A Generative Augmentation and Physics-Informed Network for Interpretable Prediction of Mining-Induced Deformation from InSAR Data

The establishment and growth of the small businesses in South Africa is of vital importance for economic stability and progress in the economy. A key small business management skill comprises occupational health and safety management, with particular reference to the proper identification of safety hazards and safety risks. This conceptual article set out to identify current perceptions about the concepts of safety, safety risks and safety hazards in the workplace while also identifying and analysing misconceptions regarding safety hazards. This article reports on a secondary data analysis of relevant literature on safety hazards and safety risk and the role thereof on small business success. The structure and functioning of the interrelated characteristics of safety hazards were visualised, with the objective of allowing small business owners or managers to understand how safety hazards contribute to safety risks. Proper identification of safety hazards and safety risks, along with adequate protection measures, allows for improved productivity and a reduction in operational costs. Safety hazards in the workplace, encompassing the functional and structural characteristics, such as humans and machinery, should be noted by small business owners, as applicable to all types of businesses. This article may serve as a catalyst for small business success through growth and sustainability by implementing enhanced safety management practices based on an accurate identification and analysis of safety hazards and safety risks. It allows for the identification and proactive mitigation of safety hazards and safety risks in all types of small businesses.

PurposeNatural hazards such as floods, wildfires and droughts disrupt communities, their economies and environments, and cost millions every year. The existing literature on hazard mitigation shows that community resilience is best achieved when mitigation strategies are integrated with land use and comprehensive planning. The purpose of this paper is to evaluate the strengths and weaknesses of hazard mitigation in local comprehensive plans.Design/methodology/approachThe analysis uses a new plan evaluation protocol that integrates flood, wildfire and drought mitigation to evaluate the plans of the six largest and fastest growing counties in Arizona.FindingsThe study finds that counties do not plan equally well for all hazards, that they tend to plan better for droughts than wildfires and floods, and indicates the need to improve hazard information in plans to support the adoption of mitigation goals, objectives and strategies.Research limitations/implicationsThe research is based on a small sample of comprehensive plans. It focuses on the content of plans rather than the causes that may explain this content or the implementation of the strategies included in the plans. Future research will thus need to analyze larger numbers of plans to identify the determinants of the degree to which comprehensive plans integrate hazard mitigation; and evaluate whether strategies advanced in plans are integrated with other planning documents and implemented.Practical implicationsThe paper makes recommendations to improve the plans evaluated and to guide planners as they develop or revise comprehensive plans in other jurisdictions subject to natural hazards.Originality/valueThe key methodological contribution of the paper is the new plan evaluation protocol designed to assess the wildfire, drought and flood mitigation provisions in comprehensive plans.

Rapid and spatially concentrated urbanization in South Africa has brought with it significant health and safety hazards. Political democracy and the dismantling of apartheid open the possibility of vigorous community participation in the identification and mitigation of such hazards. However there are severe obstacles to combining the expert knowledge of outside scientists with local knowledge of residents of the townships and squatter camps. This papers describes the common genesis of urban environmental hazards and the split between expert and local knowledge. They arise as twin products of the apartheid system that destroyed rural livelihoods, forcing Africans into over-crowded urban enclaves, denied them most educational opportunities and skilled employment, and denigrated local knowledge and self-help initiatives. This legacy must be overcome in the interest of hazard reduction in the New South Africa.

As the strength of road construction gradually increases and road networks tend to improve in mountainous areas, the safety of spoil ground slope has become an ecological and environmental problem that cannot be ignored. At present, especially under the dual control of basic farmland and ecological red lines, it is quite difficult to design a suitable spoil ground to meet construction needs. Spoil grounds are often overfilled. At present, safety evaluation is mainly conducted through field investigations and indoor calculations, which takes a longer time. It is extremely necessary to conduct quick safety evaluation and hazard mitigation on the spoil ground slope. Based on the data collection method, investigation and case study method and expert evaluation method, this paper establishes 18 evaluation indicators closely related to the safety of spoil ground slopes and assigns empowerments, forming a quick evaluation table for the safety of spoil ground slopes, and applies the table to the spoil ground slope on the Guiyang Huaxi-Anshun Expressway. The evaluation results indicate that the risk classification of the slope under normal conditions is high risk, while under rainfall conditions is extremely high risk. After slope stability calculation and comparison with the actual situation, the results are consistent, which indicate this quick evaluation table is suitable for safety evaluation of spoil ground slope.

<p>Mining exploitation is associated with the occurrence of adverse environmental effects. The most serious of such effects is land subsidence. Although land subsidence can be well predicted and mitigated by several methods, nevertheless, the extraction of mineral deposits is also associated with induced seismicity. The occurrence of seismic events causes ground surface vibrations, land surface displacements and, in many cases, has a negative impact on the safety of surface infrastructure and the inhabitants of endangered areas. Despite this, the issue of induced seismicity is much less recognized and often ignored in the assessment of the negative impacts of mining exploitation.</p><p>Induced seismicity is related to stress changes in the reservoir and surrounding rock mass that may be caused by a variety of mechanisms. Consequently, the patterns of induced seismicity vary greatly over time and space for different fields or events within the same field. It is often difficult to determine the correlation between seismicity and mining precisely because of the lack of data detailing the pattern of exploitation at the various wells. As a result, the source mechanism of mining-induced tremor remains a subject of active research.</p><p>The research aimed to better identify the phenomenon of induced seismicity caused by mining operations. Research has been conducted in the area of underground copper ore mining in Poland. Firstly, we investigate the pre-and post-seismic land-surface movements following 8 mining-induced Mw 3.6-4.8 earthquakes that occurred between 2016 and 2018. We use Sentinel 1 data to derive these movements 2 weeks before and 4 weeks after the mainshock. The results of these studies show that no substantial pre-seismic surface movements are indicating the possibility of a seismic event occurring. However, the co-seismic deformation fields are quite symmetrical, the maximum land subsidence is almost 10 cm and occurs within a few days after the mainshock. In addition, the time series of post-seismic deformation shows a gradual decay and a good correspondence with the post-shock distribution.</p><p>Secondly, we use the Mogi model, assuming the elastic half-space, to invert co-seismic deformation fields and to obtain the source parameters of the mine-induced earthquakes. The spatial distribution of the epicenters indicates a correlation with the fields of mining exploitation. The results also show that the average depth of the hypocenter tremor is approx. 650 m. This corresponds to the depth of the stiff sandstone layers adjacent to the exploration. These layers accumulate the stress of post-exploitation voids. In addition, the modeling results indicate an approx. the volume of the displaced rock layers of 1.2 x 105 m3. This value shows a high correlation with the volume of post-shock troughs determined based on InSAR data.</p><p>The results of this study contribute to research into activities related to mining operations resulting in an induced-earthquake occurrence. This demonstrates InSAR's potential for quasi-constant monitoring of large-scale areas against seismic hazards caused by ongoing mining operations.</p>

Multi-source datasets, including the UAV-Lidar/Photogrammetry, InSAR, and field investigation data, have been used for revealing the complex surface displacement pattern and focal mechanism of the 2021 Maduo Mw 7.3 earthquake. First, a co-seismic surface deformation field was extracted from the Synthetic Aperture Radar (SAR) images captured by ALOS-2 and Sentinel-1 satellites. Second, the SAR pixel offset tracking results were adopted to detect the initial location of the seismogenic fault. Then, the Lidar digital elevation model with high spatial resolution and field investigation were employed to refine and verify the location of the seismogenic fault. It was found that bifurcated strike-slip rupture should account for the 2021 Maduo earthquake. As indicated by the estimated faulting model based on the InSAR data, the maximal fault slip was ~6.2 m, occurring in the southeast of the main seismogenic fault, and five remarkable slip concentrations controlled the surface displacement of the 2021 Maduo earthquake. Furthermore, the co- and post-seismic InSAR deformation, dilatation, shear strain, Coulomb failure stress, and aftershock sequence suggest that the co-seismic rupture of the two main seismogenic faults have triggered the aseismic slip along the Changmahe fault. Lastly, according to the Coulomb failure stress change due to the historical earthquakes and the 2021 Maduo earthquake, the 1937 M 7.8 earthquake predominantly controlled the Coulomb failure stress change along the Kunlun fault, and the Xidatan-Alake Lake and Maqin segments had a higher risk of future earthquake than the other segments.

Throughout the western U.S., and in numerous other regions around the world, there is a growing need to monitor and regulate groundwater levels. Remotely sensed data offer spatially and temporally dense measurements over very large areas. of particular relevance to the characterization of groundwater systems is interferometric Synthetic Aperture Radar (inSAR), a remote sensing method that maps relative ground surface deformation. We present a methodology, using an advanced inSAR processing technique known as Small Baseline Subset Analysis (SBAS), that allows us to observe seasonal deformation and relate it to changes in the thickness of the confined aquifer due to recharge and withdrawal of groundwater. We have applied our methodology in the San Luis Valley (SLV), an 8000 km2 region in southern Colorado that is home to a thriving agricultural economy. the state has developed a hydrogeologic database and a groundwater flow model in order to quantitatively study possible management schemes for water resources in the SLV. Because well-sampled hydrographs, accurate lithologic logs and high quality aquifer tests are scarce, the model has not yet been able to characterize the spatially heterogeneous, time-varying behavior of the groundwater system. the more complete coverage offered by inSAR allows us to augment these sparse measurements. We infer hydraulic head change in the confined aquifer system by combining inSAR measurements with aquifer test data and lithologic logs. Conversely, where well-sampled hydrographs exist we use inSAR data in conjunction with the thickness of the producing zone to estimate the specific storage of the producing sediments. We propose a framework to combine all existing data together with the inSAR deformation estimates in order to improve the groundwater flow model. Ultimately all data types can be incorporated within this mathematical framework to better inform the decision-making process for groundwater management.

This study evaluates the landslide susceptibility of Zonguldak Province, Türkiye, by integrating the Analytical Hierarchy Process (AHP), artificial intelligence (AI) algorithms, and SBAS-InSAR deformation data. Eight environmental and geological parameters—elevation, slope, aspect, lithology, hydrogeology, land use, and distances to rivers and roads—were weighted using AHP and analyzed through 25 AI models. Among them, the Ensemble Bagged Trees (EBT) algorithm achieved the highest predictive accuracy (84%), demonstrating strong adaptability to complex geological datasets. The resulting susceptibility maps were validated using both traditional landslide inventories and InSAR-derived deformation maps, achieving an overall agreement of 83.05%. This dual-validation approach allows for the identification of unrecorded or active slope movements not captured in existing inventories. The combined use of AHP and AI significantly improves model reliability by incorporating both expert judgment and data-driven learning. The study introduces a novel hybrid framework for landslide susceptibility mapping and provides a valuable reference for disaster risk management and spatial planning in regions with complex topography. This study also contributes to sustainability by supporting risk-informed land-use planning, reducing potential economic losses, and enhancing environmental resilience in landslide-prone regions. The proposed framework aligns with sustainable development goals by integrating geospatial technologies and data-driven approaches for long-term hazard mitigation.

Snow avalanches are a significant concern across much of Alaska, posing risks to public safety, transportation, and accessibility. Despite their profound effect on society and the natural environment, avalanches remain poorly understood in many parts of Alaska. Public awareness and availability of information to support hazard adaptation, mitigation, and preparedness efforts are limited, even in the state’s most densely populated areas. The development of comprehensive avalanche hazard information is constrained by sparse observations of weather and snowpack conditions, and limited data on avalanche frequency. As climate warming progresses, shifts in temperature and precipitation are expected to modify snowpack conditions and influence the frequency and magnitude of avalanches, potentially changing Alaska’s vulnerability to these hazards. Understanding current avalanche hazards is critical for anticipating future climate-driven avalanche activity and assessing its potential effects on society and landscape dynamics. This project uses advanced avalanche models, originally developed and calibrated in Switzerland, to identify potential release areas and simulate millions of avalanche scenarios using downscaled climate reanalysis data and projections. The result is large-scale avalanche hazard indication maps for southeastern Alaska, both for present and future climate.

We propose a novel zero-shot multi-frame image restoration method for removing unwanted obstruction elements (such as rains, snow, and moire patterns) that vary in successive frames. It has three stages: transformer pre-training, zero-shot restoration, and hard patch refinement. Using the pre-trained transformers, our model is able to tell the motion difference between the true image information and the obstructing elements. For zero-shot image restoration, we design a novel model, termed SiamTrans, which is constructed by Siamese transformers, encoders, and decoders. Each transformer has a temporal attention layer and several self-attention layers, to capture both temporal and spatial information of multiple frames. Only self-supervisedly pre-trained on the denoising task, SiamTrans is tested on three different low-level vision tasks (deraining, demoireing, and desnowing). Compared with related methods, SiamTrans achieves the best performances, even outperforming those with supervised learning.

Morphing attack detection is a critical component of face recognition systems, ensuring reliable applications in border control. In this work, we propose a novel Differential Morphing Attack Detection (D-MAD) method capable of effectively capturing variations in differential features extracted using a Face Recognition System (FRS). Our proposed model, TimFusNet, combines time-frequency and temporal variations from the difference in facial embeddings computed from passport and trusted face images. The TimFusNet architecture comprises two branches: the first branch captures time-frequency variations from the input differential embeddings, while the second branch focuses on extracting temporal variations. The features from both branches are concatenated and passed through a self-attention layer to reliably detect morphing attacks on FRS. We conducted extensive experiments using a morphing dataset constructed from the FRGC dataset, employing five different morphing generation techniques. The detection performance of TimFusNet was benchmarked against four existing D-MAD techniques under two evaluation protocols. The results demonstrate that TimFusNet delivers outstanding detection performance across both protocols.

A method for extracting mining-induced surface subsidence based on multi-source data fusion is proposed by integrating the advantages of InSAR, PIM, and UAV technologies. This approach first employs InSAR to obtain time-series cumulative subsidence basins and constructs constraint conditions to distinguish between high-gradient deformation zones, enabling the differentiation of subsidence edges and centers. In the subsidence edge areas, InSAR monitoring results are retained, while in the central zones with large-gradient subsidence, a weighted fusion of PIM and UAV data is conducted to establish a subsidence basin model for the mining working face. Subsequently, spatial interpolation is applied to derive continuous surface subsidence information in a geographic coordinate system, ultimately generating a complete surface subsidence map of the mining area. The method is validated using Sentinel-1A satellite imagery, UAV data, and leveling measurements from the 120101 working face of the Yangchangwan Coal Mine in the Ningdong mining area. The results demonstrate that this method effectively compensates for the limitations of using InSAR, PIM, or UAV data individually, enhances monitoring capability in high-gradient subsidence areas, and enables the acquisition of more accurate and spatially continuous surface subsidence information.

To improve the accuracy of deformation prediction in concrete buildings and large-scale infrastructures such as dams, this study proposes an Attention-BiLSTM model integrated with a parameter-optimized Variational Mode Decomposition (VMD). Specifically, the Pelican Optimization Algorithm (POA) is employed to optimize VMD parameters, enhancing signal decomposition efficiency for structural deformation time series. The optimized VMD is then coupled with a BiLSTM network embedded with an attention mechanism, forming a hybrid prediction framework that captures both temporal dependencies and key feature weights in monitoring data. Using three sets of engineering-measured deformation datasets, the proposed model is validated through comparative analyses with conventional single models (e.g., standalone BiLSTM and VMD-BiLSTM without attention). Results demonstrate that the developed model achieves superior accuracy and stability, significantly outperforming all comparative methods, with the highest R2 reaching 0.996, while reducing MAE and RMSE by over 60% and 30%, respectively. Quantitative evaluation indicators (e.g., RMSE, MAE, and R2) confirm that the approach effectively captures both short-term fluctuations and long-term trends of structural deformation. These findings verify its reliability and applicability for intelligent safety monitoring of concrete buildings and infrastructures.

The highway between Aswan and Cairo on the eastern bank of the Nile Valley is one of the most used highways in Egypt, connecting most of the governorates with each other. It represents the backbone of Egyptian transportation and commercial traffic. This Highway passes through a two kilometer section of rock cut located 20 km north of New Assiut city. Serious stability and rock fall issues have been recognized in this section in the past few years. In this study the stability of the rock cuts have been evaluated using different techniques including: 1) Determining the most relevant factors affecting slope instability; 2) interpreting the discontinuity data collected from the joint surveys using stereographic projection for the assessment of the modes of failure and determining the potential unstable zones; 3) applying a rock fall simulation program(s) to evaluate the potential rollout distance for the falling rocks; 4) applying the Missouri Rock Fall Hazard Rating System (MORFH RS). Finally, the most optimum mitigation method that will decrease and minimize the consequences of slope instability was determined. This study reveals that the cut needs to be mitigated because of the ongoing slope instability present in some areas, including planar and wedge slides and raveling rock falls. It was found that the unstable rock areas create serious safety hazards to traffic.

Shock tubes are the instruments used to replicate and direct blast waves at a sensor or a model in order to simulate actual explosions and their effects, usually on a smaller scale. A shock tube is a simple aerodynamic device that is capable of producing controlled shock waves. Recently many research laboratories all over the world including the Defence organizations have shown special interest in the development of shock tubes test facilities due to its potential applications in aerodynamic testing, material testing, chemical kinetics, biological and Defence & medical applications. Results from shock tube experiments can be used to develop and validate numerical model, materials study, shock attenuation and mitigation, design of blast protective systems etc., Keeping in view of the hazards associated with the operations involved and the recent accidents in the shock tube test facilities, it is paramount important to carry out thorough safety assessment for these facilities to ensure the safety of men, machine and materials inside the facilities. Out of various safety management tools, Hazard Identification and Risk Analysis (HIRA) methodology is best suited for the risk assessment of the shock tube test facility. This paper describes the operation, maintenance safety considerations for a shock tube test facility and also discusses the hazards associated with the facility and suggest suitable hazard mitigation methodologies to ensure safe working environment.