hydrology research in the Yellow River Basin. The dataset is freely available at https://doi.org/10.5281/zenodo.5729444 (Zhen et al., 2021). In addition, the accompanying code used to generate the dataset is freely available at https://github.com/haozhen315/CCAM-China-Catchment-Attributes-and-Meteorology-dataset (last access: 26 November 2021) and supports the generation of catchment characteristics for any custom basin boundaries. Compiled data for the 4911 basins covering all of China and the open-source code should be able to support the study of any selected basins rather than being limited to only a few basins.
Semantic segmentation has been a fundamental task in interpreting remote sensing imagery (RSI) for various downstream applications. Due to the high intra-class variants and inter-class similarities, inflexibly transferring natural image-specific networks to RSI is inadvisable. To enhance the distinguishability of learnt representations, attention modules were developed and applied to RSI, resulting in satisfactory improvements. However, these designs capture contextual information by equally handling all the pixels regardless of whether they around edges. Therefore, blurry boundaries are generated, rising high uncertainties in classifying vast adjacent pixels. Hereby, we propose an edge distribution attention module (EDA) to highlight the edge distributions of leant feature maps in a self-attentive fashion. In this module, we first formulate and model column-wise and row-wise edge attention maps based on covariance matrix analysis. Furthermore, a hybrid attention module (HAM) that emphasizes the edge distributions and position-wise dependencies is devised combing with non-local block. Consequently, a conceptually end-to-end neural network, termed as EDENet, is proposed to integrate HAM hierarchically for the detailed strengthening of multi-level representations. EDENet implicitly learns representative and discriminative features, providing available and reasonable cues for dense prediction. The experimental results evaluated on ISPRS Vaihingen, Potsdam and DeepGlobe datasets show the efficacy and superiority to the state-of-the-art methods on overall accuracy (OA) and mean intersection over union (mIoU). In addition, the ablation study further validates the effects of EDA.
Semantic segmentation of remote sensing imagery is a fundamental task in intelligent interpretation. Since deep convolutional neural networks (DCNNs) performed considerable insight in learning implicit representations from data, numerous works in recent years have transferred the DCNN-based model to remote sensing data analysis. However, the wide-range observation areas, complex and diverse objects and illumination and imaging angle influence the pixels easily confused, leading to undesirable results. Therefore, a remote sensing imagery semantic segmentation neural network, named HCANet, is proposed to generate representative and discriminative representations for dense predictions. HCANet hybridizes cross-level contextual and attentive representations to emphasize the distinguishability of learned features. First of all, a cross-level contextual representation module (CCRM) is devised to exploit and harness the superpixel contextual information. Moreover, a hybrid representation enhancement module (HREM) is designed to fuse cross-level contextual and self-attentive representations flexibly. Furthermore, the decoder incorporates DUpsampling operation to boost the efficiency losslessly. The extensive experiments are implemented on the Vaihingen and Potsdam benchmarks. In addition, the results indicate that HCANet achieves excellent performance on overall accuracy and mean intersection over union. In addition, the ablation study further verifies the superiority of CCRM.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.