Search

Abstract Accurate rainfall measurement with a precise spatial and temporal resolution is essential for making informed decisions during disasters and conducting scientific studies, particularly in regions characterized by intricate terrain and limited coverage of automated weather stations. Retrieval of precipitation with satellite is currently the most effective means to obtain precipitation over large‐scale areas. The key to enhancing the accuracy of precipitation estimation and forecasting in regions with complex terrain lies in effectively integrating satellite data with topographic information. This paper introduces a deep learning approach called AttUnet_R_SFT that utilizes high temporal, spatial, and spectral resolution data obtained from the Fengyun 4A satellite, and incorporates the Deep Spatial Feature Transform (SFT) layer to incorporate geographical data for estimating half‐hourly precipitation in northeastern China. We assess it by compared to operational near‐real‐time satellite precipitation products demonstrated to be successful in estimating precipitation and baseline deep learning models. According to the experimental findings, the AttUnet_R_SFT model outperforms practical precipitation products and baseline deep learning models in both identifying and estimating precipitation. The main enhancement of the model performance is shown in the windward slope of the Greater Khingan Mountains as a result of the successful incorporation of geographical data. Hence, the suggested framework holds the capability to function as a superior and dependable satellite‐derived precipitation estimation solution in regions characterized by intricate terrain and infrequent rainfall. The findings of this study indicate that the utilization of deep learning algorithms for satellite precipitation estimation shows potential as a fruitful avenue for further research.

Ocean observation technology is an important means to effectively manage ocean affairs and exercise national sovereignty. The autonomy and controllability of ocean observation technology is of great significance to China. Innovation and application are the core of realizing the autonomy and controllability of ocean observation technology, and ocean observation network is the carrier for realizing the innovation and application of ocean observation technology. The paper sorted out the development history of the three major observation networks in the United States (Global Ocean Observing System, Integrated Ocean Observing System and Ocean Observation Initiative), and put forward the view that the government had played a leading role in the organization, implementation and management of the development of ocean observation technology represented by the observation network. According to the current situation of ocean observation in China, drawing on the development experience of the American ocean observation network, it put forward suggestions for the organization, implementation, management and development of China's ocean observation network based on innovation and application.

Abstract Considering the multi-functionalization of ligands, it is crucial for ligand molecular design to reveal the landscape of anchoring sites. Here, a typical triphenylphosphine (TPP) ligand was employed to explore its effect on the surface of CsPbI3 perovskite nanocrystals (PNCs). Except for the conventionally considered P-Pb coordination, an P-I supramolecular halogen bonding was also found on the NC surface. The coexistence of the above two types of bonding significantly increased the formation energy of iodine vacancy defects and improved the photoluminescence quantum yield of PNCs up to 93%. Meanwhile, the direct interaction of P and I enhanced the stability of the Pb-I octahedra and dramatically inhibited the migration of I ions. Furthermore, the introduction of additional benzene rings (2-(Diphenylphosphino)-biphenyl (DPB)) increased the delocalized properties of the PNC surface and significantly improved the charge transport of the PNCs. As a result, the DPB passivated CsPbI3 NCs based top-emitting LEDs exhibite a peak external quantum efficiency (EQE) of 22.8%, a maximum luminance of 15, 204 cd m−2, and an extremely low-efficiency roll-off of 2.6% at the current density of 500 mA cm−2.

Reliable near-real-time precipitation estimation is crucial for scientific research and resistance to natural disasters such as floods. Compared with ground-based precipitation measurements, satellite-based precipitation measurements have great advantages, but precipitation estimation based on satellite is still a challenging issue. In this paper, we propose a deep learning model named Attention-Unet for precipitation estimation. The model utilizes the high temporal, spatial and spectral resolution data of the FY4A satellite to improve the accuracy of precipitation estimation. To evaluate the effectiveness of the proposed model, we compare it with operational near-real-time satellite-based precipitation products and deep learning models which proved to be effective in precipitation estimation. We use classification metrics such as Probability of detection (POD), False Alarm Ratio (FAR), Critical success index (CSI), and regression metrics including Root Mean Square Error (RMSE) and Pearson correlation coefficient (CC) to evaluate the performance of precipitation identification and precipitation amounts estimation, respectively. Furthermore, we select an extreme precipitation event to validate the generalization ability of our proposed model. Statistics and visualizations of the experimental results show the proposed model has better performance than operational precipitation products and baseline deep learning models in both precipitation identification and precipitation amounts estimation. Therefore, the proposed model has the potential to serve as a more accurate and reliable satellite-based precipitation estimation product. This study suggests that applying an appropriate deep learning algorithm may provide an opportunity to improve the quality of satellite-based precipitation products.

Recurrent neural networks (RNNs) have been widely used to solve sequence problems due to their capability of modeling temporal dependency. Despite the rich varieties of RNN models proposed in the literature, the problem of different sampling rates or performing speeds in sequence tasks has not been explicitly considered in the network and the corresponding training and testing processes. This paper addresses the problem of different sampling rates or performing speeds in the skeleton-based action recognition with RNNs. Specifically, the recently proposed independently recurrent neural network (IndRNN) is used as the RNN network due to its well-behaved and easily regulated gradient backpropagation through time. Samples are extracted with variable sampling rates and thus of different lengths, then processed by IndRNN with different time steps. In order to accommodate the differences in terms of gradients introduced by the backpropagation through time under variable time steps, a learning rate adjustment method is further proposed in the paper. Different learning rate adjustment factors are obtained for different layers by analyzing the gradient behavior under IndRNN. Experiments on skeleton-based action recognition are conducted to verify its effectiveness, and the results show that the proposed variable rate IndRNN network can significantly improve the performance over the RNN models under the conventional training strategies.

This paper presents a new IndRNN-based deep attention model, termed DA-IndRNN, for skeleton-based action recognition to effectively model the fact that different joints are usually of different degrees of importance to different action categories. The model consists of (a) a deep IndRNN as the main classification network to overcome the limitation of a shallow RNN network in order to obtain deeper and longer features, and (b) a deep attention network with multiple fully connected layers to estimate reliable attention weights. To train the DA-IndRNN, a new triplet loss function is proposed to guide the learning of the attention among different action categories. Specifically, this triplet loss enforces intra-class attention distances to be smaller than inter-class attention distances and at the same time to allow multiple attention weight patterns to exist for the same class. The proposed DA-IndRNN can be trained end-to-end. Experiments on the widely used datasets, including the NTU RGB + D dataset and UOW Large-Scale Combined (LSC) Dataset, have demonstrated that the proposed method can achieve better and stable performance than the state-of-the-art attention models.

Abstract Photovoltaic devices employing lead halide perovskites as the photoactive layer have attracted enormous attention due to their commercialization potential. Yet, there exists challenges on the way to the practical use of perovskite solar cells (PSCs), such as light stability and current–voltage (J–V ) hysteresis. Inorganic perovskite nanocrystals (IPNCs) are promising candidates for high‐performance photovoltaic devices due to their simple synthesis methods, tunable bandgap, and efficient photon downshifting effect for ultraviolet (UV) light blocking and conversion. In this work, CsPbBr3 IPNCs modification could give rise to the vapor phase and solution‐processed PSCs with a power conversion efficiency (PCE) of 16.4% and 20.8%, respectively, increased by 11.6% and 5.6% compared to the control devices for more efficient UV utilization and carrier recombination suppression. As far as is known, 11.6% is the most effective enhanced factor for PSCs based on photon downshifting effect inside of devices. The CsPbBr3 layer could also significantly retard light‐induced degradation, leading to the lifetime over 100 h under UV illumination for PSCs. Additionally, the modified PSCs exhibit weak hysteresis and multiple colors of fluorescence. These results shed light on the future design of combining a photon downshifting layer and carrier interfacial modification layer in the applications of perovskite optoelectronic devices.

Smartphone-sensors-based human activity recognition is attracting increasing interest due to the popularization of smartphones. It is a difficult long-range temporal recognition problem, especially with large intraclass distances such as carrying smartphones at different locations and small interclass distances such as taking a train or subway. To address this problem, we propose a new framework of combining short-term spatial/frequency feature extraction and a long-term independently recurrent neural network (IndRNN) for activity recognition. Considering the periodic characteristics of the sensor data, short-term temporal features are first extracted in the spatial and frequency domains. Then, the IndRNN, which can capture long-term patterns, is used to further obtain the long-term features for classification. Given the large differences when the smartphone is carried at different locations, a group-based location recognition is first developed to pinpoint the location of the smartphone. The Sussex-Huawei Locomotion (SHL) dataset from the SHL Challenge is used for evaluation. An earlier version of the proposed method won the second place award in the SHL Challenge 2020 (first place if not considering the multiple models fusion approach). The proposed method is further improved in this paper and achieves 80.72% accuracy, better than the existing methods using a single model.