The presence of frozen volatiles (especially H2O ice) has been proposed in the permanently shadowed regions (PSRs) near the poles of the Moon, based on various remote measurements including the visible and near-infrared (VNIR) spectroscopy. Compared with the middle- and low-latitude areas, the VNIR spectral signals in the PSRs are noisy due to poor solar illumination. Coupled with the lunar regolith coverage and mixing effects, the available VNIR spectral characteristics for the identification of H2O ice in the PSRs are limited. Deep learning models, as emerging techniques in lunar exploration, are able to learn spectral features and patterns, and discover complex spectral patterns and nonlinear relationships from large datasets, enabling them applicable on lunar hyperspectral remote sensing data and H2O-ice identification task. Here we present H2O ice identification results by a deep learning-based model named one-dimensional convolutional autoencoder. During the model application, there are intrinsic differences between the remote sensing spectra obtained by the orbital spectrometers and the laboratory spectra acquired by state-of-the-art instruments. To address the challenges of limited training data and the difficulty of matching laboratory and remote sensing spectra, we introduce self-supervised learning method to achieve pixel-level identification and mapping of H2O ice in the lunar south polar region. Our model is applied to the level 2 reflectance data of Moon Mineralogy Mapper. The spectra of the identified H2O ice-bearing pixels were extracted to perform dual validation using spectral angle mapping and peak clustering methods, further confirming the identification of most pixels containing H2O ice. The spectral characteristics of H2O ice in the lunar south polar region related to the crystal structure, grain size, and mixing effect of H2O ice are also discussed. H2O ice in the lunar south polar region tends to exist in the form of smaller particles (similar to 70 mu m in size), while the weak/absent 2-mu m absorption indicate the existence of unusually large particles. Crystalline ice is the main phase responsible for the identified spectra of ice-bearing surface however the possibility of amorphous H2O ice beneath optically sensed depth cannot be ruled out.

The study of macroscopic discrete granular materials holds significance in hydraulic engineering, geotechnical engineering, as well as road and bridge engineering. Its foundational scientific exploration bears profound theoretical implications and is of pivotal practical value to engineering endeavors. Within the realm of engineering construction, issues such as dam breakages, earth-rock dam damage, and geological disasters involving loose particles pose substantial threats to the safety of both national livelihoods and property. Thus, delving into the examination of the structural stability of granular materials at the mesoscopic scale becomes an imperative pursuit. In this study, the topological structure of granular materials is identified and segmented based on image processing techniques, and the relationship between the compressive capacity of polygonal structures and the number of polygonal sides is studied. The redundancy function is defined to evaluate the structural stability of granular materials. In addition, the definition of structure tensor is introduced, and redundancy and structure tensor are applied to the study of biaxial compression of shale materials. The research results contribute to improving engineering safety and have guiding merits for the research and application of granular materials. Future work could focus on extending these methods to other types of granular materials and exploring their behavior under different loading conditions. (c) 2025 Published by Elsevier B.V. on behalf of Chinese Society of Particuology and Institute of Process Engineering, Chinese Academy of Sciences.

Around the world severe damages were observed due to reliquefaction during repeated earthquakes, whereas precise understanding of its mesoscopic mechanism is not much discovered. Influence of these earthquakes on reliquefaction needs to be investigated to understand its significance in contributing to inherent sand resistance. In the present study, centrifuge model experiments were performed to examine the influence of foreshocks/aftershocks and mainshock sequence on resistance to reliquefaction. Two different shaking sequences comprising six shaking events were experimented with Toyoura sand specimen with 50 % relative density. Acceleration amplitude and shaking duration of a mainshock is twice that of foreshock/aftershock. In-house developed advanced digital image processing (DIP) technology was used to estimate mesoscopic characteristics from the images captured during the experiment. The responses were recorded in the form of acceleration, excess pore pressure (EPP), subsidence, induced sand densification, cyclic stress ratio, void ratio and average coordination number. Presence of foreshocks slightly increased the resistance against EPP before it gets completely liquefied during the mainshock. Similarly, aftershocks also regained the resistance of liquefied soil due to reorientation of particles and limited generation of EPP. However, application of mainshocks triggered liquefaction and reliquefaction and thus eliminated the beneficial effects achieved from the prior foreshocks. Reliquefaction was observed to be more damaging than the first liquefaction, meanwhile the induced sand densification from repeated shakings did not contribute to increased resistance to reliquefaction. The apparent void ratio estimated from the DIP technology was in good agreement with real void ratio values. Average coordination number indicated that the sand particles moved closer to each other which resulted in increased resistance during foreshocks/aftershocks. In contrast, complete liquefaction and reliquefaction have destroyed the dense soil particle interlocking and made specimen more vulnerable to higher EPP generation. (c) 2025 Production and hosting by Elsevier B.V. on behalf of The Japanese Geotechnical Society. This is an open access article under the CC BY- NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

This investigation addresses the reinforcement of rammed earth (RE) structures by integrating carpet polyacrylic yarn waste (CPYW) generated from the carpet production process and employing Ground Granulated Blast-Furnace Slag (GGBS) as a stabilizer, in conjunction with alkali activators potassium hydroxide (KOH), to enhance their mechanical properties. The study included conducting Unconfined Compressive Strength (UCS) tests and Brazilian Tensile Strength (BTS) tests on plain samples, GGBS-stabilized (SS) samples, CPYW-reinforced (CFS) samples, and samples reinforced with a combination of GGBS and CPYW (SCFS). The results showed that the mechanical and resistance properties of the CFS and SCFS samples were improved; these findings were confirmed by the presence of more cohesive GGBS gel and fibers as seen in FE-SEM and microscopic images. Therefore, the use of GGBS and CPYW, both separately and in combination, is suggested as a viable approach to enhance mechanical performance and reduce the brittle failure propensity of RE structures. This study achieved significant improvements in the mechanical behavior of RE structures by integrating CPYW and alkali-activated GGBS. Results showed a 370% improvement in UCS and a 638% increase in BTS than the plain sample. These enhancements demonstrate the potential for using industrial waste in eco-friendly, high-performance construction materials.

The internal microstructures of rock materials, including mineral heterogeneity and intrinsic microdefects, exert a significant influence on their nonlinear mechanical and cracking behaviors. It is of great significance to accurately characterize the actual microstructures and their influence on stress and damage evolution inside the rocks. In this study, an image-based fast Fourier transform (FFT) method is developed for reconstructing the actual rock microstructures by combining it with the digital image processing (DIP) technique. A series of experimental investigations were conducted to acquire information regarding the actual microstructure and the mechanical properties. Based on these experimental evidences, the processed microstructure information, in conjunction with the proposed micromechanical model, is incorporated into the numerical calculation. The proposed image-based FFT method was firstly validated through uniaxial compression tests. Subsequently, it was employed to predict and analyze the influence of microstructure on macroscopic mechanical behaviors, local stress distribution and the internal crack evolution process in brittle rocks. The distribution of feldspar is considerably more heterogeneous and scattered than that of quartz, which results in a greater propensity for the formation of cracks in feldspar. It is observed that initial cracks and new cracks, including intragranular and boundary ones, ultimately coalesce and connect as the primary through cracks, which are predominantly distributed along the boundary of the feldspar. This phenomenon is also predicted by the proposed numerical method. The results indicate that the proposed numerical method provides an effective approach for analyzing, understanding and predicting the nonlinear mechanical and cracking behaviors of brittle rocks by taking into account the actual microstructure characteristics. (c) 2025 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/ 4.0/).

We report an innovative method of extracting water distribution network (WDN) historical repair location data from images of paper repair data maps, to provide usable geo-referenced digitally formatted data. For most water utilities, repair location data typically fall into two eras: pre- and post-GIS, approximately corresponding to pre- and post-2000. Automated conversion of pre-2000 paper maps to a geo-referenced digital format provides additional data to clarify trends in pipe repair causative factors, such as material defects, corrosive or creeping soils, and traffic. We applied the methodology to more than 3,000 maps of the Los Angeles Department of Water and Power WDN, thereby extending the record of repairs backward from 2000 to 1975, almost doubling the number of repair records. The methodology's value, when using the resulting data for analysis, lies in the following: (a) large volumes of hard copy data can now be acquired in an automated manner, saving significant time and effort, (b) specific repair locations are accurately captured, resulting in (c) more reliable, confident, analyses, and results, (d) ongoing problem areas, due to corrosive or creeping soils for example, can be more specifically understood.

In recent years, owing to the advancement of highway infrastructure, modified asphalt has been extensively employed in pavement engineering. Asphalt mixture will invade the soil under high-temperature conditions, affecting soil cracking. Cracking characteristics caused by dryness of the mixed samples of modified asphalt and soil accounting for 0%, 2.5%, 5%, and 7.5% of the total weight were investigated in this paper. According to the water loss situation, the degree of cracking was determined. The crack development was quantitatively analyzed by digital image processing technology, so as to analyze the influence of modified asphalt on soil cracking under different contents. The results show that the soil was relatively better than the normal state. Under the same conditions, the moisture content of modified asphalt soil with 2.5%, 5%, and 7.5% increased by 30.17%, 63.49%, and 110.37% compared with that without modified asphalt. At the same time, due to its special bonding properties, it can effectively improve the cracking of soil. The cracking rate of modified asphalt soil with 2.5%, 5%, and 7.5% content is reduced by 11.58%, 20%, and 31.58%, respectively. The soil added with modified asphalt can effectively increase the total porosity of the soil, thus improving the ability of water absorption, and also can well inhibit the rate of soil evaporation and reduce cracking. Modified asphalt can be rationally applied not only to have soil mechanical properties improved but also to have waste asphalt utilized to reduce environmental pollution.

Desiccation cracking has a significant impact on the hydro-mechanical properties of soils, yet quantifying crack patterns remains challenging. This study presents a quantitative framework with a total of 26 parameters for characterizing the geometric and morphological characteristics of soil desiccation crack patterns, including soil clod parameters (soil clod area, soil clod perimeter, number of clods, and the probability density distribution of clod parameters, etc.) and crack network parameters (crack length, crack width, crack inter angle, number of crack segments, surface crack ratio, crack density, connectivity index, etc.). To implement this quantitative framework, the Crack Image Analysis System (CIAS) was developed to automatically identify and analyse complex crack patterns through image preprocessing, clod identification, crack network identification and batch processing. CIAS was then applied to quantify the crack images of soil with different thicknesses, validating its efficacy. To comprehensively describe the geometric and morphological characteristics of crack networks, it is recommended to use the number of soil clods per unit area, surface crack ratio, crack density, and connectivity index as key parameters. These metrics effectively capture information on crack spacing, area, length, width, and connectivity. This comprehensive framework for characterizing and quantifying crack images is of great significant for geological engineering. Moreover, it holds great potential for application in other different disciplines such as geotechnical, hydraulic, mineral engineering and material even planetary science.

In today's urban development, Earth Pressure Balance (EPB) Tunnel Boring Machines (TBMs) play a vital role. It's crucial to design a comprehensive monitoring system to control surface settlement and prevent damage to surface structures. This study focuses on creating prediction models for estimating ground surface settlement. Two soft computing techniques, namely ANN-CFB and ANN-BP, were used for this purpose. The models were validated using operational data from the Qom metro Line A, specifically the between A14 and A10 stations. Additional input parameters were incorporated using an image processing approach to include soil properties for each segment. As a result, the most accurate ANN technique was employed to predict ground surface settlements for the mentioned project. The correlation coefficients for training, testing, validation, and the overall result were found to be 0.99439, 0.97873, 0.96381, and 0.98824, respectively. Through sensitivity analysis, the study explored the connections between different parameters and ground surface settlement. The outcomes reveal strong agreement between predicted values and real data. Notably, the parameter 'cutter head torque' exhibited the highest impact on surface settlement (8.48%), while 'Pressiometric Modulus (Ep)' had the least impact (4.24%).

Most natural disasters result from geodynamic events such as landslides and slope collapse. These failures cause catastrophes that directly impact the environment and cause financial and human losses. Visual inspection is the primary method for detecting failures in geotechnical structures, but on-site visits can be risky due to unstable soil. In addition, the body design and hostile and remote installation conditions make monitoring these structures inviable. When a fast and secure evaluation is required, analysis by computational methods becomes feasible. In this study, a convolutional neural network (CNN) approach to computer vision is applied to identify defects in the surface of geotechnical structures aided by unmanned aerial vehicle (UAV) and mobile devices, aiming to reduce the reliance on human-led on-site inspections. However, studies in computer vision algorithms still need to be explored in this field due to particularities of geotechnical engineering, such as limited public datasets and redundant images. Thus, this study obtained images of surface failure indicators from slopes near a Brazilian national road, assisted by UAV and mobile devices. We then proposed a custom CNN and low complexity model architecture to build a binary classifier image-aided to detect faults in geotechnical surfaces. The model achieved a satisfactory average accuracy rate of 94.26%. An AUC metric score of 0.99 from the receiver operator characteristic (ROC) curve and matrix confusion with a testing dataset show satisfactory results. The results suggest that the capability of the model to distinguish between the classes 'damage' and 'intact' is excellent. It enables the identification of failure indicators. Early failure indicator detection on the surface of slopes can facilitate proper maintenance and alarms and prevent disasters, as the integrity of the soil directly affects the structures built around and above it.