Quality Of Maps Research Articles

Spatial Sequential Matching Enhanced Underwater Single-Photon Lidar Imaging Algorithm

Traditional LiDAR and air-medium-based single-photon LiDAR struggle to perform effectively in high-scattering environments. The laser beams are subject to severe medium absorption and multiple scattering phenomena in such conditions, greatly limiting the maximum operational range and imaging quality of the system. The high sensitivity and high temporal resolution of single-photon LiDAR enable high-resolution depth information acquisition under limited illumination power, making it highly suitable for operation in environments with extremely poor visibility. In this study, we focus on the data distribution characteristics of active single-photon LiDAR operating underwater, without relying on time-consuming deep learning frameworks. By leveraging the differences in time-domain distribution between noise and echo signals, as well as the hidden spatial information among echo signals from different pixels, we rapidly obtain imaging results across various distances and attenuation coefficients. We have experimentally verified that the proposed spatial sequential matching enhanced (SSME) algorithm can effectively enhance the reconstruction quality of reflection intensity maps and depth maps in strong scattering underwater environments. Through additional experiments, we demonstrated the algorithm’s reconstruction effect on different geometric shapes and the system’s resolution at different distances. This rapidly implementable reconstruction algorithm provides a convenient way for researchers to preview data during underwater single-photon LiDAR studies.

A Novel Self-Supervised Learning-Based Method for Dynamic CT Brain Perfusion Imaging.

Dynamic computed tomography (CT)-based brain perfusion imaging is a non-invasive technique that can provide quantitative measurements of cerebral blood flow (CBF), cerebral blood volume (CBV), and mean transit time (MTT). However, due to high radiation dose, dynamic CT scan with a low tube voltage and current protocol is commonly used. Because of this reason, the increased noise degrades the quality and reliability of perfusion maps. In this study, we aim to propose and investigate the feasibility of utilizing a convolutional neural network and a bi-directional long short-term memory model with an attention mechanism to self-supervisedly yield the impulse residue function (IRF) from dynamic CT images. Then, the predicted IRF can be used to compute the perfusion parameters. We evaluated the performance of the proposed method using both simulated and real brain perfusion data and compared the results with those obtained from two existing methods: singular value decomposition and tensor total-variation. The simulation results showed that the overall performance of parameter estimation obtained from the proposed method was superior to that obtained from the other two methods. The experimental results showed that the perfusion maps calculated from the three studied methods were visually similar, but small and significant differences in perfusion parameters between the proposed method and the other two methods were found. We also observed that there were several low-CBF and low-CBV lesions (i.e., suspected infarct core) found by all comparing methods, but only the proposed method revealed longer MTT. The proposed method has the potential to self-supervisedly yield reliable perfusion maps from dynamic CT images.

Non-target feature filtering for weakly supervised semantic segmentation

Weakly supervised semantic segmentation (WSSS) utilizes weak labels to learn semantic segmentation models, significantly reducing reliance on pixel-level annotations. WSSS typically employs a multi-label classification network to extract image features for constructing localization maps. The quality of the localization map critically influences the performance of WSSS. However, non-target semantic noise within the features impedes the improvement of localization map quality. To address this issue, we propose a non-target feature filtering class activation mapping (NFF-CAM) for WSSS, which can reduce non-target semantic signals and generate higher-quality localization maps. Specifically, the class-constrained dual cosine clustering (CDCC) and channel identification (CI) modules are introduced in NFF-CAM. CDCC effectively addresses the issue of unsuitability in the clustering group relationships of the original features under specified class conditions. CI can efficiently identify channel features containing non-target semantic information. We conduct extensive evaluations of NFF-CAM on popular datasets, including PASCAL VOC 2012 and MS COCO 2014. Experimental results show that NFF-CAM can effectively improve the segmentation performance of off-the-shelf methods.

Analytical Performance of a Novel Nanopore Sequencing for SARS-CoV-2 Genomic Surveillance.

The genomic analysis of SARS-CoV-2 has served as a crucial tool for generating invaluable data that fulfils both epidemiological and clinical necessities. Long-read sequencing technology (e.g., ONT) has been widely used, providing a real-time and faster response when necessitated. A novel nanopore-based long-read sequencing platform named QNome nanopore has been successfully used for bacterial genome sequencing and assembly; however, its performance in the SARS-CoV-2 genomic surveillance is still lacking. Synthetic SARS-CoV-2 controls and 120 nasopharyngeal swab (NPS) samples that tested positive by real-time polymerase chain reaction were sequenced on both QNome and MGI platforms in parallel. The analytical performance of QNome was compared to the short-read sequencing on MGI. For the synthetic SARS-CoV-2 controls, despite the increased error rates observed in QNome nanopore sequencing reads, accurate consensus-level sequence determination was achieved with an average mapping quality score of approximately 60 (i.e., a mapping accuracy of 99.9999%). For the NPS samples, the average genomic coverage was 89.35% on the QNome nanopore platform compared with 90.39% for MGI. In addition, fewer consensus genomes from QNome were determined to be good by Nextclade compare with MGI (p < 0.05). A total of 9004 mutations were identified using QNome sequencing, with substitutions being the most prevalent, in contrast, 10 997 mutations were detected on MGI (p < 0.05). Furthermore, 23 large deletions (i.e., deletions≥ 10 bp) were identified by QNome while 19/23 were supported by evidence from short-read sequencing. Phylogenetic analysis revealed that the Pango lineage of consensus genomes for SARS-CoV-2 sequenced by QNome concorded 83.04% with MGI. QNome nanopore sequencing, though challenged by read quality and accuracy compared to MGI, is overcoming these issues through bioinformatics and computational advances. The advantage of structure variation (SV) detection capabilities and real-time data analysis renders it a promising alternative nanopore platform for the surveillance of the SARS-CoV-2.

Methods for refining the depth map obtained from depth sensors

Depth maps are essential in applications such as robotics, augmented reality, autonomous vehicles, and medical imaging, providing critical spatial information. However, depth maps from sensors like time-of-flight (ToF) and structured light systems often suffer from low resolution, noise, and missing data. Addressing these challenges, this study presents an innovative method to refine depth maps by integrating high-resolution color images. The proposed approach employs both hard- and soft-decision pixel assignment strategies to adaptively enhance depth map quality. The hard-decision model simplifies edge classification, while the soft-decision model, integrated within a Markov Random Field framework, improves edge consistency and reduces noise. By analyzing discrepancies between edges in depth maps and color images, the method effectively mitigates artifacts such as texturecopying and blurred edges, ensuring better alignment between the datasets. Key innovations include the use of the Canny edge detection operator to identify and categorize edge inconsistencies and anisotropic affinity calculations for precise structural representation. The soft-decision model introduces advanced noise reduction techniques, improving depth map resolution and preserving edge details better than traditional methods. Experimental validation on Middlebury benchmark datasets demonstrates that the proposed method outperforms existing techniques in reducing Mean Absolute Difference values, especially in high-upscaling scenarios. Visual comparisons highlight its ability to suppress artifacts and enhance edge sharpness, confirming its effectiveness across various conditions. This approach holds significant potential for applications requiring high-quality depth maps, including robotics, augmented reality, autonomous systems, and medical imaging. By addressing critical limitations of current methods, the study offers a robust, versatile solution for depth map refinement, with opportunities for real-time optimization in dynamic environments.

Phasing Nanopore genome assembly by integrating heterozygous variations and Hi-C data.

Haplotype-resolved genome assemblies serve as vital resources in various research domains, including genomics, medicine, and pangenomics. Algorithms employing Hi-C data to generate haplotype-resolved assemblies are particularly advantageous due to its ready availability. Existing methods primarily depend on mapping quality to filter out uninformative Hi-C alignments which may be susceptible to sequencing errors. Setting a high mapping quality threshold filters out numerous informative Hi-C alignments, whereas a low mapping quality threshold compromises the accuracy of Hi-C alignments. Maintaining high accuracy while retaining a maximum number of Hi-C alignments can be challenging. In our experiments, heterozygous variations play an important role in filtering uninformative Hi-C alignments. Here, we introduce Diphase, a novel phasing tool that harnesses heterozygous variations to accurately identify the informative Hi-C alignments for phasing and to extend primary/alternate assemblies. Diphase leverages mapping quality and heterozygous variations to filter uninformative Hi-C alignments, thereby enhancing the accuracy of phasing and the detection of switches. To validate its performance, we conducted a comparative analysis of Diphase, FALCON-Phase, and GFAse on various human datasets. The results demonstrate that Diphase achieves a longer phased block N50 and exhibits higher phasing accuracy while maintaining a lower hamming error rate. The source code of Diphase is available at https://github.com/zhangjuncsu/Diphase. Supplementary data are available at Bioinformatics online.

Suppression strategy for metal droplet overlapping fusion defects caused by droplet impact dynamics under coaxial shielding gas

High-precision droplet overlapping under coaxial shielding gas is a prerequisite for automated and lightweight metal micro-droplet deposition manufacturing. Unfortunately, the opening shielding environment exposes metal droplets directly to the atmosphere. Droplet overlapping fusion quality would be affected due to the coupling effects of impact dynamics, thermodynamics, and oxidation. In this study, based on experiments and theoretical modeling of molten droplet impact dynamics, a strategy to suppress droplet overlapping fusion defects under coaxial shielding gas was proposed for the first time. Results show that at lower shielding gas rates, molten droplet retraction, recoil, and oscillation would weaken or vanish due to the oxide film's self-limiting effect. This limits the improved model's accuracy in predicting the droplet spreading factor in lower shielding gas supply rates. The weakened droplet dynamic behaviors at low shielding gas supply rates would magnify the length and height defects of droplet overlapping, which is particularly evident at a small printing step distance. Finally, a quality mapping for different printing parameters is established, effectively suppressing overlapping defects and ensuring fusion quality through metallurgical bonding. This work could provide a solid evidence base and theoretical guidance for high-quality metal micro-droplet deposition manufacturing under an opening shielding environment.

Rapid Water Quality Mapping from Imaging Spectroscopy with a Superpixel Approach to Bio-Optical Inversion

Rapid Water Quality Mapping from Imaging Spectroscopy with a Superpixel Approach to Bio-Optical Inversion

Bringing the Veterinary Medicine Curriculum to the Fingertips of Faculty and Students: A Novel Curriculum Search and Analysis Tool.

Curriculum review is a required and essential part of the continuous improvement process to ensure that all elements of the curriculum are integrated to help students achieve intended outcomes. It is also an effective way of avoiding a disparity between the knowledge and skills students gain throughout their education and the knowledge and skills required in practice. One commonly used curriculum analysis approach is curriculum mapping, which requires extensive labor and time commitment. This best practice paper describes the development of a curriculum search and analysis tool that utilizes novel computational analysis techniques from data science and artificial intelligence approaches to enhance the quality of curriculum maps by increasing the effectiveness and efficiency of the curriculum analysis and mapping process.

Evaluation of SDGSAT-1 MII data in total suspended matter estimation in clear to extremely turbid rivers

ABSTRACT The Multispectral Imager (MII) onboard the newly launched SDGSAT-1 holds significant promise for monitoring and understanding variations in water quality within nearshore water systems, with an impressive spatial resolution of 10 m, seven spectral bands in the visible and near-infrared domain and a wide swath of 300 km. This paper evaluates the MII data in estimating the concentration of total suspended matter (TSM) in rivers and estuaries from clear to extremely turbid conditions. For atmospheric correction, the ACOLITE model showed superior performance compared to the FLAASH and 6SV, with average unbiased relative error (AURE) ranging from 11.8% to 26.4% in the four visible bands of MII. Through comparison, a TSM model based on the visible band ratio (i.e., Rrs (660)/Rrs (560)) was proposed to ensure the application of MII data in both clear and turbid waters, with an overall AURE of 40.9%. The model was then applied to map the TSM variations in the Hai and Liao Rivers in northern China using the MII data, where reliable spatial and temporal patterns were observed. The study concludes by discussing the applicability of MII data in water quality mapping in nearshore waters, along with key considerations such as model applicability, atmospheric correction, and land adjacency.

Enhancing sustainability through GIS mapping for groundwater quality analysis

Abstract The current study attempts to develop sustainability by utilizing Geographic Information System (GIS) technology by examining groundwater quality in Rajahmundry by dividing the region into 1 km × 1 km grids, resulting in 45 different areas. The grids are thoroughly dispersed, and groundwater samples have been collected from a variety of sources, including open wells, hand pumps, and bore wells, in each grid in order to assess water quality. The evaluation includes a physico-chemical parameter namely, pH, total alkalinity, TDS, total hardness, calcium hardness, magnesium hardness, chloride, nitrates, and sulphates. The purpose of this study is to create a map of the spatial distribution of these groundwater qualities using GIS in order to obtain a general understanding of the current state of the entire valorisation of groundwater resources. The current approach is novel in that it not only allows detecting the issues affecting water quality but also enables developing specific approaches for the sustainable management and protection of groundwater in Rajahmundry. Overall, through GIS mapping and conclusive water quality assessment, the study provides a significant input into the field of environmental science in terms of enhancing water sustainability practices.

Enhancing fMRI quality control

BackgroundfMRI in clinical settings faces challenges affecting activity maps. Template matching can screen for abnormal results by providing an objective metric of activity map quality. This research tests how sample size, age, or gender-specific templates, and unilateral templates affect template matching results. New MethodWe used an fMRI database of 76 healthy subjects performing 7 tasks assessing motor, language, and working memory functions. Templates were created with varying numbers of subjects, genders, and ages. Individual subjects were compared to templates using leave-one-out cross validation. We also compared unilateral and bilateral templates. ResultsIncreasing sample size improved template matches, with diminishing returns for larger sample sizes. Gender and age-specific templates increased correlations for some tasks, with age having a larger effect than gender. Generally, templates including all subjects provided the highest correlations, indicating that age and gender effects did not outweigh the benefits of larger sample sizes. Unilateral templates of the task-dominant hemisphere increased template correlations. ConclusionsAge and gender affect templates, but the benefits depend on the database size. When the database is large enough, age and gender effects are beneficial. Unilateral templates enhance template matching, but practical benefits depend on the severity of neurological abnormalities in patients.

A-posteriori analysis of the performance of a rockfall susceptibility map

BackgroundRockfalls pose a serious threat along the main road network, representing a major hazard in mountainous territory and causing damage and victims. Currently, susceptibility mapping represents a starting point to identify areas more susceptible to rockfall occurrence, a key approach in land use planning and risk management. Despite the extensive use of these maps by decision makers and administrators, the usability of such maps over time and their reliability represent a poorly discussed and examined feature.MethodsHere, we proposed a-posteriori analysis of a three-year-old rockfall susceptibility map, generated along the main road network of the Aosta Valley, an alpine region of north-western Italy. To verify map consistency over time, we implemented a dual-analysis in GIS-environment and by text mining, to respectively analyse the geocoded data and textual information derivable from the regional landslide inventory. The first one allowed us to extract rockfall events occurred after the susceptibility map generation. By this way, we operated to spatially and temporally verify the map consistency. Jointly, the textual information reported in the Event Description Form, linked to each geocoded event, are being exploited. This allowed us to derive relevant information about occurred damage and their degree, presence of protective measures or secondary roads, i.e. involvement of, farm or forestry, road.ResultsThe implemented approach allowed us to prove the quality of the previous map in terms of reliability, robustness and degree of fitting respect to the succession of rockfall occurrence over time. After only three years as many as 198 rockfall events have been occurred and collected since the map was generated. Particularly, 80% of rockfall fit with “high” and “very high” susceptibility classes, and pointed out large involvement of main roads in rockfall occurrence, representing the most affected target with damage to road pavement and vehicles, as well as a relevant involvement of existing rockfall barriers and of the dense network of forestry roads and footpaths that characterize this alpine region.ResultsThe proposed approach representing a starting point in landslide susceptibility map verification and usability as valid instrument for a reliable land planning.

High density mapping accuracy and efficiency in atrial fibrillation: real-world outcomes from the SECURE registry

Abstract Background/Introduction A high-density (HD) mapping catheter is valuable for validating pulmonary vein isolation (PVI) and analysing arrhythmic substrates of the left atrium (LA) during atrial fibrillation (AF) ablation. Multiple HD mapping catheters are available for use in clinical practice. A novel octa-spline mapping catheter with a close internal unipolar reference electrode is now available and may improve mapping efficiencies and image resolutions (Figure). Purpose This study aims to report real-world experiences with different commercially available HD mapping catheters in AF ablation and compare mapping performance. Methods SECURE is an ongoing observational, prospective, post-marketing study collecting real-world data on ablation procedures performed per standard-of-care. At the time of data extraction (Nov. 2023), 16 sites across 8 countries had enrolled 2,366 patients (pts), with 12-month follow-up data available for 828 pts. The current analysis, which included consecutive pts undergoing AF ablation, evaluated mapping efficiency and procedural outcomes with 3 HD mapping catheters: circular catheter (CC), penta-spline catheter (PSC), and octa-spline catheter (OSC). Mapping data were analysed with a cloud-based data management and artificial intelligence-powered algorithm. Results Overall, 859 pts with AF (paroxysmal AF [PAF], n=465; persistent AF [PsAF], n=240; long-standing PsAF [LS PsAF], n=154) were included in this analysis. The CC, PSC, and OSC were used in 428, 210, and 221 pts, respectively. Procedures using the OSC had a significantly higher mean mapping area (31,989.9 mm2) than those performed with the CC (23,152.2 mm2; P&amp;lt;0.0001) and PSC (29,804.6 mm2; P=0.0027), as well as a &amp;gt;3-fold higher mean mapping rate (138.4 vs 20.8 and 43.4 points/min, respectively; both P&amp;lt;0.0001). The higher number of mapping points translated to a higher mean mapping density (OSC, 0.34 vs CC, 0.05 and PSC, 0.07 points/mm2; both P&amp;lt;0.0001), with more uniform point distribution and less interpolation. With the CC, PSC, and OSC, respectively, total mean procedure times (incl PVI + other targets) were 118.0, 118.7, and 165.1 min, (P&amp;lt;0.0001 for OSC vs. both CC and PSC) and mean pre-ablation mapping times were 25.2, 25.0, and 21.5 min (P&amp;lt;0.0004 for OSC vs. both CC and PSC). The improved mapping quality and efficiency with the OSC allowed to include specific ablation targets beyond PVI. Fewer PVI-only procedures were performed with the OSC (29.4%) versus the CC (62.1%) and PSC (54.8%), while ablation of the PVI+ other targets was more common with the OSC versus the CC and PSC, including the cavotricuspid isthmus (37.1% vs 17.3% and 16.7%), LA roof (42.5% vs 13.1% and 21.4%), and LA posterior wall (21.7% vs 10.5% and 16.2%). Results were overall consistent per AF type (Table). Conclusions By providing more accurate mapping, the OSC allows for improved analysis of the arrhythmic substrate, which may improve ablation outcomes for pts with PAF and PsAF.Figure 1

New mapping algorithm SHIM (SVD, Hilbert Identifying Method) for the extraction of phase singularities and spiral waves in cardiac arrhythmias

Background and ObjectiveAtrial fibrillation (AF) is the most prevalent cardiac arrhythmia worldwide. The effectiveness of AF ablation is restricted primarily by inaccuracies in the voltage-map videos (VMVs) acquired through multielectrode catheters. We introduce an innovative algorithm improving map quality and pinpointing the precise locations of action potential singularities. MethodsThe methodology relies on three key operations: singular value decomposition (SVD), Hilbert transform, and identifying the ridge of singularities SHIM (SVD, Hilbert, Identifying Method). To check its feasibility, this approach was used to analyze record sources from two distinct origins: a) cultures of cardiac cells, and b) real-world atrial fibrillation (AF) measurements. Efficacy is exemplified through four illustrative cases, two involving cultures of cardiac cells exposing action potential spirals, and two clinical cases involving basket catheter voltage-map videos. Resolution goodness is measured by a new method of the ratio of the peak’s height divided by the average width at half maximum or the width of the ridge-of-peaks cross-section. ResultsIn the first sample, the driving rotor became evident only following the SVD procedure stage, and its stable center became more pronounced after the H and I stages. In the case of spiral splitting, SHIM extracted all the individual tiny spiral centers. In the VMVs obtained from the basket catheters, even when the image sharpness was suboptimal, distinct singularity ridges were easily discernible with peak intensities larger than 1. ConclusionThe cumulative impact of the three stages of our analysis suggests that our novel method may excel in identifying problematic sources more effectively than previously utilized systems.

Changing Climate Change Mental Models Through Game-Based Learning: A Controlled Experiment Involving Cognitive Mapping

Climate change is one of humankind's grand challenges, and how we think about it influences how we perceive its risks and act. Understanding people's mental models of climate change (that is, how they internally represent it) and potentially challenging and changing them can be a fruitful avenue towards engagement. However, our understanding of how games can affect climate change mental models is limited, especially in the lack of control conditions with comparable content. In this experiment, participants created cognitive maps of climate change before and after experiencing an immersive VR game, a desktop PC game, or a text with graphs. We show that all conditions improved the quality, focus, and systems orientation of cognitive maps, but no significant differences were found between groups. The intervention effectively increased the salience of issues such as health and biodiversity impacts, even though changes were limited in scope. The game was on average more enjoyable than the text, with the VR version significantly more so than the other two conditions. The findings suggest that games can be a viable and attractive communication and learning method where engagement is a struggle. We provide avenues for future research and, especially, game design in this area.

Comparison of Different Negative-Sample Acquisition Strategies Considering Sample Representation Forms for Debris Flow Susceptibility Mapping

The lack of reliable negative samples is an important factor limiting the quality of machine learning-based debris flow susceptibility mapping (DFSM). The purpose of this paper is to propose multiple negative-sample acquisition strategies for DFSM considering different sample representation forms. The sample representation forms mainly include a single grid, multi-grid, and watershed unit, and the negative-sample acquisition strategies are based on support vector machine (SVM), spy technique, and isolation forest (IF) methods, respectively. These three strategies can assign a value to all the samples based on different assumptions, and reliable, negative samples can be generated from samples with values below a predefined threshold. Combining different sample representation forms with negative sample acquisition strategies, nine datasets were then involved in random forest (RF) modeling. The receiver operating characteristic (ROC) curves and related statistical results were used to evaluate the models. The results show that the strategy based on the spy technique is suitable for multiple datasets, while the IF-based strategy is well-adapted to the watershed unit datasets. This study can provide more options for improving the quality of datasets in DFSM, which can further improve the performance of machine learning models.

Online extrinsic parameters calibration of on-board stereo cameras based on certifiable optimization

The extrinsic parameters of on-board stereo cameras can be slightly altered due to temperature fluctuations, vibrations, and accidental impacts during automobile driving, leading to significant performance loss in dense stereo matching. In this paper, we propose an online calibration method based on certifiable optimization to address this issue. Initially, sparse feature points are collected based on plane distribution and disparity. A robust optimization model is then developed to minimize the epipolar error, utilizing iterative local optimization to eliminate outliers and determine the 5DOF extrinsic parameters. Subsequently, a relaxation problem is constructed using inliers, and global optimization is performed to certify that the locally optimal results are indeed globally optimal. Comparative experimental results demonstrate that the proposed method offers high accuracy and reliability. Additionally, the quality of the disparity map generated by our calibration method is comparable to that achieved through offline calibration.

PGMF-VINS: Perpendicular-Based 3D Gaussian–Uniform Mixture Filter

Visual–Inertial SLAM (VI-SLAM) has a wide range of applications spanning robotics, autonomous driving, AR, and VR due to its low-cost and high-precision characteristics. VI-SLAM is divided into localization and mapping tasks. However, researchers focus more on the localization task while the robustness of the mapping task is often ignored. To address this, we propose a map-point convergence strategy which explicitly estimates the position, the uncertainty, and the stability of the map point (SoM). As a result, the proposed method can effectively improve the quality of the whole map while ensuring state-of-the-art localization accuracy. The convergence strategy mainly consists of a perpendicular-based triangulation and 3D Gaussian–uniform mixture filter, and we name it PGMF, perpendicular-based 3D Gaussian–uniform mixture filter. The algorithm is extensively tested on open-source datasets, which shows the RVM (Ratio of Valid Map points) of our algorithm exhibits an average increase of 0.1471 compared to VINS-mono, with a variance reduction of 68.8%.

Development of an Automatic Rock Mass Classification System Using Digital Tunnel Face Mapping

To mitigate unforeseen incidents, such as key block failure or tunnel collapse during excavation, an appropriate support pattern that correlates with the geological conditions of the rock mass at the tunnel face should be designed. Rock mass evaluations should be conducted through geological face mapping during the construction phase, alongside predictions based on field investigations during the design phase. When marked discrepancies are identified, it is customary to convene an on-site evaluation involving a committee of experts. This study develops a digital tunnel face mapping system that utilises mobile devices to facilitate online evaluations during the construction phase. This system effectively replaces the traditional on-site field evaluation method. Tunnel face mapping can be promptly accomplished using images captured at the excavation face, enabling rapid analysis. In conjunction with the mapping capabilities, the developed system was designed to digitally store geological information, which includes parameters such as rock strength distribution, the spacing and length of discontinuities observed during the mapping process, as well as data pertaining to weathering and the groundwater conditions of those discontinuities. This information was then correlated with the rock mass rating sheet to automate the determination of ratings for each parameter, ultimately leading to a conclusive classification of the rock mass quality. By employing this system for tunnel face mapping and rock quality evaluation, we significantly reduced the discrepancies in the evaluation results that often arise due to the subjective judgement of geologists, as well as human errors that can occur throughout the rating process.