Search results

High-resolution remote sensing images possess a wealth of semantic information. However, these images often contain objects of different sizes and distributions, which make the semantic segmentation task challenging. In this paper, a bidirectional feature fusion network (BFFNet) is designed to address this challenge, which aims at increasing the accurate recognition of surface objects in order to effectively classify special features.

There are two main crucial elements in BFFNet. Firstly, the mean-weighted module (MWM) is used to obtain the key features in the main network. Secondly, the proposed polarization enhanced branch network performs feature extraction simultaneously with the main network to obtain different feature information. The authors then fuse these two features in both directions while applying a cross-entropy loss function to monitor the network training process. Finally, BFFNet is validated on two publicly available datasets, Potsdam and Vaihingen.

In this paper, a quantitative analysis method is used to illustrate that the proposed network achieves superior performance of 2–6%, respectively, compared to other mainstream segmentation networks from experimental results on two datasets. Complete ablation experiments are also conducted to demonstrate the effectiveness of the elements in the network. In summary, BFFNet has proven to be effective in achieving accurate identification of small objects and in reducing the effect of shadows on the segmentation process.

The originality of the paper is the proposal of a BFFNet based on multi-scale and multi-attention strategies to improve the ability to accurately segment high-resolution and complex remote sensing images, especially for small objects and shadow-obscured objects.

The paper aims to tackle the classification of Remote Sensing Images (RSIs), which presents a significant challenge for computer algorithms due to the inherent characteristics of clustered ground objects and noisy backgrounds. Recent research typically leverages larger volume models to achieve advanced performance. However, the operating environments of remote sensing commonly cannot provide unconstrained computational and storage resources. It requires lightweight algorithms with exceptional generalization capabilities.

This study introduces an efficient knowledge distillation (KD) method to build a lightweight yet precise convolutional neural network (CNN) classifier. This method also aims to substantially decrease the training time expenses commonly linked with traditional KD techniques. This approach entails extensive alterations to both the model training framework and the distillation process, each tailored to the unique characteristics of RSIs. In particular, this study establishes a robust ensemble teacher by independently training two CNN models using a customized, efficient training algorithm. Following this, this study modifies a KD loss function to mitigate the suppression of non-target category predictions, which are essential for capturing the inter- and intra-similarity of RSIs.

This study validated the student model, termed KD-enhanced network (KDE-Net), obtained through the KD process on three benchmark RSI data sets. The KDE-Net surpasses 42 other state-of-the-art methods in the literature published from 2020 to 2023. Compared to the top-ranked method’s performance on the challenging NWPU45 data set, KDE-Net demonstrated a noticeable 0.4% increase in overall accuracy with a significant 88% reduction in parameters. Meanwhile, this study’s reformed KD framework significantly enhances the knowledge transfer speed by at least three times.

This study illustrates that the logit-based KD technique can effectively develop lightweight CNN classifiers for RSI classification without substantial sacrifices in computation and storage costs. Compared to neural architecture search or other methods aiming to provide lightweight solutions, this study’s KDE-Net, based on the inherent characteristics of RSIs, is currently more efficient in constructing accurate yet lightweight classifiers for RSI classification.

Classification of remote sensing images (RSI) is a challenging task in computer vision. Recently, researchers have proposed a variety of creative methods for automatic recognition of RSI, and feature fusion is a research hotspot for its great potential to boost performance. However, RSI has a unique imaging condition and cluttered scenes with complicated backgrounds. This larger difference from nature images has made the previous feature fusion methods present insignificant performance improvements.

This work proposed a two-convolutional neural network (CNN) fusion method named main and branch CNN fusion network (MBC-Net) as an improved solution for classifying RSI. In detail, the MBC-Net employs an EfficientNet-B3 as its main CNN stream and an EfficientNet-B0 as a branch, named MC-B3 and BC-B0, respectively. In particular, MBC-Net includes a long-range derivation (LRD) module, which is specially designed to learn the dependence of different features. Meanwhile, MBC-Net also uses some unique ideas to tackle the problems coming from the two-CNN fusion and the inherent nature of RSI.

Extensive experiments on three RSI sets prove that MBC-Net outperforms the other 38 state-of-the-art (STOA) methods published from 2020 to 2023, with a noticeable increase in overall accuracy (OA) values. MBC-Net not only presents a 0.7% increased OA value on the most confusing NWPU set but also has 62% fewer parameters compared to the leading approach that ranks first in the literature.

MBC-Net is a more effective and efficient feature fusion approach compared to other STOA methods in the literature. Given the visualizations of grad class activation mapping (Grad-CAM), it reveals that MBC-Net can learn the long-range dependence of features that a single CNN cannot. Based on the tendency stochastic neighbor embedding (t-SNE) results, it demonstrates that the feature representation of MBC-Net is more effective than other methods. In addition, the ablation tests indicate that MBC-Net is effective and efficient for fusing features from two CNNs.

The purpose of this study is rangeland biomass estimation and its spatial–temporal dynamics. Remote sensing has been a significant method for estimating biomass in recent years. The connection between vegetation index and field biomass will be used to assign probabilities, but in some cases, it does not provide acceptable results because of soil background and geographical and temporal variability.

In this study, the normalized difference red-edge (NDRE) index was used to calculate the rangeland biomass in comparison to five vegetation indices. Field measurements of biomass of natural rangeland in the West of Iran were taken in 2015, 2018 and 2021, and SENTINEL-2 data were used for analysis.

The results indicated that the overall advantage of NDRE stems from the fact that it adjusts for changes in leaf water content while overcoming the detrimental effects of soil substrate heterogeneity, both of these factors have a significant impact on pasture biomass. These results suggest that an NDRE-based biomass estimation model might be useful for estimating and monitoring biomass in large rangelands with significant geographical and temporal variability.

Identifying the best vegetation index to establish a vegetation-based biomass regression model for rangelands in large areas with different climatic conditions, plant compositions and soil types is the overall aim of this study.

This study aims to provide a review for scour in complex rivers and streams with coarser bed material, steep longitudinal bed slopes and dynamic environments, in the interest of the safety and the economy of hydraulic structures. The knowledge of scour in such geographical complexities is very crucial for a comprehensive understanding of scour failures and for establishing definitive criteria to bridge this major research gap.

The existing available literature shows significant work done in case of silt, sand and small sized coarser bed material but any substantial work for bed material of gravel size or above is lacking, resulting in a wide gap. Though some researchers have attempted to explore possibilities of refining the existing models by adding pier size, shape, sediment non-uniformity and armouring effects, which otherwise have been given a miss by the various researchers, including the pioneer in the field Lacey–Inglis (1930). But still, a rational model for scour estimation in such complex conditions for global use is yet to come. This is because all the parameters governing the scour have not been studied properly till date as is evident from the globally available literature and is witnessed in the field too, in recurrent failure of hydraulic structures especially bridges.

The researchers presume that the finer materials move only as a result of erosion. However, in actual field conditions, it has been observed that the large-sized stones also roll down and cause huge erosion along the river bed and damage the hydraulic structures, especially in the steep river/stream beds along hilly slopes. This fact has been overlooked in the models available globally and has been highlighted only in the current work in an attempt to recognize this major research gap. A study carried out on a number of streams globally and in Jammu and Kashmir, India also, has shown that in steep river and stream beds with bed material consisting of gravel size or greater than gravel, large scour holes ranging from 1 m to 5 m were created by furious floods, and due to other unknown forces along the channel path and near foundations of hydraulic structures.

To the best of the authors’ knowledge, this work is purely original.

The digitalization of archival management has rapidly developed with the maturation of digital technology. With data's exponential growth, archival resources have transitioned from single modalities, such as text, images, audio and video, to integrated multimodal forms. This paper identifies key trends, gaps and areas of focus in the field. Furthermore, it proposes a theoretical organizational framework based on deep learning to address the challenges of managing archives in the era of big data.

Via a comprehensive systematic literature review, the authors investigate the field of multimodal archive resource organization and the application of deep learning techniques in archive organization. A systematic search and filtering process is conducted to identify relevant articles, which are then summarized, discussed and analyzed to provide a comprehensive understanding of existing literature.

The authors' findings reveal that most research on multimodal archive resources predominantly focuses on aspects related to storage, management and retrieval. Furthermore, the utilization of deep learning techniques in image archive retrieval is increasing, highlighting their potential for enhancing image archive organization practices; however, practical research and implementation remain scarce. The review also underscores gaps in the literature, emphasizing the need for more practical case studies and the application of theoretical concepts in real-world scenarios. In response to these insights, the authors' study proposes an innovative deep learning-based organizational framework. This proposed framework is designed to navigate the complexities inherent in managing multimodal archive resources, representing a significant stride toward more efficient and effective archival practices.

This study comprehensively reviews the existing literature on multimodal archive resources organization. Additionally, a theoretical organizational framework based on deep learning is proposed, offering a novel perspective and solution for further advancements in the field. These insights contribute theoretically and practically, providing valuable knowledge for researchers, practitioners and archivists involved in organizing multimodal archive resources.

Heavy rainfall is one of the main causes of the degradation of historic rammed Earth architecture. For this reason, ensuring the conservation thereof entails understanding the factors involved in these risk situations. The purpose of this study is to research three past events in which rainfall caused damage and collapse to historic rammed Earth fortifications in Andalusia in order to analyse whether it is possible to prevent similar situations from occurring in the future.

The three case studies analysed are located in the south of Spain and occurred between 2017 and 2021. The hazard presented by rainfall within this context has been obtained from Art-Risk 3.0 (Registration No. 201999906530090). The vulnerability of the structures has been assessed with the Art-Risk 1 model. To characterise the strength, duration, and intensity of precipitation events, a workflow for the statistical use of GPM and GSMaP satellite resources has been designed, validated, and tested. The strength of the winds has been evaluated from data from ground-based weather stations.

GSMaP precipitation data is very similar to data from ground-based weather stations. Regarding the three risk events analysed, although they occurred in areas with a torrential rainfall hazard, the damage was caused by non-intense rainfall that did not exceed 5 mm/hour. The continuation of the rainfall for several days and the poor state of conservation of the walls seem to be the factors that triggered the collapses that fundamentally affected the restoration mortars.

A workflow applied to vulnerability and hazard analysis is presented, which validates the large-scale use of satellite images for past and present monitoring of heritage structure risk situations due to rain.

The primary objective of this study is to examine how students' technological factors affect remote access (RA) in smart learning (SL) environments. Additionally, the paper explores the moderating effect of students' technical skills (TS) on RA and SL.

The study applied a quantitative research approach and collected 125 valid questionnaires from students in Oman's higher education institutions (HEIs). A structural equation model (SEM) was employed for data analysis using the Smart PLS 4 version to examine the influence of technological factors on RA in SL environments.

It was found that the use of cloud-based RA in SL is influenced by students' use of technology, technology competitiveness and the availability of institutional software (IS). Moreover, students' TS were found to play a crucial role in moderating RA and SL, as well as technical knowledge (TK) and SL. These findings highlight the importance of technical competencies and software availability in shaping students' RA experiences.

The study's findings should be interpreted with caution due to the limited sample size, which may restrict the generalizability of the results.

The study suggests the technological learning capabilities of HEIs, which significantly improved by prioritizing critical technical factors, including knowledge and use of technology, availability of institutional software and RA antecedents in SL environments.

This paper offers practical and actionable directions for HEIs, universities, colleges and educators looking to incorporate technology into their practices in the dynamic and ever-evolving Fourth Industrial Era.

This paper is a literature review on use of artificial intelligence (AI) among agricultural value chain (AVC) actors, and it brings out gaps in research in this area and provides directions for future research.

The authors systematically collected literature from several databases covering 25 years (1994–2020). They classified literature based on AVC actors present in different stages of AVC. The literature was analysed using Nvivo 12 (qualitative software) for descriptive and content analysis.

Fifty percent of the reviewed studies were empirical, and 35% were conceptual. The review showed that AI adoption in AVC could increase agriculture income, enhance competitiveness and reduce cost. Among the AVC stages, AI research related to agricultural processing and consumer sector was very low compared to input, production and quality testing. Most AVC actors widely used deep learning algorithm of artificial neural networks in various aspects such as water resource management, yield prediction, price/demand forecasting, energy efficiency, optimalization of fertilizer/pesticide usage, crop planning, personalized advisement and predicting consumer behaviour.

The authors have considered only AI in the AVC, AI use in any other sector and not related to value chain actors were not included in the study.

Earlier studies focussed on AI use in specific areas and actors in the AVC such as inputs, farming, processing, distribution and so on. There were no studies focussed on the entire AVC and the use of AI. This review has filled that literature gap.

Globally, urban planners and decision makers are pursuing place-based initiatives to develop and enhance urban infrastructure to optimise city performance, competitiveness and sustainability credentials. New discourses associated with big data, Building Information Modelling, SMART cities, green and biophilic thinking inform research, policy and practice agendas to varying extents. However, these discourses remain relatively isolated as much city planning is still pursued within traditional sectoral silos hindering integration. This research explores new conceptual ground at the Smart – Natural City interface within a safe interdisciplinary opportunity space. Using the city of Birmingham UK as a case study, a methodology was developed championing co-design, integration and social learning to develop a conceptual framework to navigate the challenges and opportunities at the Smart-Natural city interface. An innovation workshop and supplementary interviews drew upon the insights and experiences of 25 experts leading to the identification of five key spaces for the conceptualisation and delivery at the Smart-Natural city interface. At the core is the space for connectivity; surrounded by spaces for visioning, place-making, citizen-led participatorylearning and monitoring.The framework provides a starting point for improved discussions, understandings and negotiations to cover all components of this particular interface. Our results show the importance of using all spaces within shared narratives; moving towards ‘silver-green’ and living infrastructure and developing data in response to identified priorities. Whilst the need for vision has dominated traditional urban planning discourses we have identified the need for improved connectivity as a prerequisite. The use of all 5 characteristics collectively takes forward the literature on socio-ecological-technological relationships and heralds significant potential to inform and improve city governance frameworks, including the benefits of a transferable deliberative and co-design method that generates ownership with a real stake in the outcomes.