Scarcity Problem Research Articles

Model Identification and Transferability Analysis for Vehicle-to-Grid Aggregate Available Capacity Prediction Based on Origin–Destination Mobility Data

Vehicle-to-grid (V2G) technology is emerging as an innovative paradigm for improving the electricity grid in terms of stabilization and demand response, through the integration of electric vehicles (EVs). A cornerstone in this field is the estimation of the aggregated available capacity (AAC) of EVs based on available data such as origin–destination mobility data, traffic and time of day. This paper considers a real case study, consisting of two aggregation points, identified in the city of Padua (Italy). As a result, this study presents a new method to identify potential applications of V2G by analyzing floating car data (FCD), which allows planners to infer the available AAC obtained from private vehicles. Specifically, the proposed method takes advantage of the opportunity provided by FCD to find private car users who may be interested in participating in V2G schemes, as telematics and location-based applications allow vehicles to be continuously tracked in time and space. Linear and nonlinear dynamic models with different input variables were developed to analyze their relevance for the estimation in one-step- and multiple-step-ahead prediction. The best results were obtained by using traffic data as exogenous input and nonlinear dynamic models implemented by multilayer perceptrons and long short-term memory (LSTM) networks. Both structures achieved an R2 of 0.95 and 0.87 for the three-step-ahead AAC prediction in the two hubs considered, compared to the values of 0.88 and 0.72 obtained with the linear autoregressive model. In addition, the transferability of the obtained models from one aggregation point to another was analyzed to address the problem of data scarcity in these applications. In this case, the LSTM showed the best performance when the fine-tuning strategy was considered, achieving an R2 of 0.80 and 0.89 for the two hubs considered.

The Problem of the Shortage of Fresh Water in Egypt and the Possibilities of Its Solution

The population growth rates that increased after the 1952 revolution accelerated the decline in the supply of fresh water to Egyptians due to the exhaustion of its traditional sources. As a result, at the turn of the 1980s – 1990s, Egypt has overcome the water deficit limit of 1000 m3 per person per year. In order to reduce water stress, the Government of the country in the second half of the twentieth century pursued a policy of birth control and reduction of cultivation of moisture-loving crops. Since the beginning of the 21st century, with the slow introduction of modern irrigation methods, it has focused on increasing the reuse of treated drainage waters in agriculture and the construction of seawater desalination plants to meet the needs of industry and public utilities. The Egyptian Government sees prospects for solving the problem of water scarcity, the growth rate of demand for which in the 21st century will decrease as population growth and economic development slow down, in the achievements of scientific and technological progress and the widespread use of cheap water treatment technologies.

Simulating water and salt changes in the root zone of salt–alkali fragrant pear and the selection of the optimal surface drip irrigation mode

Faced with the increasingly serious problem of water scarcity, developing precise irrigation strategies for crops in saline alkali land can effectively reduce the negative effects of low water resource utilization. Using a model to simulate the dynamic changes in soil water and salt environment in the root zone of fragrant pear trees in saline alkali land, and verifying them from a production practice perspective with comprehensive benefits as the goal, can optimize the irrigation amount and irrigation technology elements of saline alkali fruit trees, broaden the comprehensive evaluation perspective of decision-makers, and have important significance for improving the yield and production efficiency of forestry and fruit industry in arid and semi-arid areas worldwide. In this study, a two-year field experiment based on three irrigation levels (3000, 3750, and 4500 m3·ha−1) and four emitter discharge rates (1, 2, 3, and 4 L·h−1) was conducted in Xinjiang, China. The root zone soil water content (SWC) and soil salinity content (SSC) dynamics were simulated during the fertility period of fragrant pear using the numerical model HYDRUS-2D and field data. The results showed that the R2, root mean squared error (RMSE), and Nash–Sutcliffe efficiency coefficient (NSE) of the HYDRUS-2D simulated soil water content (SWC) (soil salinity content SSC) reached 0.89–0.97 (0.91–0.97), 0.02–0.16 cm3·cm-3 (0.22–1.54 g·kg−1), and 0.76–0.95 (0.68–0.96), respectively, indicating the strong performance of the model. A positive correlation was observed between the irrigation amount and soil infiltration depth. Moderately increasing irrigation amount could effectively leach soil salinity at a depth of 80–100 cm and maintain a water and salt environment in the main root zone of 0–80 cm, benefiting the growth and development of the main root system of fragrant pear, as well as the yield and quality of above-ground fruits. The irrigation amount and emitter discharge were optimized and quantified based on multi-objective optimization methods, normalization processing, and spatial analysis methods to maximize yield, fruit weight, soluble solids, and net profits. When the yield, fruit weight, soluble solids, and net profits simultaneously reached 90% of their maximum value, the irrigation amount and emitter discharge ranges were 4274–4297 m3·ha−1 and 3.79–3.88 L·h−1, respectively. Our study provides new insights into regulating soil water and salt environmental factors in the saline fragrant pear root zone and assessing the impact of soil water and salt management under precision irrigation strategies, and profoundly influences decision-making for irrigation of forest fruits in saline arid zones based on a production practice perspective.

A Comprehensive Evaluation of Water-Saving Society Construction in Xinxiang, Henan Province, China

Water is a crucial and fundamental resource. It is well known that agricultural cultivation, industrial production, and human daily life are not possible without water. Efficiently utilizing water resources is of great significance for achieving global Sustainable Development Goals (SDGs). In order to improve water use efficiency in various industries and promote water-saving development, China has been implementing water-saving society construction since 2002. Henan Province is the main grain-producing area in China, with wheat production accounting for a quarter of the country’s total. As the core area of “Central Plains Agricultural Valley” in Henan Province, Xinxiang City plays an important role in agricultural technology innovation and agricultural production. However, Xinxiang City is facing problems of water scarcity and pollution, which constrain the sustainability of agricultural production. Therefore, building a water-saving society can solve the current water problems faced by Xinxiang City and ensure the sustainable development of the economy and society. This study built an evaluation index system for water-saving society construction in Xinxiang, Henan Province, China. The proposed evaluation index system includes 20 evaluation indices from six aspects—integrated, agricultural water, industrial water, domestic water, water ecology and environment, and water-saving management—and then divides its development level into several stages. The Analytical Hierarchy Process (AHP) was adopted to calculate the index weight. Then, a comprehensive evaluation model for water-saving society construction in Xinxiang City was established by combining it with grey relative analysis (GRA). The results showed that the overall level of water-saving society construction in Xinxiang City is in the excellent stage, whereas water consumption per CNY 10,000 of GDP, the effective utilization coefficient of irrigation water, the reuse rate of industrial water, and the leakage rate of urban water supply network are all in the good stage. However, the urban recycled water utilization rate is still in the poor stage. These research results can effectively and reasonably reflect the development level of water-saving society construction in Xinxiang City and guide the continued implementation of water-saving society construction. At the same time, the comprehensive evaluation of water-saving society construction helps to formulate and adjust water resource management policies and measures; it also holds significant value for sustainable water management and combating water scarcity.

Semantic segmentation network for mangrove tree species based on UAV remote sensing images

Mangroves are special vegetation that grows in the intertidal zone of the coast and has extremely high ecological and environmental value. Different mangrove species exhibit significant differences in ecological functions and environmental responses, so accurately identifying and distinguishing these species is crucial for ecological protection and monitoring. However, mangrove species recognition faces challenges, such as morphological similarity, environmental complexity, target size variability, and data scarcity. Traditional mangrove monitoring methods mainly rely on expensive and operationally complex multispectral or hyperspectral remote sensing sensors, which have high data processing and storage costs, hindering large-scale application and popularization. Although hyperspectral monitoring is still necessary in certain situations, the low identification accuracy in routine monitoring severely hinders ecological analysis. To address these issues, this paper proposes the UrmsNet segmentation network, aimed at improving identification accuracy in routine monitoring while reducing costs and complexity. It includes an improved lightweight convolution SCConv, an Adaptive Selective Attention Module (ASAM), and a Cross-Layer Feature Fusion Module (CLFFM). ASAM adaptively extracts and fuses features of different mangrove species, enhancing the network’s ability to characterize mangrove species with similar morphology and in complex environments. CLFFM combines shallow details and deep semantic information to ensure accurate segmentation of mangrove boundaries and small targets.Additionally, this paper constructs a high-quality RGB image dataset for mangrove species segmentation to address the data scarcity problem. Compared to traditional methods, our approach is more precise and efficient. While maintaining relatively low parameters and computational complexity (FLOPs), it achieves excellent performance with mIoU and mPA metrics of 92.21% and 95.98%, respectively. This performance is comparable to the latest methods using multispectral or hyperspectral data but significantly reduces cost and complexity. By combining periodic hyperspectral monitoring with UrmsNet-supported routine monitoring, a more comprehensive and efficient mangrove ecological monitoring can be achieved.These research findings provide a new technical approach for large-scale, low-cost monitoring of important ecosystems such as mangroves, with significant theoretical and practical value. Furthermore, UrmsNet also demonstrates excellent performance on LoveDA, Potsdam, and Vaihingen datasets, showing potential for wider application.

Self-supervised spectral super-resolution for a fast hyperspectral and multispectral image fusion

Hyperspectral-multispectral image fusion (HSI-MSI Fusion) for enhancing resolution of hyperspectral images is a hot topic in remote sensing. An important category of approaches for HSI-MSI Fusion is based on deep learning. The main challenges in deep learning based fusion methods include the lack of training data, poor generalization to various datasets, and high computational costs. This paper suggests a new approach to tackle these difficulties by introducing an innovative technique for HSI-MSI fusion. The proposed method involves training a tiny deep neural network that can reconstruct high-resolution hyperspectral images through spectral super-resolution of high-resolution multispectral images. This method does not require high resolution training data and they are artificially generated based on the spatial degradation model of the input observation images. Therefore, the problems of data scarcity and poor generalization are addressed, and also the computational burden is significantly reduced. After conducting thorough experiments, it was found that the proposed method provides promising results. The source code of this method is available at https://github.com/rajaei-arash/SSSR-HSI-MSI-Fusion.

Few-Shot Learning Method Based on Data Enhancement and Transfer Learning

With the significant progress of deep learning technology in many fields, the dependence of model training on a large amount of labeled data is increasingly prominent. However, in many practical application scenarios, especially in tasks with high labeling costs, data scarcity often occurs. This realistic challenge has promoted the rise of Few-Shot Learning (FSL) technology, which seeks to achieve effective learning of models with extremely limited samples. This article provides a comprehensive overview of the theoretical background, key technologies of FSL, to explore its potential and effectiveness in solving the problem of small-sample learning. In the method overview section, this article pays special attention to FSL strategies based on data augmentation and transfer learning. By reviewing and analyzing these methods, this article aims to provide some theoretical support and technical references for further exploration in this field and hopes to contribute to solving the problem of data scarcity and promote the sustainable development of this field.

Reduced Graphene Oxide Loaded with ZCF Magnetic Nanoparticles as a Promising Photocatalyst and Antibacterial Agent

Due to waste, pollution, and unequal distribution of the world’s finite freshwater resources, there is currently a problem of water scarcity. Therefore, developing novel, affordable, and efficient techniques for water purification is essential. Here, the photo-assisted degradation of Methyl Orange dye (MO) under visible light and UV was achieved by using reduced graphene oxide (RGO) photocatalyst loaded with Zn0.5Cu0.5Fe2O4 (ZCF) called MRGO 20. Furthermore, all prepared samples were characterized by X-ray diffraction (XRD), fourier transformation infrared (FTIR), transmission electron microscope (TEM), vibrating sample magnetometer (VSM) and Raman analysis. After 40 minutes, the high photocatalytic efficacy effectively eliminated about 96 % of the 10 ppm MO using 20 mg of MRGO 20 NPs at pH 5 under Visible light irradiation. From the results, MRGO 20 demonstrated good performance stability after five cycles of photocatalytic degradation of MO dye. The shown performance of the generated samples in both visible and UV light may motivate further investigation into more potent photocatalysts for water filtering. MRGO 20 NPs nanocomposite displayed great activity against Gram-negative (E. coli) bacteria with a zone of inhibition (ZOI) mm value of 24.0 mm, and high biofilm inhibition of 94.3%. The produced samples’ observed efficacy in both UV and visible light may encourage continued research into more effective photocatalysts for the filtration of water and for biological applications.

Self-supervised learning-based multi-source spectral fusion for fruit quality evaluation: A case study in mango fruit ripeness prediction

Rapid and non-destructive techniques for fruit quality evaluation are widely concerned in modern agro-industry. Spectroscopy is one of the most commonly used techniques in this field. With the growing popularity of various spectroscopic instruments, it is indeed worthwhile to explore modeling with multi-source spectral data to achieve more accurate predictions. Nonetheless, a major challenge is acquiring enough labeled samples, as measuring fruit chemical values is laborious, expensive, and time-consuming, which hinders the development of a reliable prediction model. Therefore, this study aims to develop a model for predicting the internal chemical composition of fruits by integrating multi-source spectral fusion combined with self-supervised learning (SSL). A visible (Vis) and near-infrared (NIR) spectral dataset related to dry matter content (DMC) prediction in mango fruit is used as an example to validate the effectiveness of the proposed method. To obtain multi-source spectral data, the Vis and NIR portions are processed as two separate spectral ranges. An SSL pre-training is performed utilizing a large amount of raw unlabeled spectral data to extract general knowledge, which is subsequently migrated to a downstream task for fine-tuning. The experimental results indicate that the multi-source spectral fusion model performs better than the single-source spectral model. Moreover, SSL solves the data scarcity problem and outperforms non-pre-trained models in downstream DMC prediction tasks with less computational overhead. Remarkably, utilizing only <10 % of the total samples is sufficient to achieve a performance close to 99 % of the best results. The presented method has great potential in spectral analysis of food and agro-products.

Stacked solar distiller using water to storage heat for high-temperature evaporation

Solar stills can produce freshwater with low or even no carbonization to alleviate the problem of freshwater resource scarcity. However solar distiller's operation period is limited by the intermittence of solar energy, and the Gained-output ratio (GOR) is determined by operation temperature. To further develop efficient solar distillers, this paper investigates a stacked solar distiller with high evaporation temperature, utilizing water to storage heat. A mathematical model of a triple-stacked solar distiller (TSD) was established to describe the internal heat and mass transfer processes. Then an experimental device was built. The experiments under steady-heating and outdoor solar-heating have been conducted. The steady-heating testing results show that, when the evaporation temperature of TSD reaches 79.9 °C, the GOR reaches 2.00. The theoretical model can accurately predict the operating parameters of the distiller, with the deviation of the theoretical temperature from the experimental value within 0.9 °C and the GOR deviation ranging from 2.2 % to 21.0 %, under steady-heating testing. The outdoor testing results show that, at an average daily irradiance of 606 W/m2, the maximum evaporation temperature is above 90.0 °C, achieving a water yield rate of 2.53 kg/(h·m2) and the maximum instant GOR of system closing to 2.23. Combined with nighttime water yield attributing to heating storage, a water yield of 28.00 kg/(d·m2) can be achieved. This research may provide a good scheme for the scenario of small-scale distributed solar desalination demands.

Few-Shot Learning Method for Continuous Prediction of Rock Mechanical Parameters Based on Logging Data.

The stratigraphic sequence displays pronounced variations in lithological and physical characteristics along the vertical axis. The acquisition of vertically continuous variations in stratigraphic rock mechanical parameters is essential for the detailed characterization of stratigraphy, particularly in reservoir layers. Moreover, mechanical parameters are essential for the establishment of a rock mechanical stratigraphic framework. However, the existing research methods cannot obtain the complete stratum rock mechanics parameters by relying solely on a small number of rock samples. In this study, a method for continuously predicting rock mechanic parameters within geological sequences by using geophysical logging data was proposed. The method aims to solve the problems of sample scarcity and global geological feature extraction in the continuous prediction of rock mechanics parameters. This methodology achieves the continuous extraction of stratigraphic features, generation of samples, and prediction of the mechanical parameters. The research result showed that the stratigraphic feature extractor of the logging autoencoder possesses global stratigraphic perception capabilities. Stratigraphic feature extractors can precisely identify and pinpoint key locations where stratigraphic properties change, such as lithological transitions and abnormal parts within thick rock layers. The fake rock mechanical samples produced by the generator exhibit data characteristics identical to those of the genuine samples. The rock mechanics parameter prediction model with the ability to extract stratigraphic features performs significantly better than traditional models when evaluated on real data sets (the mean square errors for the friction angle and cohesion are 17.2 and 12.65, respectively, mean absolute errors are 2.85 and 2.64, respectively, and R2 values are both 0.91) and produces more reasonable calculation results in the actual prediction task of Longtan Formation rock mechanics parameters compared to traditional models. This study provides an extensive applicable methodological framework to address the issues of insufficient samples and continuous prediction of geological parameters in the field of geology.

Use of Data Augmentation and Fine-tuned Transfer Learning Models for Classification of Cervical Cancer

Innovative strategies for early and accurate diagnosis of cervical cancer continue to be a global health priority. In this research, we present a powerful framework for improving cervical cancer classification by combining data augmentation methods with tailored transfer learning models. The lack of properly labelled medical data is a major roadblock to developing reliable diagnosis models. The geometric transformations, contrast tweaks, and noise addition that we use to increase the dataset artificially help us overcome this difficulty. The model's robustness is improved as a result of the additional exposure to diverse real-world circumstances provided by this supplemented dataset. We use a transfer learning strategy based on pre-trained convolutional neural networks (CNNs) to harness the potential of deep learning. These networks are well-suited for medical image analysis due to their ability to quickly and accurately identify features in a wide variety of images. Our expanded cervical cancer dataset is used to fine-tune these algorithms for their diagnostic purpose. Our experiments show that utilising both data augmentation and fine-tuned transfer learning considerably raises the accuracy of cervical cancer categorization. In terms of sensitivity, specificity, and overall accuracy, the model performs at a state-of-the-art level. This suggests that it may be useful in the diagnosis and early identification of cervical cancer. Additionally, our method demonstrates the significance of efficient data utilisation and model adaptability in the field of medicine. Our method is scalable and affordable, and it can be easily implemented in healthcare settings since we handle the problem of data scarcity and take advantage of the features of pre-trained deep learning models.

Efficient Federated Recommender System with Adaptive Model Pruning and Momentum-based Batch Adjustment

With the development of 5G communication and smart devices, the prosperity of online content has boosted the research of Recommender System (RS). Due to the data scarcity problem, researchers employ knowledge transfer techniques to improve the accuracy of RS. Data sharing or data augmentation are promising methods for such a problem, but the data suffers from privacy leakage during sharing. Thus, Federated Learning (FL) has been adopted to collaboratively train recommender models while preserving data privacy. Federated Recommender System (FRS) combines FL and RS to provide distributed recommendation services to the users. However, the existing FRS suffers from massive communication and system heterogeneity, where the necessity of model transmission and the diversity of the clients bring significant communication overhead to the system. In this paper, we propose Efficient Federated Recommender System with Adaptive Model Pruning and Momentum-based Batch Adjustment ( eFRSA 2 ) to reduce the communication overhead of FRS. eFRSA 2 contains two modules. Adaptive Model Pruning utilizes magnitude pruning to reduce the communication volume and adaptively modifies the compression ratios of different clients to maintain the model accuracy. Momentum-based Batch Adjustment adjusts the local training batch number by a similar method of gradient descent with momentum to align the local computation time of the clients and reduce the communication overhead. The experimental results demonstrate that eFRSA 2 can reduce up to 90% communication volume and mitigate the system heterogeneity by over 75%, demonstrating the priority of eFRSA 2 in training efficiency. Source code can be found at https://github.com/shhjwu5/eFRSA2.

There is No Scarcity Problem

Recently, John Danaher and Sven Nyholm argued that partial “digital duplicates” of real persons (simulations and imitations) prima facie makes the real person less valuable because they become less scarce. They call this the “scarcity problem.” If true, this thesis is amongst the most important insights in ethics of technology because of the simplicity of duplication. However, based on an analysis of their argument, I suggest that the thesis has no support.

Optimizing Water Productivity through the Conjunctive Use of Borewell and Canal Water for Enhancing Sheep Productivity in Arid Climate of Western Rajasthan, India

In the arid regions of Rajasthan, water scarcity poses a significant challenge to both agriculture and livestock productivity. Sustainable practices in such climates require effective management of limited water resources. This study focuses on optimizing water productivity through the conjunctive use of canal water and borewell water to address the problem of water scarcity while maximizing output per unit of water. The experiment involved eighteen healthy lambs of aged 2-3 months which were managed intensively and divided into three groups of six lambs each based on a randomized block design. All groups were fed Pennisetum glaucum (pearl millet) and Medicago sativa (lucerne) ad-libitum along with concentrates adjusted according to their body weights. The groups were offered three types of drinking water: canal water (G1), a combination of canal and borewell water (G2) and borewell water (G3) in a clean bucket twice a day. No significant effect on total feed intake and body weight of the lambs was found based on the drinking water source. However, G1 and G2 lambs, which were offered canal water, consumed significantly (p&lt;0.05) less water (74.4 ± 1.84 liters) compared to the lambs in G3 (81.6 ± 1.91 liters). The virtual water requirement per kilogram of weight gain, calculated from both direct water intake and indirect intake through feed was lowest in G1 lambs (5771.34 liters) followed by G2 lambs (6129.00 liters) and G3 lambs (6312.00 liters) per kilogram of weight gain, respectively. These results indicate that water productivity was highest with canal water (G1) and lowest with borewell water (G3) per kilogram of weight gain. This study underscores the importance of efficient water management in maximizing productivity and resource use efficiency in water-limited arid regions.

Sustainable Water Management Solutions for Urban Areas

The management of water resources is a serious concern in urban areas because of the effects of climate change, aging infrastructure, and rapid population increase. This essay examines the vital significance of sustainable water management in urban settings, emphasizing cutting-edge frameworks for policy and technology that can improve water resilience and efficiency. Successful strategies, such as demand management and diversification of the water supply, are demonstrated by case studies like Windhoek, Namibia. In order to solve the intricate and interrelated problems of urban water scarcity, infrastructure constraints, and environmental repercussions, the essay emphasizes integrated water resources management (IWRM) as a crucial technique that incorporates multidisciplinary viewpoints. In order to guarantee a sustainable urban water future, the importance of inclusive policies and governance is also covered, highlighting the necessity of cooperative and flexible problemsolving techniques.

Nano Filtration Techniques in Waste Water Treatment

Nano filters, based on nanotechnology to improve filtration processes, offer sophisticated solutions for contaminant removal from liquids and gases. The filters in this group include polymeric membranes with a pore size of 1-100 nanometres, ceramic membranes that are tolerant to chemicals, and carbon nanotube and graphene-based filters with advancedpermeability and selectivity. Recently, differentiated nanomaterials have been developed to make composite membranes with improved performance and durability. However, NF have disadvantages such as membrane fouling and high production costs. In this respect, research is currently being done to come up with solutions to the challenges, optimize the integration of nanomaterials, and realize application possibilities in water treatment, air purification, and industrial processes. On the whole, NF stand as the radical improvement filtration technology has so far achieved, and further research is bound to make them more efficient and cheaper About 17–19 million people in the world lack access to clean water. It is estimated that about 3.4 million people die every year from water scarcity, sanitation, and hygiene-related problems out of which 99% of deaths occurin developing countries. In recent years, water contamination has become a global environmental concern. The paper providesinsights into advancements in wastewater treatment through nano-filters. The paper focuses on evaluating the effectiveness ofnanomembranes in removing containments such as inorganic salts, organic compounds, and heavy metals. Additionally, the paper gives information about performance based on a comparison of the tractional filters and RO in terms of flexibility, durability, efficiency, and cost-effectiveness. Furthermore, it explores the application of NF in industries such as textile, pharmaceuticals, and agriculture and evaluates the versatility and effectiveness in these sectors.

MW‐SAM:Mangrove wetland remote sensing image segmentation network based on segment anything model

AbstractMangrove wetlands are important ecosystems in tropical and subtropical coastal areas, providing wind and wave attenuation and embankment protection functions. However, mangrove wetlands worldwide are facing severe loss and degradation. Accurate identification of mangrove wetland extent is crucial for their protection, but traditional methods struggle to meet the requirements of large‐scale, high‐precision identification. Furthermore, field data collection and annotation in wetlands in complex intertidal zones pose challenges, and the lack of high‐quality training samples limits the application of deep learning methods in this field. This paper proposes a novel semantic segmentation framework for mangrove wetlands called mangrove wetland remote sensing image segmentation network based on segment anything model (MW‐SAM) to address these issues. MW‐SAM is based on the pre‐trained SAM and achieves cross‐domain adaptation through parameter‐efficient fine‐tuning techniques. It introduces wetland‐specific prompts, auxiliary branches, semi‐supervised training, and iterative optimization strategies to improve accuracy and tackle the problem of sample scarcity. Moreover, on the mangrove wetland dataset constructed in this paper, MW‐SAM significantly outperforms SAM and other traditional methods. MW‐SAM provides a new technology for monitoring and protecting mangrove wetlands, and the constructed dataset will be made publicly available, which is expected to promote the development of mangrove wetland conservation efforts.

MTGGAN: generate type-controllable magnetic tile defect data to improve defect detection performance

ABSTRACT The scarcity of training samples and label information poses a major challenge for deep learning defect detection technology. Using generative models to expand sample data is considered an effective approach to address this issue. However, existing GAN models struggle to generate high-fidelity and type-controllable magnetic tile defect samples. Therefore, this paper proposes a type-controllable magnetic tile generation method (MTGGAN) that generates data with inherent label information. The model enhances fidelity and diversity in conditional generation through dual discriminator, auxiliary classifier, and auxiliary generator mechanisms. Additionally, focal loss is introduced to address the model’s class tendency issue during training. Extensive experiments demonstrate that, compared to advanced GAN methods, samples generated by MTGGAN exhibit superior quality and diversity. Furthermore, the generated data can train superior detection models. Effectively alleviating the problem of data scarcity in defect detection.

Fabrication of Micro/Nanostructured Copper Fibers by Vibration Cutting for Felt-Based Freshwater Purification

Freshwater purification from wasted water and seawater is crucial in addressing the global problem of water scarcity. Porous fiber felt with a micro/nanostructure emerges as an efficient approach for water purification; however, its production usually relies on chemical postprocessing to create micro/nano structures on the fiber surface, which might pollute the environment. This study proposed an ecofriendly method to produce micro/nanostructured copper fiber felt without chemical treatment. First, a new transverse-feeding vibration cutting is proposed to fabricate micro/nanostructured fibers with controllable structure characteristics. Through the sintering of the structured fibers without postprocessing, the fiber felt can be produced in an ecofriendly way and exhibit special wettability and excellent photothermal properties. Felt-based freshwater purification, including oil–water separation and solar-driven seawater desalination, can be realized effectively. Results show an oil–water separation efficiency of > 90% and a high evaporation rate of water of > 1.08 kg m−2 h−1 at 73 mW cm−2 are achieved, demonstrating the application prospect of the produced fiber felt.