Search

Scientometric reviews, facilitated by computational and visual analytical approaches, allow researchers to gain a thorough understanding of research trends and areas of concentration from a large number of publications. With the fast development of satellite altimetry, which has been effectively applied to a wide range of research topics, it is timely to summarize the scientific achievements of the previous 50 years and identify future trends in this field. A comprehensive overview of satellite altimetry was presented using a total of 8541 publications from the Web of Science Core Collection covering the years from 1970 to 2021. We begin by presenting the fundamental statistical results of the publications, such as the annual number of papers, study categories, countries/regions, afflictions, journals, authors, and keywords, in order to provide a comprehensive picture of satellite altimetry research. We discuss the co-occurrence of the authors in order to reveal the global collaboration network of satellite altimetry research. Finally, we utilised co-citation networks to detect the development trend and associated crucial publications for various specific topics. The findings show that satellite altimetry research has been changed immensely during the last half-century. The United States, France, China, England, and Germany made the most significant contributions in the field of satellite altimetry. The analysis reveals a clear link between technology advancements and the trend in satellite altimetry research. As a result, wide swath altimetry, GNSS-reflectometry, laser altimetry, terrestrial hydrology, and deep learning are among the most frontier study subjects. The findings of this work could guide a thorough understanding of satellite altimetry's overall development and research front. [ABSTRACT FROM AUTHOR]

Over the past four decades, Arctic sea ice coverage has steadily declined. This loss of sea ice has amplified solar radiation and heat absorption from the ocean, exacerbating both polar ice loss and global warming. It has also accelerated changes in sea ice movement, posing safety risks for ship navigation. In recent years, numerical prediction models have dominated the field of sea ice movement prediction. However, these models often rely on extensive data sources, which can be limited in specific time periods or regions, reducing their applicability. This study introduces a novel approach for predicting Arctic sea ice motion within a 10-day window. We employ a Self-Attention ConvLSTM deep learning network based on single-source data, specifically optical flow derived from the Advanced Microwave Scanning Radiometer Earth Observing System 36.5 GHz data, covering the entire Arctic region. Upon verification, our method shows a reduction of 0.80 to 1.18 km in average mean absolute error over a 10-day period when compared to ConvLSTM, demonstrating its improved ability to capture the spatiotemporal correlation of sea ice motion vector fields and provide accurate predictions. [ABSTRACT FROM AUTHOR]

With the development of deep learning techniques, convolutional neural networks (CNN) are increasingly being used in image recognition for marine surveys and underwater object classification. Automatic recognition of targets on side-scan sonar (SSS) images using CNN can improve recognition accuracy and efficiency. However, the vast selection of CNN models makes it challenging to select models for target recognition in SSS images. Therefore, this paper aims to compare different CNN models' prediction accuracy and computational performance comprehensively. First, four traditional CNN models were applied to train and predict the same submarine SSS dataset using both the original model and models with transfer learning methods. Then, we examined and studied the prediction accuracy and computation performance of four CNN models. Results showed that transfer learning enhances the accuracy of all CNN models, with lesser improvements for AlexNet and VGG-16 and greater improvements for GoogleNet and ResNet101. GoogleNet has the highest prediction of accuracy (100% in the train dataset and 94.27% in the test dataset) and good computational difficulty. The findings of this work are useful for future model selection in target recognition in SSS images. [ABSTRACT FROM AUTHOR]

In the Bering Sea slope, ocean eddies are essential physical processes that carry nutrients to the shelf. The development of the satellite altimeter has facilitated the observation of oceanic eddies. Attention networks are used as the core algorithm for eddy detection to suppress feature responses in irrelevant non-eddy areas, which can address the issue of sample imbalance in high-latitude ocean eddies. Furthermore, data from both the sea surface height (SSH) and geostrophic velocity were employed as model inputs to integrate more eddy-related properties. The results of ocean eddy detection using this method and the dataset allowed more eddies to be detected than with traditional vector geometry-based methods and only SSH-based models. This study also incorporated the results of multiple deep learning models to increase both the overall and single-day eddy detection efficiency. As a result, the algorithms in this paper show that attention networks and geostrophic velocity data are both appropriate for high-latitude ocean eddy identification. This makes a contribution to the further application of deep learning methods to satellite altimetry data. [ABSTRACT FROM AUTHOR]

Deep-learning (DL)-based object detection algorithms can greatly benefit the community at large in fighting fires, advancing climate intelligence, and reducing health complications caused by hazardous smoke particles. Existing DL-based techniques, which are mostly based on convolutional networks, have proven to be effective in wildfire detection. However, there is still room for improvement. First, existing methods tend to have some commercial aspects, with limited publicly available data and models. In addition, studies aiming at the detection of wildfires at the incipient stage are rare. Smoke columns at this stage tend to be small, shallow, and often far from view, with low visibility. This makes finding and labeling enough data to train an efficient deep learning model very challenging. Finally, the inherent locality of convolution operators limits their ability to model long-range correlations between objects in an image. Recently, encoder–decoder transformers have emerged as interesting solutions beyond natural language processing to help capture global dependencies via self- and inter-attention mechanisms. We propose Nemo: a set of evolving, free, and open-source datasets, processed in standard COCO format, and wildfire smoke and fine-grained smoke density detectors, for use by the research community. We adapt Facebook's DEtection TRansformer (DETR) to wildfire detection, which results in a much simpler technique, where the detection does not rely on convolution filters and anchors. Nemo is the first open-source benchmark for wildfire smoke density detection and Transformer-based wildfire smoke detection tailored to the early incipient stage. Two popular object detection algorithms (Faster R-CNN and RetinaNet) are used as alternatives and baselines for extensive evaluation. Our results confirm the superior performance of the transformer-based method in wildfire smoke detection across different object sizes. Moreover, we tested our model with 95 video sequences of wildfire starts from the public HPWREN database. Our model detected 97.9% of the fires in the incipient stage and 80% within 5 min from the start. On average, our model detected wildfire smoke within 3.6 min from the start, outperforming the baselines. [ABSTRACT FROM AUTHOR]