Field Data Processing Research Articles

Quadratic Unet for seismic random noise attenuation

In the field of seismic data processing, seismic denoising is essential to improve the quality of seismic data. Various deep learning methods have been proposed, showing promising performance for seismic denoising. However, most deep learning methods are based on lin ear neurons, resulting in limited expressive ability for complex seismic signals. To enhance denoising capability using non-linear neurons, we propose a supervised quadratic U-shaped network (QUnet) for seismic random noise attenuation. The quadratic neurons in QUnet are represented by a second-order polynomial of input data and weighted parameters. Nu merical synthetic seismic data experiments show that the proposed QUnet method achieves higher signal-to-noise ratio results and preserves the continuity of reflectors more effectively. We have also tested the effectiveness of QUnet on both prestack field data and post-stack seismic data. The detailed structures and weak signals of seismic data are better preserved by our proposed QUnet method.

The Identification of Faults using Magnetic Method in Kulonprogo, Yogyakarta, Indonesia

The aims of this study to identify faults and identify subsurface lithology using magnetic anomaly data in the Kulonprogo. In the acquisition was carried out using a Proton Procession Magnetometer (PPM) Geotron G5 with 62 measurement points and a distance of ±1 km between point. Measurements were made on Kebobutak (Tmok), Aluvium (Qa), Andesit (a), and Sentolo (Tmps) formations. The total magnetic field data processing is done with several correction, namely diurnal correction, IGRF, reduce to equator, upward continuation at an altitude of 2000 m, and reduce to pole, and 2D modelling using the forward modelling method. The result of the analysis obtained magnetic field anomaly values in the range of values -400 to 950 nT. The 2D modelling shows that the research area is composed of 4 dominating rock types, namely andesite rock with a susceptibility value of 94 x 10-3, andesite breccia rock with a susceptibility value of 29 x 10-3, clay rock with a susceptibility value of 0,013 x 10-3, and sandstone with a susceptibility value of 5 x 10-3. The identification result show the existence of faults line on Mount Watuaglik, Mount Kamal, and Mount Bodag.

High-Precision Monitoring during the Installation of Large Steel Structures by UAV Nap-of-the-Object Photogrammetry

Abstract. This paper proposes and validates a method based on UAV nap-of-the-object photogrammetry for refined 3D digital modeling to achieve high-precision monitoring during the installation of large steel structures, offering a comparative analysis with traditional oblique photogrammetry methods. Through field tests and data processing on the steel structure of a sports stadium in Zhejiang Province, the results demonstrate that nap-of-the-object photogrammetry can capture high-resolution images, offering significant advantages in detail representation and modeling of complex structures. Experimental data reveal that the model's root mean square error (RMSE) generated by nap-of-the-object photogrammetry is 14.56mm, markedly lower than the 51.99mm achieved by traditional methods, meeting the Level II accuracy standard specified in the "Technical Specifications for Nap-of-the-Object Photogrammetry." The study further shows that, when combined with optimized flight path planning, nap-of-the-object photogrammetry enhances both the efficiency and accuracy of data collection while improving operational safety. This technique is highly applicable and flexible, making it suitable for data acquisition of complex structures and high-rise buildings. In summary, the proposed method exhibits significant advantages in terms of accuracy, efficiency, safety, and applicability, providing a practical solution for high-precision, comprehensive digital modeling of large steel structures.

Distance-regularized level set inversion of magnetic data

Inversion is one of the key and difficult issues in potential field data processing and interpretation, and high-precision inversion has long been a popular research topic. We develop the distance-regularized level set inversion of the magnetic data (DRLSI-M) method. A double-well function is introduced into the objective function of the level set inversion, and we take advantage of its mathematical properties to minimize the gradient of the level set function so that it reaches a minimum value at points 0 and 1. As a result, the distance-regularized term not only replaces the costly reinitialization process so that the level set function maintains a signed distance property but also stabilizes the evolution of the level set function. When solving for the minimum value of the objective function, we transform the optimization problem into an initial-boundary value problem and solve it with the finite-difference method. The distance-regularized level set inversion method and the reinitialization level set inversion method are tested using three models: a single-level-set double-inclined plate model, a double-level-set double-inclined plate model, and a multiple-level-set three-cuboid model. Through model tests, the soundness of our method is verified and compared with the reinitialization level set inversion method. Our method avoids the limitations such as low efficiency and instability caused by the reinitialization of the level set inversion method. Furthermore, we apply our method for the inversion of aeromagnetic data from the Jinchuan copper-nickel mine. The results are consistent with the known geologic information, thus validating the practicality and effectiveness of DRLSI-M. The distance-regularized level set inversion method provides a theoretical basis for deep mine exploration.

Assessing Large Language Models Used for Extracting Table Information from Annual Financial Reports

The extraction of data from tables in PDF documents has been a longstanding challenge in the field of data processing and analysis. While traditional methods have been explored in depth, the rise of Large Language Models (LLMs) offers new possibilities. This article addresses the knowledge gaps regarding LLMs, specifically ChatGPT-4 and BARD, for extracting and interpreting data from financial tables in PDF format. This research is motivated by the real-world need to efficiently gather and analyze corporate financial information. The hypothesis is that LLMs—in this case, ChatGPT-4 and BARD—can accurately extract key financial data, such as balance sheets and income statements. The methodology involves selecting representative pages from 46 annual reports of large Swiss corporations listed in the SMI Expanded Index from 2022 and copy–pasting text from these into LLMs. Eight analytical questions were posed to the LLMs, and their responses were assessed for accuracy and for identifying potential error sources in data extraction. The findings revealed significant variance in the performance of ChatGPT-4 and another LLM, BARD, with ChatGPT-4 generally exhibiting superior accuracy. This research contributes to understanding the capabilities and limitations of LLMs in processing and interpreting complex financial data from corporate documents.

One‐dimensional deep learning inversion of marine controlled‐source electromagnetic data

AbstractThis paper explores the application of machine learning techniques, specifically deep learning, to the inverse problem of marine controlled‐source electromagnetic data. A novel approach is proposed that combines the convolutional neural network and recurrent neural network architectures to reconstruct layered electrical resistivity variation beneath the seafloor from marine controlled‐source electromagnetic data. The approach leverages the strengths of both convolutional neural network and recurrent neural network, where convolutional neural network is used for recognizing and classifying features in the data, and recurrent neural network is used to capture the contextual information in the sequential data. We have built a large synthetic dataset based on one‐dimensional forward modelling of a large number of resistivity models with different levels of electromagnetic structural complexity. The combined learning of convolutional neural network and recurrent neural network is used to construct the mapping relationship between the marine controlled‐source electromagnetic data and the resistivity model. The trained network is then used to predict the distribution of resistivity in the model by feeding it with marine controlled‐source electromagnetic responses. The accuracy of the proposed approach is examined using several synthetic scenarios and applied to a field dataset. We explore the sensitivity of deep learning inversion to different electromagnetic responses produced by resistive targets distributed at different depths and with varying levels of noise. Results from both numerical simulations and field data processing consistently demonstrate that deep learning inversions reliably reconstruct the subsurface resistivity structures. Moreover, the proposed method significantly improves the efficiency of electromagnetic inversion and offers significant performance advantages over traditional electromagnetic inversion methods.

MSAACNN for intense noise suppression in DAS-VSP records

Distributed optical fiber sensor (DAS) is an emerging acquisition technique and has begun to be widely applied in seismic exploration owing to its advantages in acquisition and deployment. Nonetheless, DAS record has a low signal-to-noise ratio (SNR) due to the intense background noise. How to suppress the DAS background noise and increase the SNR of the DAS records has gradually become one of the hot issues in the field of seismic data processing. To solve the challenging tasks in intense DAS noise suppression, a multiscale sparse asymmetric attention convolutional neural network (MSAACNN) is proposed. The network uses dilated convolutions to expand the receptive field and map more feature information. Moreover, asymmetric convolutions are introduced to form an asymmetric unit, aiming to strengthen the feature extraction ability and realize the interaction between feature information of different scales. Finally, a pyramid attention module is used to enhance the primary features and improve the network denoising performance. The experimental results show that MSAACNN can effectively suppress the complex background noise in DAS records, compared with the traditional denoising methods and typical convolutional neural network (CNN) architecture. Additionally, the recovered signal components in the processing results are clear and complete, with significantly improved SNR.

SGIR-Tree: Integrating R-Tree Spatial Indexing as Subgraphs in Graph Database Management Systems

Efficient spatial query processing in Graph Database Management Systems (GDBMSs) has become increasingly important owing to the prevalence of spatial graph data. However, current GDBMSs lack effective spatial indexing, causing performance issues with complex spatial graph queries. This study proposes a spatial index called Subgraph Integrated R-Tree (SGIR-Tree) for efficient spatial query processing in GDBMSs. The SGIR-Tree integrates the hierarchical R-Tree structure with the graph structure of GDBMSs by converting R-Tree elements into graph components like nodes and edges. The Minimum Bounding Rectangle (MBR) information of spatial objects and R-Tree nodes is stored as properties of these graph elements, and the leaf nodes are directly connected to the spatial nodes. This approach combines the efficiency of spatial indexing with the flexibility of graph databases, thereby allowing spatial query results to be directly utilized in graph traversal. Experiments using OpenStreetMap datasets demonstrate that the SGIR-Tree outperforms the previous approaches in terms of query overhead and index overhead. The results are expected to improve spatial graph data processing in various fields, including location-based service and urban planning, significantly advancing spatial data management in GDBMSs.

An open-source, QGIS-based solution for digital geological mapping: GEOL-QMAPS

Digital geological mapping has experienced significant growth over the past three decades due to the advent of commercial geographical information systems, advances in global positioning systems, and the availability of portable hand-held devices, such as mobile personal computers (PCs), smartphones, and tablets. Numerous software packages have been developed to collect, combine, organise, visualise, publish, and share field data with enhanced spatial accuracy and minimal post-field processing. However, many of these tools are not open-source or are not made available to the geoscientific community, remaining specific to given mapping projects or organisations.In this contribution we introduce GEOL-QMAPS, an open-source, QGIS-based solution promoting digital geological mapping in a harmonised, comprehensive and flexible way. It can be used in the field with a tablet PC or via the QGIS-based QField app on iOS or Android mobile devices, enabling synchronisation with desktop QGIS and the creation of field databases. Designed as a general solution, the GEOL-QMAPS solution consists of a QGIS field data entry template and a custom QGIS plugin, both available on free-access online repositories. The plugin allows for the adaptation of dictionaries (i.e., lists of attributes describing geological features), initially set to international nomenclatures, to the guidelines of different mapping projects. The solution also facilitates the loading and consultation of relevant legacy geodatasets (e.g., preexisting field data, geochemical, geophysical maps or punctual datasets). A fact map, created from field data collected across the Archean Sula-Kangari greenstone belt in Sierra Leone, demonstrates the solution's advantages in terms of post-field processing and raw field data sharing.

Research on prediction of yellow flesh peach firmness using a novel acoustic real-time detection device and Vis/NIR technology

Firmness is a critical indicator for predicting fruit ripeness, optimal harvest date, and shelf life. In this study, a novel fruit acoustic real-time detection prototype device and a conventional visible near-infrared (Vis/NIR) spectroscopy real-time detection device were used to collect acoustic and spectral signals from yellow flesh peaches to jointly predict their firmness. The acoustic and optical signals were generated into one- and two-dimensional feature data by complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), continuous wavelet transform (CWT) and Gramian angular field (GAF) data processing methods. Based on these data, a variety of yellow flesh peach firmness prediction models were constructed in this study, including partial least square (PLS), support vector regression (SVR), Swin Transformer (SwinT), and SwinT-PLS/SVR. The experimental results showed that the SwinT-PLS model based on the fusion of competitive adaptive re-weighted sampling (CARS)-acoustic image features and CARS-Vis/NIR spectral features showed the best prediction performance (R2P = 0.951, the RMSEP = 0.443 N/mm, RPDP = 4.339), and the prediction performance is significantly higher than that of the prediction model based on single acoustic and Vis/NIR spectral data. The method proposed can fast, non-destructively, accurately predict fruit firmness and has excellent prospects for commercial real-time fruit sorting applications.

Three-Dimensional Subsurface Pipe Network Survey and Target Identification Using Ground-Penetrating Radar: A Case Study at Jilin Jianzhu University Campus

This study focuses on the application of ground-penetrating radar (GPR) in conducting field surveys and data processing at the northern campus of Jilin Jianzhu University. The research site’s geographical location and overall conditions are described. A detailed layout of the survey lines for 3D surveys is presented. The collected data undergo basic processing and interpretation, identifying multiple target bodies and their associated electromagnetic responses. Advanced analyses such as 3D imaging, common attribute analysis, and time-varying centroid frequency attribute analysis are employed to investigate underground features and potential pipe networks. The case study in this research demonstrates that the integration of 3D GPR surveys and time-varying centroid frequency analysis can effectively assess the attenuation characteristics of subsurface media and structures, thereby enhancing the overall prospecting and data interpretation capabilities of GPR.

Optimized design of hardware accelerator based on machine learning

Hardware accelerators are playing an increasingly important role in the field of computer science and engineering, especially in accelerating deep learning and large-scale data processing. However, the traditional hardware accelerator design often relies on manual adjustment and experience accumulation, which is inefficient. Therefore, the use of machine learning technology to optimize hardware accelerator design has become a new trend. In this paper, a hardware accelerator optimization design method based on machine learning is proposed, including hardware design, algorithm optimization, system-level optimization, and deep learning model compression. Through the research and verification of the actual case, this research proves the effectiveness and feasibility of the hardware accelerator optimization design method based on machine learning. Compared with the traditional design method, this method can find better design scheme in shorter time and has higher performance prediction accuracy. Therefore, this method can significantly improve the design efficiency and performance of hardware accelerators. The results of this study are of great significance for promoting the development of hardware accelerator technology. It can promote scientific research and engineering applications in related fields to make greater progress, and promote the development of artificial intelligence, big data processing and other fields.

Exploring how social housing residents interact with building openings in a hot-humid climate

In a hot-humid climate, natural ventilation is the most recommended strategy for obtaining thermal comfort indoors. The residents' behavior in opening windows and doors to promote natural ventilation is crucial for predicting thermal comfort, especially for low-income housing where energy costs can exceed household budgets. This study identifies residents’ behavior in social housing in northeast Brazil (a hot-humid climate), focusing on actions to regulate thermal comfort with natural ventilation. The methodology comprehends field research, surveys, data processing, and analysis. Interviews with 375 individuals across two social housing complexes reveal the significant role of security and cultural factors in window control behavior. The results highlight the considerable role of security and cultural factors in shaping occupant behavior concerning window control. The residents indicated that they are stimulated to open the windows and doors right after they wake up and close them at bedtime or when leaving the house. Occupancy is a significant driving factor, but the sleep period (unconscious state) plays a crucial role in determining the closure of openings, even to housing units with a 2.0 m high wall on the plot land limits and security bars on windows. This study contributes to the understanding of the complex interplay between security, cultural factors, and thermal comfort regulation, proposing valuable insights for design and policy interventions aimed at improving living conditions in similar contexts.

Active few-shot learning for rare bioacoustic feature annotation

The collection and annotation of bioacoustic data present several challenges to researchers. Bioacoustic monitoring of rare (sparse) or cryptic species generally encounter two main issues. The cost of collecting and processing field data and a lack of labelled datasets for the target species. The detection of invasive species incursions and probability of absence testing is especially challenging due to these species having population densities at or close to zero. We present a methodology specifically designed to aid in the analysis of rare acoustic events within long-term field recordings. This approach combines a wavelet-based segmentation method that automatically extracts transient features from within-field recordings. A few-shot active learning recommender system in a human-in-the-loop process prioritises the annotation of low-certainty samples. This process combines the accuracy of human classification and the speed of computational tools to greatly reduce the presence of non-target features in field recordings. We evaluate this approach using an invasive species identification case study. This methodology achieves a test accuracy of 98.4% as well as 81.2% test accuracy using 2-shot, 2-way prototypical learning without fine-tuning, demonstrating high performance at varying data availability contexts. Active learning using low-certainty samples achieves >90% test accuracy using only 20 training samples compared to 80 samples without active learning. This approach allows users to train custom audio classification models for any application with rare features. The model can be easily exported for use in the field making real-time bioacoustic monitoring of less-vocal species a possibility. All code and data are available at https://github.com/Listening-Lab/Annotator.

Benthic habitat mapping for estimating seagrass carbon stock across Takabonerate Islands, Indonesia

Data on benthic habitat cover are essential for monitoring and managing coastal areas, providing valuable ecosystem services for local communities. Moreover, seagrass extent is crucial for estimating carbon stock using Tier-1 calculations. On the other side, remote sensing technology has proven effective in mapping benthic habitat cover, including seagrass, over large local areas. Therefore, this research aims to map specific benthic habitats in a local area to obtain high-accuracy estimates of seagrass extent for carbon stock estimation. The study was conducted in the Takabonerate Islands, Indonesia, using Sentinel-2A imagery. The study involved field data processing, which enabled the mapping of eight benthic habitat classes using Sentinel-2A images, along with the steps for Sentinel-2A image processing for benthic habitat mapping. The benthic habitat map was produced following image correction steps, including atmospheric, sunglint, and water column corrections, followed by image classification using a Neural Net Classifier (NNC). Seagrass carbon stock estimation was performed using the Tier-1 equation from IPCC 2013. The study revealed a total benthic habitat area of 57,538.04 ha, with a seagrass area of 3127.42 ha for carbon stock estimation. The potential seagrass carbon stock in the study area was estimated to range from 337.76 GgC/ha to 31.27 GgC/ha using the Tier-1 equation. The overall accuracy of the benthic habitat map was 80.5 %, calculated using a confusion matrix table. The spatial information from this study can be used by local coastal managers and governments for baseline and monitoring purposes. The key interpretations from this study provide valuable findings that can be adapted and improved for future local mapping purposes.

Analisis Produktivitas Alat Gali Muat dan Alat Angkut Pada Pengupasan Lapisan Tanah Penutup (Overburden) Di Pt. Cahaya Riau Mandiri Kabupaten Lahat Provinsi Sumatera Selatan

PT Cahaya Riau Mandiri is a company engaged in coal mining that operates in Lahat Regency, South Sumatra Province with an open pit mining system. PT Cahaya Riau Mandiri has a production target of 70,000 tons/month in one shift. The purpose of this study is to determine the actual production of excavating and hauling equipment and the compatibility factor in coal mining, knowing the obstacles to effective working time in overcoming work obstacles that can be avoided so that loss time can be reduced and the resulting production can be achieved according to the company's target. The research method used in this research is quantitative and the stages in the preparation of this writing start from literature study, field observation, field data collection, data processing, data analysis, discussion and conclusions and suggestions. Based on the research and calculations that have been carried out, it is obtained that the actual production of the Liugong CLG952E excavator digging and loading equipment is 46. 522, 30 tons / month and the Iveco 682 dump truck conveyance is 44. 525, 25 tons / month with a compatibility factor of 0, 56. The strategy that can be done in increasing production is to improve work barriers, filling factors, tool compatibility and circulation time by using the basic work reference from the company. After improving the work of the Liugong CLG952E excavator and Iveco 682 dump truck transport equipment, the production of the Liugong CLG952E excavator increased from 46. 522, 30 tons / month to 70. 068, 54 tons / month and the Iveco 682 dump truck transport equipment increased from 44. 525, 25 tons / month to 70. 048, 21 tons/month.

Enhancing Geographic Information System Skills through Boundary Mapping Training at Pesantren Rahmatullah, Lempake, Samarinda

This program designed to enhance the skills and knowledge of students and teaching staff at Pesantren Rahmatullah (Islamic boarding school) regarding the use of Geographic Information System (GIS) technology in boundary mapping. The initiative was launched recognizing the importance of understanding territorial boundaries in the context of natural resource management, development planning, and disaster mitigation in the surrounding areas. The training includes a series of theoretical sessions and field practices. The first stage involves learning how to gather coordinate points in the field using the Garmin 60 CSX GPS device. The second stage focuses on field data processing and coordinate data correction, covering basic GIS knowledge, introduction to GIS software, and usage of Autodesk Map software and Arc GIS 10.8. The third stage is the scaled printing of processed field data. The duration of the training is one semester, following the curriculum set by the Rahmatullah Islamic boarding school. This training aims to equip participants with the necessary skills to produce accurate and informative boundary maps, which will later serve as tools for decision-making and strategic planning at Rahmatullah Lempake Islamic boarding school in Samarinda. Additionally, this activity also aims to enhance the boarding school’s awareness and capacity in utilizing geographic information technology for educational and environmental management purposes.

Comparative Analysis of CMOS-based D-type Flip-Flop Architectures for High-Performance VLSI Applications Using 45-nm CMOS Technology

High performance VLSI (very large-scale integration) is an essential electronic technology required for space missions and scientific advancements. The only source of reliance for the VLSI designer is the data storage devices designated as flip-flops, which are widely used in semiconductor memory devices as well as for data processing and storage in the telecommunication fields. In this paper, the four D-type flip-flop architectures of CMOS-based D-type flip-flops, such as D-type flip-flops using traditional technology (DFF-T), D-type flip-flops with Demorgan’s law (DFF-DL), D-type flip-flops with transmission gates (DFF-TG), and D-type flip-flops with five transistors (DFF-F), have been designed and constructed. The analytical simulations of the schematics and equivalent layouts of these four architectures are implemented using 45-nm complementary metal-oxide-semiconductor (CMOS) technology. With cadence virtuoso design software, the performance investigation of the four D-type flip-flop architectures is compared in terms of layout area, transistor counts, average power consumption, rise time, fall time, and propagation delay. The DFF-F technologies have modestly compact design goals in order to reduce production costs and achieve faster processing speeds with fewer transistors.

Influence of strong directional sources in ambient seismic imaging using traffic-induced noise

Continuously moving seismic sources, such as vehicles and train cars, play a crucial role as passive sources for nondestructive exploration in urban areas. Seismic interferometry is commonly used in field data acquisition and processing using linear arrays. However, the simultaneous recording of high-energy noise, excited by buildings and factories, cannot be overlooked. We simulate moving-source seismic records with strong noises using orthogonal arrays. When strong noise originates from specific angles, the energy-phase velocity curves of arrays in different directions significantly diverge. We determine that an L-shaped array, formed by orthogonal arrays, can effectively mitigate this effect, yielding more consistent results. Nonetheless, spatial constraints often preclude the deployment of L-shaped arrays. To mitigate this issue, we develop a new parallel observation system. Field tests conducted on a main road validate that the new array is comparable with the L-shaped array in terms of dispersion extraction. Similar to synthetic data, the phase velocity extracted from the linear array field data is found to be unreliable. Drilling data align well with the inversion results of the parallel observation system. Given the challenges of urban traffic-induced signal acquisition, deploying multiazimuth arrays to minimize noise impact is essential. Considering the spatial limitations, the convenient parallel observation system emerges as a good choice.

CONCEPTUAL FOUNDATIONS FOR THE FORMATION OF PERSONNEL STRATEGY AT INDUSTRIAL ENTERPRISES IN THE CONTEXT OF DIGITALISATION

The relevance of research on the conceptual foundations of personnel strategy formation in industrial enterprises under the conditions of digitalisation appears to be very relevant, which is due to the following factors. The digital transformation of industrial enterprises leads to the emergence of new technologies, processes and personnel requirements. The HR strategy must adapt to these changes in order to ensure that the company has the necessary qualifications and skills. Under the conditions of digitalisation, the demand for specialists in the field of information technologies and digital data processing is increasing. Companies need to develop strategies to attract, retain and develop such personnel in order to remain competitive. Digital technologies make it possible to automate and optimise business processes, so the HR strategy must reflect these changes and take into account the new roles and requirements for personnel. As technologies and processes change, there is a need for continuous training and development of personnel. The HR strategy should include training and development programmes aimed at increasing digital skills. Studying the conceptual foundations of personnel strategy development in the conditions of digitalisation will help companies to effectively adapt to contemporary challenges and ensure their competitiveness. The purpose of the article is to disclose the conceptual foundations of forming a personnel strategy at industrial enterprises in the context of digitalisation. The methodology of the study is an interdisciplinary approach based on the idea of effective development of an industrial enterprise as a sociotechnological system, which allowed to combine systemic knowledge that will help to understand how social factors affect the implementation of technologies and the development of the enterprise as a whole. The enterprise as a complex social and technological system should be analysed within the framework of the socio-humanistic approach, which is based on the recognition of the human being as the subject and object of all processes. In the context of a socio-humanistic approach to business analysis, it is important to address aspects related to social relations, human needs and values, and the interaction between employees and management. The fundamental principles of the socio-humanistic approach, such as taking into account the individual needs of employees, supporting their development and satisfaction from professional activities, can be applied to the analysis of an enterprise's performance. This means that the efficiency and success of an organisation is assessed not only by financial indicators, but also by the level of satisfaction and development of its employees. Studying the social interactions, communication and psychological climate of the team can help to understand what factors contribute to or hinder the effective functioning of the organisation. This approach allows to see the company as a living, organic system in which human relationships and values play an essential role. The study opens up the possibility of integrating different scientific disciplines, such as sociology, technology, economics, psychology and management, in order to understand the complex relationships in today's industrial companies. The implementation of the recommendations will help companies improve the efficiency of personnel management, provide the necessary human resources and meet the requirements of the modern market. The research generates new knowledge in the field of personnel management and digitalisation, has direct practical application for companies in increasing their competitiveness and stability in the market.