Scarcity Problem Research Articles

Distillate yield improvement techniques for solar still coupled with evacuated tube collector: a review.

Many effective solutions to the problem of freshwater scarcity have been offered by the research community across the globe. Evacuated tube collector (ETC)-aided solar thermal desalination devices have succeeded magnificently in providing drinking water to the general public, especially in solar-rich isolated locations. Furthermore, heat transfer fluid ETC solar water desalination units are a much smarter, novel, and cost-effective solution that does not needed additional power and is well-suited to remote locations with a greater rate of self-sustainability. The efficiency of ETC-assisted solar distillation equipment as well as the essential analytical parameters related to the device and heat transfer fluid are thoroughly examined in this study. Literatures published in the last three decades are keenly reviewed and reported. The key finding reveals that solar still integrated with ETC can produce 3.5 to 4l of freshwater per m2 area with depth varying from 0.01 to 0.03m. It is discovered that the ETC-assisted solar still has a mean energy efficiency that is around 33% greater than the traditional solar still. When it comes to exergy efficiency, the ETC solar still outperforms conventional stills by 4%. Novel methods adopted for boosting the effectiveness of a solar still combined with ETC are reported for further research.

Bacterial cellulose-based porous Janus aerogels for efficient interfacial solar steam generation

Interfacial solar steam generation (ISSG) is considered a green and inexpensive technology to solve water scarcity problems. Currently, it still needs to pursue a fast evaporation rate, high-quality fresh water production, and excellent mechanical properties. Herein, Janus aerogels with hydrophilic and hydrophobic structures were prepared by effective spraying of polydimethylsiloxane (PD on the upper surface of bacterial cellulose (BC) /carbon black (CB) /agar powder composites (named JBCA). After a series of experiments, the results showed that the obtained JBCA evaporator had a water evaporation rate of 1.83 kg m−2 h−1 under 1000 W m−2 solar radiation. Meanwhile, the same high evaporation rate (1.63 kg m−2 h−1) was obtained in high salinity (20 wt%) solution. More importantly, the ion removal rate for real seawater was more than 99 %. The results of outdoor evaporation experiments and sustainability analyses indicated that this low-cost material with Janus structure had great potential for practical applications.

Effect of titanium oxide/reduced graphene (TiO2/rGO) addition onto water flux and reverse salt diffusion thin-film nanocomposite forward osmosis membranes

Thin-film nanocomposite (TFN) forward osmosis (FO) membranes have attracted significant attention due to their potential for solving global water scarcity problems. In this study, we investigate the impact of titanium oxide (TiO2) and titanium oxide/reduced graphene (TiO2/rGO) additions on the performance of TFN-FO membranes, specifically focusing on water flux and reverse salt diffusion. Membranes with varying concentrations of TiO2 and TiO2/rGO were fabricated as interfacial polymerizing M-phenylenediamine (MPD) and benzenetricarbonyl tricholoride (TMC) monomers with TiO2 and its reduced graphene composites (TiO2/rGO). The TMC solution was supplemented with TiO2 and its reduced graphene composites (TiO2/rGO) to enhance FO performance and reverse solute flux. All MPD/TMC polyamide membranes are characterized using various techniques such as scanning electron microscopy (SEM), atomic force microscopy (AFM), and contact angle measurements. The results demonstrate that incorporating TiO2/rGO into the membrane thin layer improves water flux and reduces reverse salt diffusion. In contrast to the TFC membrane (10.24 L m−2h−1 and 6.53 g/m2 h), higher water flux and higher reverse solute flux were detected in the case of TiO2and TiO2/rGO-merged TFC skin membranes (18.81 and 24.52 L m−2h−1 and 2.74 and 2.15 g/m2 h, respectively). The effects of TiO2 and TiO2/rGO stacking on the skin membrane and the performance of TiO2 and TiO2/rGO skin membranes have been thoroughly studied. Additionally, being investigated is the impact of draw solution concentration.Graphical

Optimizing Mini Dam Placement for Sustainable Water Management in FUTA: A GIS-MCDA Approach

Addressing the increasing demand for water resources at the Federal University of Technology, Akure (FUTA) due to the growing population requires a data-driven solution. This study determined the suitable locations for the siting of mini-dams as an alternative solution to the problem of water scarcity in FUTA using a Geographical Information Systems (GIS)-based Multi-Criteria Decision Analysis (MCDA) approach by integrating five thematic factors: drainage density, slope, elevation, land cover and soil texture. Preference values were assigned to the criteria based on their importance to a dam. Analytical Hierarchy Process (AHP) was used to assign weights to these criteria, and they were combined using a weighted sum to produce a mini dam suitability map within the study area. The suitable areas were divided into five classes: highly suitable (9%), suitable (18%), marginally suitable (30%), least suitable (26%) and not suitable (17%). The suitability map was validated against the locations of existing dams in the study area. This study contributes to the efforts to manage water resources for a growing population in FUTA and to evaluate the GIS-AHP approach for dam siting for a small study area.

Addressing data scarcity issue for English–Mizo neural machine translation using data augmentation and language model

Low-resource language in machine translation systems poses multiple complications regarding accuracy in translation due to insufficient incorporation of linguistic information. The difference in the linguistic information between the language pair also significantly impacts the dataset creation for improving translation accuracy. Although neural machine translation achieves a state-of-the-art approach, dealing with low-resource language is challenging since it struggled with limited resources. This paper attempts to address the data scarcity problem using augmentation of synthetic parallel sentences, source-target phrase pairs, and language models at the target side for English-to-Mizo and Mizo-to-English translation via transformer-based neural machine translation. We have attained state-of-the-art results for both directions of translation.

Plant disease recognition in a low data scenario using few-shot learning

Plant disease is one of the major problems in agriculture. Diseases damage plants, reduce yields and lower the quality of the produce. Traditional approaches to detecting plant diseases are usually based on visual inspection and laboratory testing, which can be expensive and time-consuming. They require trained plant pathologists as well as specialised equipment. Several studies demonstrate that artificial intelligence (AI) methods can produce promising results. However, AI methods are generally data-hungry and require large annotated datasets, and the collection and annotation of such datasets can be a limiting factor. It often appears that only a small amount of data is available for certain disease types. Whereas the performance of typical AI methods drops significantly when they are trained with inadequate data. This paper proposes a novel few-shot learning (FSL) method to detect plant diseases and alleviate the data scarcity problem. The proposed method uses as few as five images per class in the machine learning process. Our method is based on a state-of-the-art FSL pipeline called pre-training, meta-learning, and fine-tuning (PMF), integrated with a novel feature attention (FA) module; we call the overall method PMF+FA. The FA module emphasises the discriminative parts in the image and reduces the impact of complicated backgrounds and undesired objects. We used ResNet50 and Vision Transformers (ViT) as the feature learner. Two publicly available plant disease datasets were repurposed to meet the FSL requirements. We thoroughly evaluated the proposed method on the PlantDoc dataset, which contains disease samples in field environments with complex backgrounds and unwanted objects. The PMF+FA method with ViT achieved an average accuracy of 90.12% in disease recognition. The results demonstrate that the PMF+FA pipeline consistently outperforms the baseline PMF. The results also highlight that the method using ViT generates better results than ResNet50 for diagnosing complex data. ViT and ResNet50 implementations are computationally efficient, taking 1.11 and 0.57 ms on average per image to evaluate the test set respectively. The high throughput and high-quality performance with only a small training dataset indicate that the proposed technique can be used for real-time disease detection in digital farming systems.

The SnC/WS2 vdW heterojunction: A prospective direct Z-scheme photocatalyst for overall water decomposition with high STH efficiency and catalytic activity

Searching for an advanced photocatalyst is a solution to the global energy scarcity and environmental problem. In this paper, we construct a SnC/WS2 heterojunction and its structural, electronic, optical and photocatalytic properties have been investigated by first-principles calculations. The SnC/WS2 heterojunction exhibits thermodynamic stability, with a type II (staggered) energy band structure and an indirect bandgap of 1.393 eV. A built-in electrical field with direction from SnC layer to WS2 layer is formed together with a band bending in interface region. The SnC/WS2 heterojunction is a direct Z-scheme photocatalyst supporting overall water decomposition, allowing a reductive reaction to take place in the conduction band of the SnC layer to produce H2 and an oxidative reaction in the valence band of the WS2 layer to produce O2. Meanwhile, the light absorption of the SnC/WS2 heterojunction is superior to that of the two single layer materials, with the highest absorption peak 5.3 × 105 in visible light region and a solar-to-hydrogen efficiency of 42 %. Furthermore, the Gibbs free energy calculations demonstrate the high catalytic activity of the SnC/WS2 heterojunction for redox reactions. The findings reveal that the SnC/WS2 heterojunction is a super-efficient direct Z-scheme photocatalyst for overall water splitting.

YIELD PERFORMANCE AND COST-EFFECTIVENESS OF DRY DIRECT SEEDED BORO RICE IN RESPONSE TO SOWING DATE AND IRRIGATION REGIME

Dry direct seeding is a new technology to address the water scarcity problem faced in rice culture in boro season. An experiment was run at Bangladesh Agricultural University in Mymensingh, to determine the impact of the sowing date and irrigation schedule on the yield potential and cost effectiveness of boro rice grown under a dry direct seeding system. The experiment was laid out in a split-plot design and consisted of two sowing dates viz. 10 February and 02 March; and five irrigation regimes viz., no irrigation, one irrigation at 25% field capacity (FC), two irrigations (at 25% FC and at 1 week after 25% FC), three irrigations (at 25% FC, at 1 and at 2 weeks after 25% FC) and four irrigations (at 25% FC, 1, 2 and 3 weeks after 25% FC) replicated thrice assigning sowing date in main plots and irrigation in sub-plots. The result showed that BRRI dhan58 sown on 10 February with four irrigations (at 25% FC, 1, 2 and 3 weeks after 25% FC) produced the highest grain yield and economic return which was statistically comparable to those for two (at 25% FC and at 1 week after 25% FC), and three irrigations (at 25% FC, at 1 and at 2 weeks after 25% FC). The present study concludes that rice variety BRRI dhan58 can be cultivated successfully to achieve maximum yield and economic return by sowing the seed during 10 February to 02 March and applying 2 - 3 irrigations at the vegetative phase in dry direct seeding system.

Evaluating the Effect of Deficit Irrigation on Yield and Water Use Efficiency of Drip Irrigation Cotton under Film in Xinjiang Based on Meta-Analysis.

Water scarcity constrains the sustainable development of Chinese agriculture, and deficit irrigation as a new irrigation technology can effectively alleviate the problems of water scarcity and water use inefficiency in agriculture. In this study, the drip irrigation cotton field under film in Xinjiang was taken as the research object. Meta-analysis and machine learning were used to quantitatively analyze the effects of different farm management practices, climate, and soil conditions on cotton yield and water use efficiency under deficit irrigation, to investigate the importance of the effects of different factors on cotton yield and water use efficiency, and to formulate appropriate optimization strategies. The results showed that deficit irrigation significantly increased cotton water use efficiency (7.39%) but decreased cotton yield (-15.00%) compared with full irrigation. All three deficit irrigation levels (80~100% FI, 60~80% FI, and 40~60% FI; FI: full irrigation) showed a significant decrease in cotton yield and a significant increase in water use efficiency. Under deficit irrigation, cotton yield reduction was the smallest and cotton water use efficiency increased the most when planted with one film, two tubes, a six-row cropping pattern, an irrigation frequency ≥10 times, a nitrogen application of 300~400 kg·ha-1, and a crop density ≥240,000 per hectare, and planted with the Xinluzhong series of cotton varieties; deficit irrigation in areas with average annual temperature >10 °C, annual evapotranspiration >2000 mm, annual precipitation <60 mm, and with loam, sandy soil had the least inhibition of cotton yield and the greatest increase in cotton water use efficiency. The results of the random forest showed that the irrigation amount and nitrogen application had the greatest influence on cotton yield and water use efficiency. Rational irrigation based on optimal management practices under conditions of irrigation not less than 90% FI is expected to achieve a win-win situation for both cotton yield and water use efficiency. The above results can provide the best strategy for deficit irrigation and efficient water use in drip irrigation cotton under film in arid areas.

On subjective well‐being and excess strategy to cope with financial‐scarcity problem

AbstractModern economic theory asserts that consumers experiencing the scarcity problem should try to enlarge their budget. By contrast, relying on the ancient Greeks' perspective, we present a mathematical model demonstrating that higher investment in reducing material desires is positively associated with higher welfare. We present evidence from 999 participants aged 25–65 survey, showing that adopting the ancient Greek strategy for dealing with the gap between material desires and financial means is positively correlated with individuals' subjective well‐being, while adopting the modern economics strategy is not. Moreover, we show that the prudent desire management becomes less productive with age.

Probabilistic Analysis of Basic Causes of Vessel–Platform Allision Accidents

This paper proposes a methodology to estimate the probability of basic causes of allision accidents between vessels and offshore platforms that overcomes the problem of data scarcity required for causal analysis. The approach uses information derived from incidental data and expert elicitation, processed by a multiple attribute utility method and hierarchical Bayesian analysis. First, the methodology is detailed, briefly describing the adopted approaches. A dataset of allision incidents provided mainly by the UK Health and Safety Executive and other agencies is prepared. The features of the incidents’ causation in terms of the causal factors and basic causes are presented and discussed. A novel scheme is proposed to evaluate the annual occurrence rates of basic causes of accidents from the relative importance of each basic cause derived by the Deck of Cards method. Then, a hierarchical Bayesian analysis is conducted to predict the posterior distribution of the occurrence rate of each basic cause in the time frame under analysis. The proposed holistic methodology provides transparent estimates of allision causation probabilities from limited and heterogeneous datasets.

Re–operating the Bhumibol and Sirikit Dams Using Hybrid Neuro–Fuzzy Technique to Solve the Water Scarcity and Flooding Problems in the Chao Phraya River Basin

The decision support system to reservoir re–operation using Artificial Intelligence has been broadly studied and proven in term of the operational performances for both single and multiple reservoir system, this study applied Adaptive Neuro Fuzzy Inference System (ANFIS) technique for reservoir re–operation in Chao Phraya River Basin aiming to reduce water scarcity and flooding problems in the central region of Thailand. ANFIS is an integrated approach in which neural networks are utilized to enhance the fuzzy inference system and create fuzzy “IF–Then” reservoir operational guidelines with proper membership functions for reservoir re–operation. In this study, ANFIS operating rules were trained using two different datasets; long–term dataset (scenario 1) and water year–based dataset (scenario 2). It is revealed that the extent of yearly water deficit in critical dry years are totally reduced to nearly zero when re–operating with ANFIS operation rules, except in the year 2012. However, the yearly water deficit in year 2012 is also substantially reduced from 504 MCM by the current operation to 127 and 119 MCM for scenario 1 and scenario 2, respectively when two scenarios of ANFIS–based reservoir re–operation model were performed. Moreover, considerable total amount of spilled water from BB and SK Dams is definitely declined to 0 and 37 MCM in years 2002 and 2011, respectively when water year–based ANFIS model was implemented. In addition, it is expressed that average water storages of two main dams obtained from two scenarios of ANFIS model are substantially increased up to +6.08% and +6.94% for BB Dam and +0.09% and +1.62% for SK Dam in comparison with the current operation. This signifies that supplying water from dams to meet the target water demand through adaptive fuzzy–rules can be well handled and flooded water can be minimized.

Evaluating the potential of Abelmoschus esculentus, Solanum melongena, and Capsicum annuum spp. for nutrient and microbial reduction from wastewater in hybrid constructed wetland.

Utilizing engineered wetlands for the cultivation of vegetables can help to overcome the problems of water and food scarcity. These wetlands are primarily designed for wastewater treatment, and their efficiency and effectiveness can be improved by selecting an appropriate substrate. To investigate the potential for nutrient and microbial removal, the Abelmoschus esculentus, Solanum melongena, and Capsicum annuum L. plants were selected to grow in a hybrid constructed wetland (CW) under natural conditions. The removal efficiency of the A. esculentus, S. melongena, and C. annuum L. in the CW system varied between 59.8 to 68.5% for total phosphorous (TP), 40.3 to 53.1% for ammonium (NH4+), and 33.6 to 45.1% for total nitrogen (TN). The influent sample contained multiple pathogenic bacteria, including Alcaligenes faecalis, Staphylococcus aureus, and Escherichia coli, with Capsicum annuum exhibiting a positive association with 7 of the 11 detected species, whereas microbial removal efficiency was notably higher in the S. melongena bed, potentially attributed to temperature variations and plant-facilitated oxygen release rates. While utilizing constructed wetlands for vegetable cultivation holds promising potential to address the disparity between water and food supply and yield various environmental, economic, and social benefits, it is crucial to note that the wastewater source may contain heavy metals, posing a risk of their transmission to humans through the food chain.

Shape Matters: Detecting Vertebral Fractures Using Differentiable Point-Based Shape Decoding

Background: Degenerative spinal pathologies are highly prevalent among the elderly population. Timely diagnosis of osteoporotic fractures and other degenerative deformities enables proactive measures to mitigate the risk of severe back pain and disability. Methods: We explore the use of shape auto-encoders for vertebrae, advancing the state of the art through robust automatic segmentation models trained without fracture labels and recent geometric deep learning techniques. Our shape auto-encoders are pre-trained on a large set of vertebrae surface patches. This pre-training step addresses the label scarcity problem faced when learning the shape information of vertebrae for fracture detection from image intensities directly. We further propose a novel shape decoder architecture: the point-based shape decoder. Results: Employing segmentation masks that were generated using the TotalSegmentator, our proposed method achieves an AUC of 0.901 on the VerSe19 testset. This outperforms image-based and surface-based end-to-end trained models. Our results demonstrate that pre-training the models in an unsupervised manner enhances geometric methods like PointNet and DGCNN. Conclusion: Our findings emphasize the advantages of explicitly learning shape features for diagnosing osteoporotic vertebrae fractures. This approach improves the reliability of classification results and reduces the need for annotated labels.

Creating and Leveraging a Synthetic Dataset of Cloud Optical Thickness Measures for Cloud Detection in MSI

Cloud formations often obscure optical satellite-based monitoring of the Earth’s surface, thus limiting Earth observation (EO) activities such as land cover mapping, ocean color analysis, and cropland monitoring. The integration of machine learning (ML) methods within the remote sensing domain has significantly improved performance for a wide range of EO tasks, including cloud detection and filtering, but there is still much room for improvement. A key bottleneck is that ML methods typically depend on large amounts of annotated data for training, which are often difficult to come by in EO contexts. This is especially true when it comes to cloud optical thickness (COT) estimation. A reliable estimation of COT enables more fine-grained and application-dependent control compared to using pre-specified cloud categories, as is common practice. To alleviate the COT data scarcity problem, in this work, we propose a novel synthetic dataset for COT estimation, which we subsequently leverage for obtaining reliable and versatile cloud masks on real data. In our dataset, top-of-atmosphere radiances have been simulated for 12 of the spectral bands of the Multispectral Imagery (MSI) sensor onboard Sentinel-2 platforms. These data points have been simulated under consideration of different cloud types, COTs, and ground surface and atmospheric profiles. Extensive experimentation of training several ML models to predict COT from the measured reflectivity of the spectral bands demonstrates the usefulness of our proposed dataset. In particular, by thresholding COT estimates from our ML models, we show on two satellite image datasets (one that is publicly available, and one which we have collected and annotated) that reliable cloud masks can be obtained. The synthetic data, the newly collected real dataset, code and models have been made publicly available.

Visible light-promoted anti-biofouling performance of cellulose acetate membrane for reverse osmosis desalination

Sea water desalination is regarded as a major solution that could alleviate the water scarcity problem. Reverse osmosis (RO) is typically employed to recover fresh water from sea and brackish water via economical means. RO membrane fouling remains a critical issue restricting their widespread application. In this work, a tertiary thiophenal quaternary ammonium salt-based antibacterial agent was covalently reacted with cellulose acetate (CA) to obtain contact-active antibacterial quaternized CA-RO membrane (QCA-RO). The membrane was characterized by Fourier transform infrared spectroscopy, X-ray photoelectron spectroscopy, scanning electron microscopy, water contact angle testing, and X-ray diffraction spectroscopy. The obtained QCA-RO membrane displayed good antibacterial activity against Pseudomonas aeruginosa and Staphylococcus aureus and had bactericidal rates of 99 % in the presence of visible light. Results showed that embedding the quaternary ammonium salt did not cause any significant changes to the morphology, mechanical performance, and thermal stability of the RO membrane. The method described in this work not only produces QCA-RO membranes with good anti-biofilm performance but also presents great potential in seawater desalination.

Named Entity Recognition in Government Audit Texts Based on ChineseBERT and Character-Word Fusion

Named entity recognition of government audit text is a key task of intelligent auditing. Aiming at the problems of scarcity of corpus in the field of governmental auditing, insufficient utilization of traditional character vector word-level information features, and insufficient capturing of auditing entity features, this study builds its own dataset in the field of auditing and proposes the model CW-CBGC for recognizing named entities in governmental auditing text based on ChineseBERT and character-word fusion. First, the ChineseBERT pre-training model is used to extract the character vector that integrates the features of glyph and pinyin, combining with word vectors dynamically constructed by the BERT pre-training model; then, the sequences of character-word fusion vectors are input into the bi-directional gated recurrent neural network (BiGRU) to learn the textual features. Finally, the global optimal sequence label is generated by Conditional Random Field (CRF), and the GHM classification loss function is used in the model training to solve the problem of error evaluation under the conditions of noisy entities and unbalanced number of entities. The F1 value of this study’s model on the audit dataset is 97.23%, which is 3.64% higher than the baseline model’s F1 value; the F1 value of the model on the public dataset Resume is 96.26%, which is 0.73–2.78% higher than the mainstream model. The experimental results show that the model proposed in this paper can effectively recognize the entities in government audit texts and has certain generalization ability.

Taylor Tuna Optimizer‐based hybrid deep Q‐network for channel assignment in cognitive radio networks with user mobility and power control

SummaryCognitive radio networks (CRNs) have emerged as a promising solution to address the spectrum scarcity problem by allowing unlicensed secondary users (SUs) to opportunistically access the underutilized licensed spectrum bands. However, efficient channel assignment in CRNs, especially with user mobility and power control considerations, remains a challenging problem. Traditional channel assignment algorithms often struggle to adapt to changing network conditions, resulting in suboptimal performance. To address these challenges, this research presents a novel Taylor Tuna Optimizer‐based hybrid deep Q‐network (TayTO‐based HDQNet) for channel assignment in CRNs with user mobility and power control considerations. The proposed TayTO‐based HDQNet combines the Elman neural network architecture with the reinforcement learning framework of deep Q‐networks, tuned using the Taylor Tuna Optimizer. This hybrid approach enables intelligent channel assignment decisions while considering power consumption constraints, leading to efficient communication in CRNs. To train the HDQNet agent, a comprehensive dataset is generated through simulations of various CRN scenarios, incorporating channel availability, interference levels, and power consumption for different channel assignment decisions. The HDQNet agent undergoes iterative training using this dataset to develop an optimal channel assignment policy. Experimental results demonstrate the effectiveness of the proposed TayTO‐based HDQNet approach done by MATLAB, achieving a high success rate of 98.47% and surpassing the reliability scores of previous studies. This highlights the improved performance and reliability of the proposed approach for channel assignment in CRNs.

Link stability based multipath routing and effective mobility prediction in cognitive radio enabled vehicular ad hoc network

Vehicular ad hoc networks (VANETs) provide a robust infrastructure for intelligent transportation system (ITS) applications. VANET communication involves vehicle-to-vehicle and vehicle-to-infrastructure connections, primarily with roadside units (RSUs). Analyzing cognitive radio (CR)-VANET studies revealed two key performance issues: high energy consumption and latency. To address these challenges, we propose a novel approach: link stability and mobility prediction-based clustered CR-VANETs, known as LMCCR-VANET. LMCCR-VANET consists of four main components: CR-VANET construction, clustering model, speed-based mobility prediction, and link-based multipath routing. Initially, we establish cluster-based CR-VANETs to analyze and mitigate spectrum scarcity and power utilization problems in VANETs. Mobility prediction evaluates vehicle speed variations and predictions. Finally, employing link stability-based multipath routing (LSMR) in conjunction with the fuzzy interference model and ad hoc on-demand multipath distance vector (AOMDV) routing protocol ensures stable and efficient routing. Experimental results showcase the superiority of LMCCR-VANET. It exhibits enhanced energy efficiency, delivery rates, reduced energy consumption, end-to-end latency, and routing overhead when compared to recent works such as SCCR-VANET, CFCR-VANET, and MMCR-VANET.

Spatiotemporal attention aided graph convolution networks for dynamic spectrum prediction

To solve the spectrum scarcity problem, dynamic spectrum access (DSA) technology has emerged as a promising solution. Effectively implementing DSA demands accurate and efficient spectrum prediction. However, complex spatiotemporal correlation and heterogeneity in spectrum observations usually make spectral prediction arduous and even ambiguous. In this letter, we propose a spectrum prediction method based on an attention-aided graph convolutional neural network (AttGCN) to capture features in both spatial and temporal dimensions. By leveraging the attention mechanism, the AttGCN adapts its attention weights at different time steps and spatial positions, thus enabling itself to seize changes in spatiotemporal correlations dynamically. Simulation results show that the proposed spectrum prediction method performs better than baseline algorithms in long-term forecasting tasks.