Soil moisture, organic carbon, and nitrogen content prediction with hyperspectral data using regression models
- Authors: Datta, Dristi , Paul, Manoranjan , Murshed, Manzur , Teng, Shyh Wei , Schmidtke, Leigh
- Date: 2022
- Type: Text , Journal article
- Relation: Sensors (Basel, Switzerland) Vol. 22, no. 20 (2022), p.
- Full Text:
- Reviewed:
- Description: Soil moisture, soil organic carbon, and nitrogen content prediction are considered significant fields of study as they are directly related to plant health and food production. Direct estimation of these soil properties with traditional methods, for example, the oven-drying technique and chemical analysis, is a time and resource-consuming approach and can predict only smaller areas. With the significant development of remote sensing and hyperspectral (HS) imaging technologies, soil moisture, carbon, and nitrogen can be estimated over vast areas. This paper presents a generalized approach to predicting three different essential soil contents using a comprehensive study of various machine learning (ML) models by considering the dimensional reduction in feature spaces. In this study, we have used three popular benchmark HS datasets captured in Germany and Sweden. The efficacy of different ML algorithms is evaluated to predict soil content, and significant improvement is obtained when a specific range of bands is selected. The performance of ML models is further improved by applying principal component analysis (PCA), a dimensional reduction method that works with an unsupervised learning method. The effect of soil temperature on soil moisture prediction is evaluated in this study, and the results show that when the soil temperature is considered with the HS band, the soil moisture prediction accuracy does not improve. However, the combined effect of band selection and feature transformation using PCA significantly enhances the prediction accuracy for soil moisture, carbon, and nitrogen content. This study represents a comprehensive analysis of a wide range of established ML regression models using data preprocessing, effective band selection, and data dimension reduction and attempt to understand which feature combinations provide the best accuracy. The outcomes of several ML models are verified with validation techniques and the best- and worst-case scenarios in terms of soil content are noted. The proposed approach outperforms existing estimation techniques.
Preparation of starch-based nanoparticles through high-pressure homogenization and miniemulsion cross-linking: Influence of various process parameters on particle size and stability
- Authors: Shi, Aimin , Li, Dong , Wang, Li Ming , Li, Bingzheng , Adhikari, Benu
- Date: 2010
- Type: Text , Journal article
- Relation: Carbohydrate Polymers Vol. 83, no. 4 (2010), p. 1604-1610
- Full Text: false
- Reviewed:
- Description: A new and convenient synthetic route using high-pressure homogenization combined with water-in-oil (w/o) miniemulsion cross-linking technique was used to prepare sodium trimetaphosphate (STMP)-cross-linked starch nanoparticles. Dynamic light scattering (DLS) and transmission electron microscopy (TEM) revealed that starch nanoparticles had narrow size distribution, good dispersibility and spherical shape. Effect of process parameters (surfactant content, water/oil ratio, starch concentration, homogenization pressure and cycles) on the starch nanoparticle size in miniemulsion was evaluated. We show that there is an optimal surfactant concentration giving rise to smaller starch nanoparticles and better stability. Apart from the water/oil ratio and starch concentration, the homogenization pressure and cycles (passes) also significantly affect the size of starch nanoparticles (p < 0.05). The stability analysis of starch nanoparticles in water for 2 h to 2 days and in temperature ranges of 25-45 °C showed firm structure and good stability. These nanoparticles are expected to be exploited as drug carriers. © 2010 Elsevier Ltd. All rights reserved.
- Description: 2003008433
Experimental investigations on mechanical performance of rocks under fatigue loads and biaxial confinements
- Authors: Du, Kun , Li, Xue-feng , Yang, Cheng-zhi , Zhou, Jian , Chen, Shao-jie , Manoj, Khandelwal
- Date: 2020
- Type: Text , Journal article
- Relation: Journal of Central South University Vol. 27, no. 10 (2020), p. 2985-2998
- Full Text:
- Reviewed:
- Description: In this research, a series of biaxial compression and biaxial fatigue tests were conducted to investigate the mechanical behaviors of marble and sandstone under biaxial confinements. Experimental results demonstrate that the biaxial compressive strength of rocks under biaxial compression increases firstly, and subsequently decreases with increase of the intermediate principal stress. The fatigue failure characteristics of the rocks in biaxial fatigue tests are functions of the peak value of fatigue loads, the intermediate principal stress and the rock lithology. With the increase of the peak values of fatigue loads, the fatigue lives of rocks decrease. The intermediate principal stress strengthens the resistance ability of rocks to fatigue loads except considering the strength increasing under biaxial confinements. The fatigue lives of rocks increase with the increase of the intermediate principal stress under the same ratio of the fatigue load and their biaxial compressive strength. The acoustic emission (AE) and fragments studies showed that the sandstone has higher ability to resist the fatigue loads compared to the marble, and the marble generated a greater number of smaller fragments after fatigue failure compared to the sandstone. So, it can be inferred that the rock breaking efficiency and rock burst is higher or severer induced by fatigue loading than that induced by monotonous quasi-static loading, especially for hard rocks. © 2020, Central South University Press and Springer-Verlag GmbH Germany, part of Springer Nature.
Ode to form
- Authors: Mestrom, Sanne
- Date: 2012
- Type: Text , Visual art work
- Full Text:
The effect of addition of flaxseed gum on the emulsion properties of soybean protein isolate (SPI)
- Authors: Wang, Yong , Li, Dong , Wang, Li Ming , Adhikari, Benu
- Date: 2011
- Type: Text , Journal article
- Relation: Journal of Food Engineering Vol. 104, no. 1 (2011), p. 56-62
- Full Text: false
- Reviewed:
- Description: The effect of addition of flaxseed gum on the emulsion properties of soybean protein isolate (SPI) were investigated in this study. Flaxseed gum with 0.05-0.5% (w/v) concentration was used together with 1% (w/v) SPI to emulsify 10% (v/v) soybean oil. The emulsion was analyzed for emulsion activity (turbidity), stability, particle size, surface charge, and rheological properties. The turbidity and absolute zeta-potential values decreased initially by the addition of flaxseed gum and subsequently increased with further increase in the gum concentration to reach their peak around 0.35% (w/v) gum. The particle size of the emulsion decreased and reached a minimum value at 0.1% (w/v) gum concentration. Any increase in gum concentration beyond this value resulted into increase in the particle size. This study would help to widen the application of SPI and flaxseed gum mixture, and also contribute to the understanding of protein-gum interaction in emulsion. © 2010 Elsevier Ltd. All rights reserved.
Comparative analysis of machine and deep learning models for soil properties prediction from hyperspectral visual band
- Authors: Datta, Dristi , Paul, Manoranjan , Murshed, Manzur , Teng, Shyh Wei , Schmidtke, Leigh
- Date: 2023
- Type: Text , Journal article
- Relation: Environments Vol. 10, no. 5 (2023), p. 77
- Full Text:
- Reviewed:
- Description: Estimating various properties of soil, including moisture, carbon, and nitrogen, is crucial for studying their correlation with plant health and food production. However, conventional methods such as oven-drying and chemical analysis are laborious, expensive, and only feasible for a limited land area. With the advent of remote sensing technologies like multi/hyperspectral imaging, it is now possible to predict soil properties non-invasive and cost-effectively for a large expanse of bare land. Recent research shows the possibility of predicting those soil contents from a wide range of hyperspectral data using good prediction algorithms. However, these kinds of hyperspectral sensors are expensive and not widely available. Therefore, this paper investigates different machine and deep learning techniques to predict soil nutrient properties using only the red (R), green (G), and blue (B) bands data to propose a suitable machine/deep learning model that can be used as a rapid soil test. Another objective of this research is to observe and compare the prediction accuracy in three cases i. hyperspectral band ii. full spectrum of the visual band, and iii. three-channel of RGB band and provide a guideline to the user on which spectrum information they should use to predict those soil properties. The outcome of this research helps to develop a mobile application that is easy to use for a quick soil test. This research also explores learning-based algorithms with significant feature combinations and their performance comparisons in predicting soil properties from visual band data. For this, we also explore the impact of dimensional reduction (i.e., principal component analysis) and transformations (i.e., empirical mode decomposition) of features. The results show that the proposed model can comparably predict the soil contents from the three-channel RGB data.
Estimating the mean cutting force of conical picks using random forest with salp swarm algorithm
- Authors: Zhou, Jian , Dai, Yong , Tao, Ming , Khandelwal, Manoj , Zhao, Mingsheng , Li, Qiyue
- Date: 2023
- Type: Text , Journal article
- Relation: Results in Engineering Vol. 17, no. (2023), p.
- Full Text:
- Reviewed:
- Description: Conical picks are widely used as cutting tools in shearers and roadheaders, and the mean cutting force (MCF) is one of the important parameters affecting conical pick performance. As MCF depends on a number of parameters and due to that the existing empirical and theoretical formulas and numerical modelling are not sufficient enough and reliable to predict MCF in a proficient manner. So, in this research, a novel intelligent model based on a random forest algorithm (RF) and a heuristic algorithm called the salp swarm algorithm (SSA) have been applied to determine the optimal hyper-parameters in RF, and root mean square error is used as a fitness function. A total of 188 data samples including 50 rock types and seven parameters (tensile strength of the rock
Optimum design of limaçon gas expanders based on thermodynamic performance
- Authors: Sultan, Ibrahim
- Date: 2012
- Type: Text , Journal article
- Relation: Applied Thermal Engineering Vol. 39, no. 4 (2012), p. 188-197
- Full Text:
- Reviewed:
- Description: Positive displacement expanders are acquiring popularity due to the current push to harvest energy from low-grade heat resources which have been previously overlooked. The limaçon technology does offer a simple and reliable design with a considerable potential for small-size (≤4 kW) power plants. This paper presents a thermodynamic model for the limaçon design and goes on to utilise this model in an optimisation procedure adopted to calculate the expanders geometric parameters for specific power and operating constraints. The numerical method employed to solve the thermodynamic model is presented for the benefit of the reader. Two design case studies, for expanders with and without an inlet control valve, are offered at the end of the paper to prove the validity of the presented concepts and their suitability for the analysis. © 2012 Elsevier Ltd.
Effect of moisture content and heating rates on the thermal properties of rice embryos measured by differential scanning calorimetry
- Authors: Yan, Ping-yu , Wang, Li-jun , Li, Dong , Adhikari, Benu , Mao, Zhihuai
- Date: 2016
- Type: Text , Journal article
- Relation: International Agricultural Engineering Journal Vol. 25, no. 1 (2016), p. 38-42
- Full Text: false
- Reviewed:
- Description: The effect of moisture content on the thermal properties of rice embryos was investigated using differential scanning calorimetry (DSC). A long grain hybrid rice variety (Jinyou 974) grown in Hunan Province of China was selected in this investigation. The temperature scanning tests were carried out from 20°C to 180°C at different heating rates from 2°C/min to 20°C/min. Consistently higher values of glass transition temperature (Tg) were measured when higher heating rates were used during DSC measurements at every set of moisture contents. The Tg values decreased from (65.28±0.38)°C to (31.08±0.26)°C with increase in moisture content from (10.7±0.3)% to (22.0±0.7)% (w/w). The analysis of variance and the regression analysis showed that both the linear function and Gordon Taylor model can adequately represent the variation of Tg with moisture content (R2 > 0.96).
Low amplitude fatigue performance of sandstone, marble, and granite under high static stress
- Authors: Du, Kun , Su, Rui , Zhou, Jian , Wang, Shaofeng , Khandelwal, Manoj
- Date: 2021
- Type: Text , Journal article
- Relation: Geomechanics and Geophysics for Geo-Energy and Geo-Resources Vol. 7, no. 3 (2021), p.
- Full Text:
- Reviewed:
- Description: Abstract: Fatigue tests under high static pre-stress loads can provide meaningful results to better understand the time-dependent failure characteristics of rock and rock-like materials. However, fatigue tests under high static pre-stress loads are rarely reported in previous literature. In this study, the rock specimens were loaded with a high static pre-stress representing 70% and 80% of the uniaxial compressive strength (UCS), and cyclic fatigue loads with a low amplitude (i.e., 5%, 7.5% and 10% of the UCS) were applied. The results demonstrate that the fatigue life decreased as the static pre-stress level or amplitude of fatigue loads increased for different rock types. The high static pre-stress affected the fatigue life greatly when the static pre-stress was larger than the damage stress of rocks in uniaxial compression tests. The accumulative fatigue damage exhibited three stages during the fatigue failure process, i.e., crack initiation, uniform velocity, and acceleration, and the fatigue modulus showed an “S-type” change trend. The lateral and volumetric strains had a much higher sensitivity to the cyclic loading and could be used to predict fatigue failure characteristics. It was observed that volumetric strain εv = 0 is a threshold for microcracks coalescence and is an important value for estimating the fatigue life. Article highlights: Fatigue mechanical performance of high static pre-stressed rocks were evaluated.The results demonstrate that the fatigue life decreased as the static pre-stress level increased and the static pre-stress affected the fatigue life more than the amplitude of fatigue loads.The volumetric strain of zero before fatigue loading is a threshold for fatigue failure of rocks under high static stress. © 2021, The Author(s), under exclusive licence to Springer Nature Switzerland AG. **Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliate “Manoj Khandelwal” is provided in this record**
Recent contributions to linear semi-infinite optimization
- Authors: Goberna, Miguel , López, Marco
- Date: 2017
- Type: Text , Journal article
- Relation: 4OR: A Quarterly Journal of Operations Research Vol. 15, no. 3 (2017), p. 221-264
- Relation: http://purl.org/au-research/grants/arc/DP160100854
- Full Text:
- Reviewed:
- Description: This paper reviews the state-of-the-art in the theory of deterministic and uncertain linear semi-infinite optimization, presents some numerical approaches to this type of problems, and describes a selection of recent applications in a variety of fields. Extensions to related optimization areas, as convex semi-infinite optimization, linear infinite optimization, and multi-objective linear semi-infinite optimization, are also commented. © 2017, Springer-Verlag GmbH Germany.
A guide to the short, long and circular RNAs in hypertension and cardiovascular disease
- Authors: Prestes, Priscilla , Maier, Michelle , Woods, Bradley , Charchar, Fadi
- Date: 2020
- Type: Text , Journal article , Review
- Relation: International Journal of Molecular Sciences Vol. 21, no. 10 (2020)
- Full Text:
- Reviewed:
- Description: Cardiovascular disease (CVD) is the leading cause of morbidity and mortality in adults in developed countries. CVD encompasses many diseased states, including hypertension, coronary artery disease and atherosclerosis. Studies in animal models and human studies have elucidated the contribution of many genetic factors, including non-coding RNAs. Non-coding RNAs are RNAs not translated into protein, involved in gene expression regulation post-transcriptionally and implicated in CVD. Of these, circular RNAs (circRNAs) and microRNAs are relevant. CircRNAs are created by the back-splicing of pre-messenger RNA and have been underexplored as contributors to CVD. These circRNAs may also act as biomarkers of human disease, as they can be extracted from whole blood, plasma, saliva and seminal fluid. CircRNAs have recently been implicated in various disease processes, including hypertension and other cardiovascular disease. This review article will explore the promising and emerging roles of circRNAs as potential biomarkers and therapeutic targets in CVD, in particular hypertension. © 2020 by the authors. Licensee MDPI, Basel, Switzerland.
Discussion of “Behaviour of a Foam Mixture as a Lightweight Construction Material” [Int J of Geosynth and Ground Eng (2021) 7(3), 51]
- Authors: O’Kelly, Brendan , Soltani, Amin
- Date: 2022
- Type: Text , Journal article
- Relation: International Journal of Geosynthetics and Ground Engineering Vol. 8, no. 2 (2022), p.
- Full Text:
- Reviewed:
Psychological distress, fear and coping strategies among hong kong people during the COVID-19 pandemic
- Authors: Chair, Sek , Chien, Wai , Liu, Ting , Lam, Louisa , Cross, Wendy , Banik, Biswajit , Rahman, Muhammad Aziz
- Date: 2023
- Type: Text , Journal article
- Relation: Current Psychology Vol. 42, no. 3 (2023), p. 2538-2557
- Full Text:
- Reviewed:
- Description: The COVID-19 pandemic contributed to potential adverse effects on the mental health status of a wide range of people. This study aimed to identify factors associated with psychological distress, fear and coping strategies during the COVID-19 pandemic in Hong Kong. A cross-sectional online survey was conducted among general population in Hong Kong. Psychological distress was assessed using the Kessler Psychological Distress Scale; level of fear was evaluated using the Fear of COVID-19 scale; and coping strategies were assessed using the Brief Resilient Coping Scale. Multivariable logistic regression was used to identify key factors associated with these mental health variables. Of the 555 participants, 53.9% experienced moderate to very high levels of psychological distress, 31.2% experienced a high level of fear of COVID-19, and 58.6% showed moderate to high resilient coping. Multivariable logistic regression indicated that living with family members, current alcohol consumption, and higher level of fear were associated with higher levels of psychological distress; perceived stress due to a change in employment condition, being a frontline worker, experiencing ‘moderate to very high’ distress, and healthcare service use to overcome the COVID-19 related stress in past 6 months were associated with a higher level of fear; and perceived better mental health status was associated with a moderate to high resilient coping. This study identified key factors associated with distress, fear and coping strategies during the pandemic in Hong Kong. Mental health support strategies should be provided continuously to prevent the mental impact of the pandemic from turning into long-term illness. © 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
Mouse models for abdominal aortic aneurysm
- Authors: Golledge, Jonathan , Krishna, Smriti , Wang, Yutang
- Date: 2022
- Type: Text , Journal article , Review
- Relation: British Journal of Pharmacology Vol. 179, no. 5 (2022), p. 792-810
- Full Text:
- Reviewed:
- Description: Abdominal aortic aneurysm (AAA) rupture is estimated to cause 200,000 deaths each year. Currently, the only treatment for AAA is surgical repair; however, this is only indicated for large asymptomatic, symptomatic or ruptured aneurysms, is not always durable, and is associated with a risk of serious perioperative complications. As a result, patients with small asymptomatic aneurysms or who are otherwise unfit for surgery are treated conservatively, but up to 70% of small aneurysms continue to grow, increasing the risk of rupture. There is thus an urgent need to develop drug therapies effective at slowing AAA growth. This review describes the commonly used mouse models for AAA. Recent research in these models highlights key roles for pathways involved in inflammation and cell turnover in AAA pathogenesis. There is also evidence for long non-coding RNAs and thrombosis in aneurysm pathology. Further well-designed research in clinically relevant models is expected to be translated into effective AAA drugs. LINKED ARTICLES: This article is part of a themed issue on Preclinical Models for Cardiovascular disease research (BJP 75th Anniversary). To view the other articles in this section visit http://onlinelibrary.wiley.com/doi/10.1111/bph.v179.5/issuetoc. © 2020 The British Pharmacological Society
A robust gradient based method for building extraction from LiDAR and photogrammetric imagery
- Authors: Siddiqui, Fasahat , Teng, Shyh , Awrangjeb, Mohammad , Lu, Guojun
- Date: 2016
- Type: Text , Journal article
- Relation: Sensors (Switzerland) Vol. 16, no. 7 (2016), p. 1-24
- Full Text:
- Reviewed:
- Description: Existing automatic building extraction methods are not effective in extracting buildings which are small in size and have transparent roofs. The application of large area threshold prohibits detection of small buildings and the use of ground points in generating the building mask prevents detection of transparent buildings. In addition, the existingmethods use numerous parameters to extract buildings in complex environments, e.g.,hilly area and high vegetation. However, the empirical tuning of large number of parameters reduces the robustness of building extraction methods. This paper proposes a novel Gradient-based Building Extraction (GBE) method to address these limitations. The proposed method transforms the Light Detection And Ranging (LiDAR) height information into intensity image without interpolation of point heights and then analyses the gradient information in the image. Generally, building roof planes have a constant height change along the slope of a roof plane whereas trees have a random height change. With such an analysis, buildings of a greater range of sizes with a transparent or opaque roof can be extracted. In addition, a local colour matching approach is introduced as a post-processing stage to eliminate trees. This stage of our proposed method does not require any manual setting and all parameters are set automatically from the data. The other post processing stages including variance, point density and shadow elimination are also applied to verify the extracted buildings, where comparatively fewer empirically set parameters are used. The performance of the proposed GBE method is evaluated on two benchmark data sets by using the object and pixel based metrics (completeness, correctness and quality). Our experimental results show the effectiveness of the proposed method in eliminating trees, extracting buildings of all sizes, and extracting buildings with and without transparent roof. When compared with current state-of-the-art building extraction methods, the proposed method outperforms the existing methods in various evaluation metrics. © 2016 by the authors; licensee MDPI, Basel, Switzerland.
Initial state of excavated soil and rock (ESR) to influence the stabilisation with cement
- Authors: Lu, Yi , Xu, Changhao , Baghbani, Abolfazl
- Date: 2023
- Type: Text , Journal article
- Relation: Construction and Building Materials Vol. 400, no. (2023), p.
- Full Text:
- Reviewed:
- Description: This paper investigates the initial state of excavated soil and rock (ESR). These initial states include dry density, organic content, water content (Wc), cement content (Cc), liquid index (LI), dry or wet mixing method. Three ESRs collected from tunnelling projects and kaolin were used in this study to compare. The specimens (i.e., 50 mm in diameter and 100 mm in height) were prepared in the laboratory and cured at 7 and 14 days, and then assessed by the unconfined compressive strength (UCS) test. The analysis shows that the ratio of Wc/Cc is the primary factor to obtain different UCS for high LI ESR and a simple equation is proposed for quick prediction. For ESR with a more general LI, predictive equations are also proposed in terms of artificial neural network (ANN) and genetic programming (GP) for 7-days curing time. The results indicate that the both ANN models with Bayesian Regularization (BR) algorithm outperform ANN with Levenberg-Marquardt (LM) and GP model are accurate to predict UCS of mixtures. © 2023 Elsevier Ltd
Attributed collaboration network embedding for academic relationship mining
- Authors: Wang, Wei , Liu, Jiaying , Tang, Tao , Tuarob, Suppawong , Xia, Feng , Gong, Zhiguo , King, Irwin
- Date: 2021
- Type: Text , Journal article
- Relation: ACM Transactions on the Web Vol. 15, no. 1 (2021), p.
- Full Text:
- Reviewed:
- Description: Finding both efficient and effective quantitative representations for scholars in scientific digital libraries has been a focal point of research. The unprecedented amounts of scholarly datasets, combined with contemporary machine learning and big data techniques, have enabled intelligent and automatic profiling of scholars from this vast and ever-increasing pool of scholarly data. Meanwhile, recent advance in network embedding techniques enables us to mitigate the challenges of large scale and sparsity of academic collaboration networks. In real-world academic social networks, scholars are accompanied with various attributes or features, such as co-authorship and publication records, which result in attributed collaboration networks. It has been observed that both network topology and scholar attributes are important in academic relationship mining. However, previous studies mainly focus on network topology, whereas scholar attributes are overlooked. Moreover, the influence of different scholar attributes are unclear. To bridge this gap, in this work, we present a novel framework of Attributed Collaboration Network Embedding (ACNE) for academic relationship mining. ACNE extracts four types of scholar attributes based on the proposed scholar profiling model, including demographics, research, influence, and sociability. ACNE can learn a low-dimensional representation of scholars considering both scholar attributes and network topology simultaneously. We demonstrate the effectiveness and potentials of ACNE in academic relationship mining by performing collaborator recommendation on two real-world datasets and the contribution and importance of each scholar attribute on scientific collaborator recommendation is investigated. Our work may shed light on academic relationship mining by taking advantage of attributed collaboration network embedding. © 2020 ACM.
Global optimality conditions for some classes of polynomial integer programming problems
- Authors: Quan, Jing , Wu, Zhiyou , Li, Guoquan
- Date: 2011
- Type: Text , Journal article
- Relation: Journal of Industrial and Management Optimization Vol. 7, no. 1 (2011), p. 67-78
- Full Text:
- Reviewed:
- Description: In this paper, some verifiable necessary global optimality conditions and sufficient global optimality conditions for some classes of polynomial integer programming problems are established. The relationships between these necessary global optimality conditions and these sufficient global optimality conditions are also discussed. The main theoretical tool for establishing these optimality conditions is abstract convexity.
Knowledge graphs : opportunities and challenges
- Authors: Peng, Ciyuan , Xia, Feng , Naseriparsa, Mehdi , Osborne, Francesco
- Date: 2023
- Type: Text , Journal article
- Relation: Artificial Intelligence Review Vol. 56, no. 11 (2023), p. 13071-13102
- Full Text:
- Reviewed:
- Description: With the explosive growth of artificial intelligence (AI) and big data, it has become vitally important to organize and represent the enormous volume of knowledge appropriately. As graph data, knowledge graphs accumulate and convey knowledge of the real world. It has been well-recognized that knowledge graphs effectively represent complex information; hence, they rapidly gain the attention of academia and industry in recent years. Thus to develop a deeper understanding of knowledge graphs, this paper presents a systematic overview of this field. Specifically, we focus on the opportunities and challenges of knowledge graphs. We first review the opportunities of knowledge graphs in terms of two aspects: (1) AI systems built upon knowledge graphs; (2) potential application fields of knowledge graphs. Then, we thoroughly discuss severe technical challenges in this field, such as knowledge graph embeddings, knowledge acquisition, knowledge graph completion, knowledge fusion, and knowledge reasoning. We expect that this survey will shed new light on future research and the development of knowledge graphs. © 2023, The Author(s).