Storage Resources Research Articles

The potential for CO2 storage in residual oil zones in onshore Australian basins

Geoscience Australia and CSIRO have collaborated to investigate whether residual oil zones (ROZs), sometimes associated with conventional Australian hydrocarbon plays, could provide a carbon dioxide (CO2) storage resource and enhance the storage capacity of depleted fields. Our petrophysical study demonstrates that ROZs occur in Australia’s hydrocarbon-rich regions, particularly in the Cooper-Eromanga Basin. ROZs with more than 10% residual oil saturation are uncommon, likely due to small original oil columns and lower residual saturations retained in sandstone reservoirs than in classic, carbonate-hosted North American ROZs. Extensive, reservoir-quality rock is found below the deepest occurring conventional oil in many of the fields in the Eromanga Basin, potentially offering significant CO2 storage capacity. Multiphase compositional flow modelling was used to estimate the CO2 storage efficiency of typical Australian ROZs. We developed a novel modelling methodology that first captures oil migration events leading to the formation of ROZs. Modelling CO2 storage over a 20-year injection period demonstrates that CO2-oil interactions increase the density and viscosity of CO2, enhancing CO2 sweep efficiency and lateral flow, improving storage efficiency. The extent of these effects depends on the quantity and spatial distribution of residual oil in place and the miscibility of CO2 at reservoir conditions.

Building a carbon storage portfolio for the Barrow and Dampier sub-basins – a national resource

The Australian government has recently legislated a 43% emissions reduction target for 2030 to drive net zero ambitions for 2050. The government plans for carbon capture and storage (CCS) to play a significant role in achieving this through greenhouse gas storage licence rounds. Rapid screening of Australia’s carbon storage opportunities is necessary to position future acreage release and ultimately identify and mature carbon storage sites. An industry collaboration between Geoscience Australia and SLB has conducted a basin-scale carbon storage assessment project for the Barrow and Dampier sub-basins. The project has built and modernised a subsurface database fit for CCS screening. The dataset was used as the foundation to create a carbon storage opportunity portfolio and storage resource assessment for the area. The project has three major streams: (1) CCS-focussed reprocessing, depth imaging and merging of 29 legacy seismic surveys covering 26,150 km2 – focussed on detailed image resolution for containment analysis. (2) A basin-wide audit of 1620 wells and databasing of available log data, 129 wells were carried through for petrophysical and rock physics analysis relevant to CCS. (3) A portfolio of carbon storage opportunities and associated capacity assessment for the Barrow–Dampier including saline aquifers and depleted fields ranked on storage capacity, reservoir and seal properties and integrity. The results of this study will be released via the National Offshore Petroleum Information Management System as a public resource to expedite CCS implementation for the region.

Development of long-distance and large-scale carbon capture and storage (CCS) value chain using liquefied CO2 ship transportation

Carbon capture and storage (CCS) is central to clean energy transition. Globally, potential aggregated carbon dioxide (CO2) storage resource capacity is ~13,000 billion tonnes. Assuming global greenhouse gas emissions of 51 billion tonnes per annum, CO2 storage capacity equates to 250 years of global emissions reduction. While there is significant momentum to deploy CCS technology for meeting Paris Agreement targets, the key challenge for offering CCS to all industrial sectors is that many major CO2 emission sources are located hundreds of kilometres away from geological storage sites. To address this key challenge, there is a need to develop a long-distance and large-scale CCS value chain that utilises liquefied CO2 (LCO2) ship transportation. This paper discusses key technical, commercial, and regulatory considerations that must be addressed in parallel for developing such a CCS value chain. More specifically, it will cover the following: (1) technical – CO2 liquefaction condition, CO2 supply specification and LCO2 ship parcel size; (2) commercial – business model (ownership of CO2 retained by emitters or transferred to CCS project proponent), CO2 supply or CCS facility lease terms and conditions; and (3) regulatory – domestic versus transboundary projects and associated needs for policy and legislative underpinning.

Tele-Trafficking of Virtual Data Storage Obtained from Smart Grid by Replicated Gluster in Syntose Environment

One of the most important developments in the energy industry is the evolution of smart grids, which record minute details of voltage levels, energy usage, and other critical electrical variables through General Packet Radio Service (GPRS)-enabled meters. This phenomenon creates an extensive dataset for the optimization of the grid system. However, the minute-by-minute energy details recorded by GPRS meters are challenging to store and manage in physical storage resources (old techniques lead to a memory shortage). This study investigates using the distributed file system, replicated Gluster, as a reliable storage option for handling and protecting the enormous volumes of data produced by smart grid components. This study performs two essential tasks. (1) The storage of virtual data received from GPRS meters and load flow analysis of SynerGee Electric 4.0 software from the smart grid (we have extracted electrical data from 16 outgoing feeders, distributed lines, in this manuscript). (2) Tele-trafficking is performed to check the performance of replicated Gluster (RG) for virtual data (electrical data received from the smart grid) storage in terms of User Datagram Protocol (UDP), Transmission Control Protocol (TCP), data flow, and jitter delays. This storage technique provides more opportuni11ty to analyze and perform smart techniques efficiently for future requirement, analysis, and load estimation in smart grids compared to traditional storage methods.

A Novel Lightweight Model for Underwater Image Enhancement.

Underwater images suffer from low contrast and color distortion. In order to improve the quality of underwater images and reduce storage and computational resources, this paper proposes a lightweight model Rep-UWnet to enhance underwater images. The model consists of a fully connected convolutional network and three densely connected RepConv blocks in series, with the input images connected to the output of each block with a Skip connection. First, the original underwater image is subjected to feature extraction by the SimSPPF module and is processed through feature summation with the original one to be produced as the input image. Then, the first convolutional layer with a kernel size of 3 × 3, generates 64 feature maps, and the multi-scale hybrid convolutional attention module enhances the useful features by reweighting the features of different channels. Second, three RepConv blocks are connected to reduce the number of parameters in extracting features and increase the test speed. Finally, a convolutional layer with 3 kernels generates enhanced underwater images. Our method reduces the number of parameters from 2.7 M to 0.45 M (around 83% reduction) but outperforms state-of-the-art algorithms by extensive experiments. Furthermore, we demonstrate our Rep-UWnet effectively improves high-level vision tasks like edge detection and single image depth estimation. This method not only surpasses the contrast method in objective quality, but also significantly improves the contrast, colorimetry, and clarity of underwater images in subjective quality.

Privacy-Enhanced Cooperative Storage Scheme for Contact-Free Sensory Data in AIoT with Efficient Synchronization

The growing popularity of contact-free smart sensing has contributed to the development of the Artificial Intelligence of Things (AIoT). The contact-free sensory data has great potential to mine and analyze the hidden information for AIoT-enabled applications. However, due to the limited storage resource of contact-free smart sensing devices, data is naturally stored in the cloud, which is at risk of privacy leakage. Cloud storage is generally considered insecure. On one hand, the openness of the cloud environment makes the data easy to be attacked, and the complex AIoT environment also makes the data transmission process vulnerable to the third party. On the other hand, the Cloud Service Provider (CSP) is untrusted. In this article, to ensure the security of data from contact-free smart sensing devices, a Cloud-Edge-End cooperative storage scheme is proposed, which takes full advantage of the differences in the cloud, edge, and end. Firstly, the processed sensory data is stored separately in the three layers by utilizing well-designed data partitioning strategy. This scheme can increase the difficulty of privacy leakage in the transmission process and avoid internal and external attacks. Besides, the contact-free sensory data is highly time-dependent. Therefore, combined with the Cloud-Edge-End cooperation model, this article proposes a delta-based data update method and extends it into a hybrid update mode to improve the synchronization efficiency. Theoretical analysis and experimental results show that the proposed cooperative storage method can resist various security threats in bad situations and outperform other update methods in synchronization efficiency, significantly reducing the synchronization overhead in AIoT.

Significant contribution of the Tianshan lakes to their water storage and water resources

Study regionThe Tianshan region Study focusThe Tianshan region possesses a complex landscape with lakes, and changes in the water storage of these lakes serve as a crucial indicator of climate change. They also represent a significant water resource for the local area, profoundly impacting water resource allocation and playing a pivotal role in understanding the mass balance in the Tianshan region. Nevertheless, there is still a lack of systematic research on the Tianshan lake group. New hydrological insights for the regionThe results reveal that the total lake water storage is exhibiting an increasing trend (0.73±0.10 Gt/a). The Tianshan region experienced two periods of mass anomalies in 2010 and 2016, which were reflected not only in the changes of lake water storage but also in soil moisture, snow water, and even Global Navigation Satellite System (GNSS) displacement fields. These two mass anomalies were closely related to abnormal precipitation resulting from El Niño events (r=0.55, p<0.01). During these two mass anomaly periods, the regional total mass increased by 65.73 Gt and 67.35 Gt. Compared with their contributions to the mass (22% and 14%), the variations in lake area were remarkably slight (0.01% and 0.014%). This study contributes to understanding the sensitivity of lakes to climate responses and underscores the necessity of lake research for water resource management in complex surface environments.

Hardware Implementation of a Resilient Energy Management System for Networked Microgrids

A networked microgrid is composed of multiple nearby microgrids linked together to gain additional flexibility for resilient operations. Networked microgrids collaborate to prevent power shortages in microgrid clusters by sharing critical renewable and energy storage resources. However, controlling the local resources of each microgrid, including the energy storage systems’ charging and discharging, maintaining the DC bus voltage, and even overseeing the power shared by multiple microgrids, is challenging. Therefore, a microgrid control technique and distributed energy management are used cooperatively in this study to handle the shared power between a system of networked microgrids incorporating photovoltaics and battery energy storage systems. Numerical simulation results from a networked microgrid system verify the accuracy and soundness of the suggested distributed energy management under several operating conditions, including renewable uncertainties and sequential load variations in different zones. The applicability of the suggested technique is confirmed by hardware implementation, and several operational scenarios further evaluate the proposed system on a practical two-microgrid system located in the Florida International University (FIU) testbed.

Co-creation of a novel approach for improving supply chain management for SARS-CoV-2 point of care diagnostic services in Mopani District, Limpopo Province: nominal group technique.

Effective supply chain management (SCM) of point-of-care (POC) tests for diseases like severe acute respiratory syndrome coronavirus type 2 (SARS-CoV-2) requires active participation from diverse stakeholders, government entities, and regulatory bodies. The responsibility for overseeing various aspects of POC tests, including procurement, quality assurance, storage, inventory management, distribution, and human resource capacity, lies with national, provincial, and local levels of government. This study aimed to collaboratively develop an innovative approach to enhance SCM for SARS-CoV-2 POC diagnostic services in resource-limited settings, using the Mopani District in Limpopo province, South Africa, as a case study. Key stakeholders were invited to participate in an online workshop using purposive sampling. The study employed the nominal group technique (NGT) for data collection, which consisted of two phases. Phase 1 focused on identifying barriers in the supply chain of COVID-19 rapid tests, while phase 2 aimed to devise strategies to overcome the priority barriers identified in phase 1. Participants used a Likert scale of 1-5 to rank barriers and strategies, and an overall ranking score was calculated for each. The participants were provided with the results of the ranking exercise for their feedback. Eleven key stakeholders from national (n = 1), provincial (n = 4), and local government (n = 2) levels, research entities (n = 3), and non-governmental organizations (n = 1) took part in the study. Participants identified significant barriers in the supply chain, such as the availability of testing kits, unknown demand, information on SCM during a pandemic, methods of controlling stock, and procurement processes. Strategies suggested by key stakeholders included monitoring stock levels and optimizing stock visibility systems to improve test availability, enhancing information visibility and consistent data updates to address unknown demand and improve SCM during a pandemic, employing data capturing and digitization for effective stock control, and implementing demand planning and standardized procurement processes at the national level to enhance stock procurement. The successful collaboration with key stakeholders, facilitated by the NGT, resulted in the co-creation of a novel approach to enhance SCM for COVID-19 diagnostic services in resource-limited settings. This study holds the potential to support the provision of COVID-19 diagnostic services in such settings. A recommended follow-up study would assess the feasibility of implementing this approach.

EleVMate — A data-driven approach for ‘on-the-fly’ horizontal small datacentre scalability and VM starvation

The volume of data exchanged over the network has increased exponentially over the past few years, driving the need for a new solution. To address this issue, a new layer for computation and storage between the cloud and the user has been introduced to reduce the load on the network. To facilitate this solution, small datacentres have emerged characterized by their limited capacity in terms of computation and storage resources. These datacentres are managed by small fog service providers (SFSPs) and are used to host virtual machines (VMs) with QoS requirements that vary based on application and user subscription. Being limited in capacity, these SFSPs are unable to accept all incoming VM requests, forcing them to reject some VM requests based on QoS requirements. This causes an issue for VMs with minimum QoS requirements as they are kept waiting for unlimited time causing them to starve. VM starvation in SFSPs is a critical issue that has not been addressed in the literature. To address this issue, in this paper, we propose to support the SFSP by horizontally scaling up its resources using volunteer nodes. We propose, EleVMate, a novel management framework to manage the allocation of VMs to the SFSP nodes. Our solution works to prioritize the placement of priority VMs in these datacentres. We validated the solution using a publicly available VM dataset and we concluded that priority influences VM placement in SFSP. Last, our framework has improved the performance of the SFSP by reducing rejection rate by at least 4% with existing solutions.

Near Real-Time Monitoring of Large Gradient Nonlinear Subsidence in Mining Areas: A Hybrid SBAS-InSAR Method Integrating Robust Sequential Adjustment and Deep Learning

With the increasing availability of satellite monitoring data, the demand for storage and computational resources for updating the results of monitoring the surface subsidence in a mining area continues to rise. Sequential adjustment (SA) models are considered effective for rapidly updating time series interferometry synthetic aperture radar (TS-InSAR) measurements. However, the accuracy of surface subsidence values estimated through traditional sequential adjustment is highly sensitive to abnormal observations or prior information on anomalies. Moreover, the surface subsidence associated with mining exhibits nonlinear and large gradient characteristics, making general InSAR methods challenging for obtaining reliable monitoring results. In this study, we employ the phase unwrapping network (PUNet) to obtain unwrapped values of differential interferograms. To mitigate the impact of abnormal errors in the near real-time small baseline subset InSAR (SBAS-InSAR) sequential updating process in mining areas, a robust sequential adjustment method based on M-estimation is proposed to estimate the temporal deformation parameters by using the equivalent weight model. Using a coal backfilling mining face in Shanxi, China, as the study area and the Sentinel-1 SAR dataset, we comprehensively evaluate the performance of unwrapping methods and subsidence time series estimation techniques and evaluate the effect of filling mining on surface subsidence control. The results are validated using leveling measurements within the study area. The relative error of the proposed method is less than 5%, which can meet the requirements of monitoring the surface subsidence in mining areas. The method proposed in this study not only enhances computational efficiency but also addresses the issue of underestimation encountered by InSAR methods in mining area applications. Furthermore, it also mitigates unwrapping phase anomalies on the monitoring results.

Bacterial Community Structure of Typical Lake Sediments in Yinchuan City and Its Response to Heavy Metals

Lake wetlands are extremely important and special ecosystems, which are important for regional water resource storage, environmental protection, and biodiversity maintenance. Sediment bacteria are an important component of lake ecosystems and are a major driver of biogeochemical cycling in lakes. In order to investigate the community structure of bacteria in typical lake sediments in Yinchuan City and their influencing factors, three typical lakes in Yinchuan City (Yuehai Lake, Mingcui Lake, and Xiniu Lake) were selected for the study and surface sediments were collected in January, April, July, and October 2021. The composition of the sediment bacterial community was examined using 16S rDNA high-throughput sequencing technology, and the response relationships between them and heavy metals were explored. The results showed that the ecological hazard coefficient for heavy metals in the sediments of three typical lakes in Yinchuan City was far less than 40, and the ecological hazard index was far less than 150, all of which indicated a minor ecological hazard. There were no significant differences in bacterial community diversity among the three lakes, but there were significant variations in diversity among the lakes in different seasons and significant differences in community composition. The dominant phyla (top three in terms of relative abundance) in Yuehai Lake, Mingcui Lake, and Xiniu Lake were Proteobacteria, Bacteroidetes, and Chloroflexi. The dominant lower orders were Gammaproteobacteria, Alphaproteobacteria, and Deltaproteobacteria. The main divergent species that occurred at the phylum level in typical lakes in Yinchuan were Proteobacteria, Bacteroidetes, Euryarchaeota, Firmicutes, Actinobacteria, and Acidobacteria. The sediment bacterial community structure of Yuehai Lake was significantly correlated with Cu, Fe, Mn, Zn, As, and Pb; the sediment bacterial community structure of Lake Mingcui was significantly correlated with Fe, Pb, and Cr; and the sediment bacterial community structure of Xiniu Lake was not significantly correlated with heavy metals. The types and contents of sediment heavy metals had a significant effect on the bacterial community structure of sediments in Yinchuan Yuehai Lake and Mingcui Lake and were important environmental factors that caused changes in the bacterial community structure of lake sediments.

A Framework on Group Data Sharing Based Agreement Implementation in Cloud Computing

Abstract -- Cloud computing and cloud storage have become hot topics in recent decades. Both are changing the way we live and greatly improving production efficiency in some areas. At present, due to limited storage resources and the requirement for convenient access, we prefer to store all types of data in cloud servers, which is also a good option for companies and organizations to avoid the overhead of deploying and maintaining equipment when data are stored locally. The cloud server provides an open and convenient storage platform for individuals and organizations, but it also introduces security problems. Due to the particularity of some industries, some enterprises have extremely high requirements on the security of data. If the data is lost or destroyed, the enterprise will bear serious consequences. The second problem is reliability. Only by ensuring that the data records are accurate and reliable can the data transmission be more secure and the enterprise win a higher reputation. In addition, the issue of cloud computing regulation is also very important. Only through efficient and orderly regulation can enterprises operate healthily and normally. At present, many small and medium sized enterprises need to spend huge costs on data storage, which will continue to increase with the expansion of data volume. However, the emergence of cloud storage services has brought the dawn for these enterprises, they will need to store the data transmission to the cloud, through the cloud storage service provider to solve this problem, so that they can save the cost of their own data center, use low price to achieve the purpose of data storage.

Research on optimal configuration of natural gas electric hybrid energy system

Natural gas resources are crucial for the development of the international community, which has the advantages of energy conservation, economy, and environmental protection. By optimizing the allocation of natural gas energy storage resources, the negative impact of randomness and volatility on the energy system can be effectively suppressed. Therefore, this article proposes a research on optimal configuration of natural gas electric hybrid energy system. Using the investment payback period as the economic evaluation indicator, analyze the influencing factors of the economic performance of the natural gas electricity hybrid energy system from a technical and economic perspective. By using historical data of actual natural gas electricity hybrid energy systems for example calculation and analysis, the configuration method under the proposed strategy was verified to meet the multi time scale requirements of the system while considering equipment characteristics, effectively improving system economy. l gas electric hybrid energy system

Cluster partition-based two-layer expansion planning of grid–resource–storage for distribution networks

In order to realize the optimal planning of grid–resource–storage for distribution networks (DNs) with high penetrated distributed photovoltaics (PVs), a cluster partition-based two-layer expansion planning for DNs is proposed. First, a comprehensive cluster partition index-based cluster partition method is proposed, which involves the indexes such as electrical distance, power balance of the cluster, and cluster size. Second, a cluster partition-based two-layer expansion planning model is proposed. In the upper layer, a line planning model for clusters is established to carry out the planning of cluster connection lines. In the lower layer, a robust source-storage planning model is established with the uncertainty of PVs and loads, and then, the optimal location and capacity of PVs and energy storages (ESs) can be obtained. In addition, the uncertainty regulation parameter is utilized to control the range of uncertainty sets, which can reduce the conservatism of the optimization. Finally, the proposed method is carried out in a real DN in China, which can effectively improve the economy of DN planning.

Origin, distribution, and CO2 EOR and CO2 storage resource assessment of selected residual oil zone fairways in the Illinois Basin

Residual Oil Zones (ROZs) are volumes of rock with low, largely immobile, oil saturations that provide opportunities for low carbon intensity oil production via carbon dioxide enhanced oil recovery (CO2-EOR) and associated CO2 storage. Oil shows of varying degree have been observed throughout the Illinois Basin (ILB). This work is the first to assess these shows as ROZs.In the ILB, the distribution of ROZ fairways and prospects is controlled by the geologic setting and oil migration history of the basin. ILB ROZ fairways that are stratigraphically proximal to the source rock are generally widespread whereas fairways developed in formations with a greater thickness of intervening strata are more discrete, an indication of influence from fault systems and fracturing associated with major structures. Within these fairways, 41 ROZ prospects were defined across three formations (Tar Springs Sandstone, Cypress Sandstone, Carper Sandstone) containing a best estimate (P50) of five billion barrels (bbls) of original oil in place (OOIP). For context, this volume is 35% of the estimated 14.1 billion bbls of OOIP in the conventional reservoirs in the ILB. In comparison to the Permian Basin, the ILB ROZ OOIP volume is 20% of the estimated 25 billion bbl of ROZ OOIP within a nine-county area of the San Andres Formation.The CO2-EOR resource of the ILB ROZ prospects exceeds 518 million bbls of oil using CO2 injection via pattern flooding. Associated CO2 storage is estimated to be 411 million tonnes of CO2. This study builds on past efforts to establish the CO2-EOR and associated CO2 storage resource potential of the ILB and presents a methodology that can be used to assess ROZ resources in other parts of the world.

Delay-guaranteed Mobile Augmented Reality Task Offloading in Edge-assisted Environment

With the introduction of Augmented Reality (AR) into mobile devices, it becomes a trend to develop mobile AR applications in various fields. However, the execution of AR task demands the extensive resources of computation, memory and storage, which makes it difficult for mobile terminals with constrained hardware resources to carry out AR applications within the limited delay. In response to this challenge, we propose a mobile AR offloading method under the edge-assisted environment. Firstly, we divide an AR task into consecutive subtasks, and then collect the features of hardware, software, configuration, and runtime environments from the edge servers to be offloaded. With the features, we construct an AR subtask Execution delay Prediction Bayesian Network (EPBN) to predict the execution delay of different subtasks on each edge platform. Based on the prediction, we model the task offloading as the NP-hard Traveling Salesman Problem (TSP), and then propose a PSO-GA based solution by adopting the heuristic algorithm of Particle Swarm Optimization (PSO) to encode the offloading strategy and using Genetic Algorithm (GA) for particle update. The extensive experiments prove that the average performances of EPBN outperform the others with 17.23%, 23.97%, and 20.67% on micro-P, micro-R, and micro-F1 respectively, and the PSO-GA ensures that the offloading latency is reduced by nearly 5% compared to the suboptimal algorithm.

Machine Learning and Weather Model Combination for PV Production Forecasting

Accurate predictions of photovoltaic generation are essential for effectively managing power system resources, particularly in the face of high variability in solar radiation. This is especially crucial in microgrids and grids, where the proper operation of generation, load, and storage resources is necessary to avoid grid imbalance conditions. Therefore, the availability of reliable prediction models is of utmost importance. Authors address this issue investigating the potential benefits of a machine learning approach in combination with photovoltaic power forecasts generated using weather models. Several machine learning methods have been tested for the combined approach (linear model, Long Short-Term Memory, eXtreme Gradient Boosting, and the Light Gradient Boosting Machine). Among them, the linear models were demonstrated to be the most effective with at least an RMSE improvement of 3.7% in photovoltaic production forecasting, with respect to two numerical weather prediction based baseline methods. The conducted analysis shows how machine learning models can be used to refine the prediction of an already established PV generation forecast model and highlights the efficacy of linear models, even in a low-data regime as in the case of recently established plants.

Research on building extraction from remote sensing imagery using efficient lightweight residual network

Automatic building extraction from very high-resolution remote sensing images is of great significance in several application domains, such as emergency information analysis and intelligent city construction. In recent years, with the development of deep learning technology, convolutional neural networks (CNNs) have made considerable progress in improving the accuracy of building extraction from remote sensing imagery. However, most existing methods require numerous parameters and large amounts of computing and storage resources. This affects their efficiency and limits their practical application. In this study, to balance the accuracy and amount of computation required for building extraction, a novel efficient lightweight residual network (ELRNet) with an encoder-decoder structure is proposed for building extraction. ELRNet consists of a series of downsampling blocks and lightweight feature extraction modules (LFEMs) for the encoder and an appropriate combination of LFEMs and upsampling blocks for the decoder. The key to the proposed ELRNet is the LFEM which has depthwise-factorised convolution incorporated in its design. In addition, the effective channel attention (ECA) added to LFEM, performs local cross-channel interactions, thereby fully extracting the relevant information between channels. The performance of ELRNet was evaluated on the public WHU Building dataset, achieving 88.24% IoU with 2.92 GFLOPs and 0.23 million parameters. The proposed ELRNet was compared with six state-of-the-art baseline networks (SegNet, U-Net, ENet, EDANet, ESFNet, and ERFNet). The results show that ELRNet offers a better tradeoff between accuracy and efficiency in the automatic extraction of buildings in very highresolution remote sensing images. This code is publicly available on GitHub (https://github.com/GaoAi/ELRNet).

A relationship-aware mutual learning method for lightweight skin lesion classification

A relationship-aware mutual learning method for lightweight skin lesion classification