Search

Monitoring of volcanic eruptions, the atmosphere, and the ocean, along with their scientific understanding, can be achieved through multifaceted observations that include camera images, topographic deformations, elastic waves, geology, and the chemical constituents and temperatures of air and water. However, regions of increased volcanic activity and/or shallow waters are difficult to access by crewed ship due to danger or grounding risk. To overcome these difficulties, we used an uncrewed surface vessel (USV), Bluebottle, to operate multiple observation around oceanic volcanoes in the Bonin Island arc in May 2023. Even under adverse sea conditions, the USV successfully reached a remote observation site, Nishinoshima volcano, which is about 130 km away from Chichijima Island where the USV started out from. The USV conducted five days of observations at shallower than 500 m water depth around Nishinoshima Island, the first time after violent eruptions of Nishinoshima in June 2020. The USV is equipped with various sensors and data collection technologies, including a single-beam echosounder, oceanographic and meteorological sensors, an Acoustic Doppler Current Profiler, and a time-lapse camera. These tools have provided a multi-dimensional view of the underwater landscape and marine conditions near the volcano for the first time in the world. We obtained new bathymetric data, sub-bottom images, and measurements of temperature, salinity, and pH. This study leverages advanced technologies and innovative methodologies to enhance our understanding of marine and geological phenomena.

Abstract Focal segmental glomerulosclerosis (FSGS) is a common glomerular injury leading to end-stage renal disease. Monogenic FSGS is primarily ascribed to decreased podocyte integrity. Variants between residues 184 and 245 of INF2, an actin assembly factor, produce the monogenic FSGS phenotype. Meanwhile, variants between residues 57 and 184 cause a dual-faceted disease involving peripheral neurons and podocytes (Charcot–Marie–Tooth CMT/FSGS). To understand the molecular basis for INF2 disorders, we compared structural and cytoskeletal effects of INF2 variants classified into two subgroups: One (G73D, V108D) causes the CMT/FSGS phenotype, and the other (T161N, N202S) produces monogenic FSGS. Molecular dynamics analysis revealed that all INF2 variants show distinct flexibility compared to the wild-type INF2 and could affect stability of an intramolecular interaction between their N- and C-terminal segments. Immunocytochemistry of cells expressing INF2 variants showed fewer actin stress fibers, and disorganization of cytoplasmic microtubule arrays. Notably, CMT/FSGS variants caused more prominent changes in mitochondrial distribution and fragmentation than FSGS variants and these changes correlated with the severity of cytoskeletal disruption. Our results indicate that CMT/FSGS variants are associated with more severe global cellular defects caused by disrupted cytoskeleton-organelle interactions than are FSGS variants. Further study is needed to clarify tissue-specific pathways and/or cellular functions implicated in FSGS and CMT phenotypes

Marine plastic pollution is a pressing global issue nowadays. To address this problem, automated image analysis techniques that can identify plastic litter are necessary for scientific research and coastal management purposes. The Beach Plastic Litter Dataset version 1 (BePLi Dataset v1) comprises 3709 original images taken in various coastal environments, along with instance-based and pixel-level annotations for all plastic litter objects visible in the images. The annotations were compiled in the Microsoft Common Objects in Context (MS COCO) format, which was partially modified from the original format. The dataset enables the development of machine-learning models for instance-level and/or pixel-wise identification of beach plastic litter. All original images in the dataset were extracted from beach litter monitoring records operated by the local government of Yamagata Prefecture in Japan. Litter images were taken in different backgrounds, such as sand beaches, rocky beaches, and tetrapods. The annotations for instance segmentation of beach plastic litter were made manually, and were given for all plastics objects, including PET bottles, containers, fishing gear, and styrene foams,all of which were categorized in a single class “plastic litter”. Technologies developed using this dataset have the potential to enable further scalability for the estimation of plastic litter volume. This would help researchers, including individuals, and the the government to monitor or analyze beach litter and the corresponding pollution levels.

This dataset is a time series of tropical cyclones simulated using the high-resolution Nonhydrostatic Icosahedral Atmospheric Model (NICAM). By tracking tropical cyclones from 30 years of simulation data, 2,463 tracks that include the life stages of precursors (pre-TCs), tropical cyclones (TCs), and post-tropical cyclones (post-TCs), if any, were extracted. Each track data includes the time, latitude, longitude, maximum wind speed, minimum pressure, elapsed time since onset, and life-stage label of the tropical cyclone. The numbers of steps (6 h) for pre-TCs, TCs, and post-TCs were 45,288, 55,206, and 37,312, respectively. The dataset for each step also consists of atmospheric field data of multiple physical quantities, such as outgoing longwave radiation at the top-of-the-atmosphere, sea level pressure, sea surface temperature, specific humidity at 600 hPa, and zonal and meridional winds at 850 and 200 hPa over a 1000 km2 area that includes a tropical cyclone at its center. This dataset can be used to develop machine-learning models for the detection, intensity prediction, and cyclogenesis prediction of tropical cyclones.

A common observation in the field of pattern recognition for atmospheric phenomena using supervised machine learning is that recognition performance decreases for events with few observed cases, such as extreme weather events. Here, we aimed to mitigate this issue by using numerical simulation and satellite observational data for training. However, as simulation and observational data possess distinct characteristics, we employed neural style transformation learning to transform the simulation data to more closely resemble the observational data. The resulting transformed cloud images of the simulation data were found to possess physical features comparable to those of the observational data. By utilizing the transformed data for training, we successfully improved the classification performance of cloud images of tropical cyclone precursors 7, 5, and 3 days before their formation by 40.5, 90.3, and 41.3%, respectively.

Abstract Image data classification using machine learning is an effective method for detecting atmospheric phenomena. However, extreme weather events with a small number of cases cause a decrease in classification prediction accuracy owing to the imbalance in data between the target class and the other classes. To build a highly accurate classification model, I held a data analysis competition to determine the best classification performance for two classes of cloud image data, specifically tropical cyclones including precursors and other classes. For the top models in the competition, minority data oversampling, majority data undersampling, ensemble learning, deep layer neural networks, and cost-effective loss functions were used to improve the classification performance of the imbalanced data. In particular, the best model of 209 submissions succeeded in improving the classification capability by 65.4% over similar conventional methods in a measure of the low false alarm ratio.

This dataset consists of 3500 images of beach litter and 3500 corresponding pixel-wise labelled images. Although performing such pixel-by-pixel semantic masking is expensive, it allows us to build machine-learning models that can perform more sophisticated automated visual processing. We believe this dataset may be of significance to the scientific communities concerned with marine pollution and computer vision, as this dataset can be used for benchmarking in the tasks involving the evaluation of marine pollution with various machine learning models. The beach litter images were obtained from coastal environment surveys conducted between 2011 and 2019 by the Yamagata Prefectural Government, Japan. These images were originally obtained owing to the reporting guidelines concerning regular coastal-environmental-cleanup and beach-litter-monitoring surveys. Based on these images, the Japan Agency for Marine-Earth Science and Technology created 3500 images comprising eight classes of semantic masks for beach litter detection [1].

Abstract Background Mutations in the Wilms tumor 1 gene cause a spectrum of podocytopathy ranging from diffuse mesangial sclerosis to focal segmental glomerulosclerosis. In a considerable fraction of patients with Wilms tumor 1 mutations, the distinctive histology of immune-complex-type glomerulonephritis has been reported. However, the clinical relevance and etiologic mechanisms remain unknown. Case presentation A 5-year-old child presented with steroid-resistant nephrotic range proteinuria. Initial renal biopsy revealed predominant diffuse mesangial proliferation with a double-contour and coexisting milder changes of focal segmental glomerulosclerosis. Immunofluorescence and electron microscopy revealed a full-house-pattern deposition of immune complexes in the subendothelial and paramesangial areas. Serial biopsies at 6 and 8 years of age revealed that more remarkable changes of focal segmental glomerulosclerosis had developed on top of the initial proliferative glomerulonephritis. Identification of a de novo Wilms tumor 1 splice donor-site mutation in intron 9 (NM_024426.6:c.1447 + 4C > T) and 46,XY-gonadal dysgenesis led to the diagnosis of Frasier syndrome. Conclusions Our findings, together with those of others, point to the importance of heterogeneity in clinicopathological phenotypes caused by Wilms tumor 1 mutations and suggest that immune-complex-mediated membranoproliferative glomerulopathy should be considered as a histological variant.

Abstract Analyses of large ensemble data on future climate are significantly useful for the probabilistic future projection of climate change in various interdisciplinary fields. However, the data volume of the Database for Policy Decision making for Future climate change or d4PDF, which is a mega-ensemble dataset, exceeds ∼ 3 PB, which is too large to download to local computers. To allow users for retrieve and downloading necessary data, we developed a user-friendly system called “System for Efficient content-based retrieval to Analyze Large volume climate data” (SEAL) under the Social Implementation Program on Climate Change Adaptation Technology (SI-CAT). Conventional web-based retrieval systems allow retrievals using metadata associated with a data file itself. In contrast, SEAL allows the users to retrieve the necessary data by using metadata associated with contents, such as physical values, of a data file. We confirmed that SEAL can reduce data sizes and total time required for obtaining necessary data to less than 0.5% and 1%, respectively, compared to conventional web-based retrieval systems.

Atmospheric simulation data present richer information in terms of spatiotemporal resolution, spatial dimension, and the number of physical quantities compared to observational data; however, such simulations do not perfectly correspond to the real atmospheric conditions. Additionally, extensive simulation data aids machine learning-based image classification in atmospheric science. In this study, we applied a machine learning model for tropical cyclone detection, which was trained using both simulation and satellite observation data. Consequently, the classification performance was significantly lower than that obtained with the application of simulation data. Owing to the large gap between the simulation and observation data, the classification model could not be practically trained only on the simulation data. Thus, the representation capability of the simulation data must be analyzed and integrated into the observation data for application in real problems.

Abstract We propose a deep learning approach for identifying tropical cyclones (TCs) and their precursors. Twenty year simulated outgoing longwave radiation (OLR) calculated using a cloud-resolving global atmospheric simulation is used for training two-dimensional deep convolutional neural networks (CNNs). The CNNs are trained with 50,000 TCs and their precursors and 500,000 non-TC data for binary classification. Ensemble CNN classifiers are applied to 10 year independent global OLR data for detecting precursors and TCs. The performance of the CNNs is investigated for various basins, seasons, and lead times. The CNN model successfully detects TCs and their precursors in the western North Pacific in the period from July to November with a probability of detection (POD) of 79.9–89.1% and a false alarm ratio (FAR) of 32.8–53.4%. Detection results include 91.2%, 77.8%, and 74.8% of precursors 2, 5, and 7 days before their formation, respectively, in the western North Pacific. Furthermore, although the detection performance is correlated with the amount of training data and TC lifetimes, it is possible to achieve high detectability with a POD exceeding 70% and a FAR below 50% during TC season for several ocean basins, such as the North Atlantic, with a limited sample size and short lifetime.

The comprehensive production of detailed bathymetric maps is important for disaster prevention, resource exploration, safe navigation, marine salvage, and monitoring of marine organisms. However, owing to observation difficulties, the amount of data on the world’s seabed topography is scarce. Therefore, it is essential to develop methods that effectively use the limited data. In this study, based on dictionary learning and sparse coding, we modified the super-resolution technique and applied it to seafloor topographical maps. Improving on the conventional method, before dictionary learning, we performed pre-processing to separate the teacher image into a low-frequency component that has a general structure and a high-frequency component that captures the detailed topographical features. We learn the topographical features by training the dictionary. As a result, the root-mean-square error (RMSE) was reduced by 30% compared with bicubic interpolation and accuracy was improved, especially in the rugged part of the terrain. The proposed method, which learns a dictionary to capture topographical features and reconstructs them using a dictionary, produces super-resolution with high interpretability.