The Loess Plateau, as a natural ecological barrier in the western region of China, has made positive contributions to the sustainable development of the nation. The governance and restoration of the ecological environment on the Loess Plateau (Gansu region) plays a critical role in the implementation of China’s ecological civilization construction strategy. To monitor the changes in forest resources on the Loess Plateau (Gansu region) from 2008 to 2018, based on cloud platform, Landsat, PALSAR, and terrain data were integrated to explore the advantages of spectral index, backscatter, texture, and terrain features in obtaining forest resource information. The random forest feature selection algorithm was utilized to obtain the spatiotemporal distribution of forest cover in the study area for 10 years, and factor detection was conducted using geographic detectors. The results indicate that the random forest feature selection algorithm can effectively screen important feature information, with an overall accuracy of 91.88% and a Kappa coefficient of 0.91. The experimental scheme that integrates Landsat, PALSAR, and terrain data presents significantly higher accuracy compared to the forest classification results using a single data source. The overall accuracy of the four classification results is 86.65%, 88.23%, 90.15%, and 89.86% respectively. Over the past 10 years, the net increase in forest area in the study area is 0.60×10⁴ km². The areas with increased forests are primarily distributed in the central and eastern parts of Qingyang City, Pingliang City, Tianshui City, and the western region of Linxia Hui Autonomous Prefecture, while forest degradation primarily occurs in the southwestern part of Dingxi City and the central and eastern areas of Linxia Hui Autonomous Prefecture. In single-factor detection, land use type is the dominant factor in forest cover change, and the spatial distribution of suitable soil type and the auxiliary effect of rainfall provide favorable natural conditions for the survival rate of afforestation and the healthy growth of forests.

Primary cracks and new cracks develop within the engineering rock mass, leading to the formation of macroscopic cracks. The hollow cylindrical discrete element simulation test enables the emulation of complex stress paths. In order to solve the problems existing in the simulation test of hollow cylindrical discrete element, such as numerous influencing factors and lengthy meso-parameter calibration, a method of mesoscale parameter calibration of hollow cylindrical sandstone discrete element based on machine learning algorithm was proposed. Through variations in input variables within the discrete element model, 210 sets of simulation data were obtained. A mesoscopic parameter calibration model based on random forest algorithm and extreme gradient boosting(XGBoost) algorithm was established, the prediction accuracy of the model was compared, the parameter sensitivity was analyzed, and the contribution of input parameters to the overall mechanical properties of the rock was quantified. Combined with the indoor triaxial test of hollow cylinder, the calibration results show that the XGBoost algorithm has the advantages of computing speed, and can quickly locate the range of discrete element mesoscopic parameters, which provides a new idea for the calibration of discrete element mesoscopic parameters of hollow cylinder, and has the value of engineering application.

The scientific extraction of urban built-up area information and the exploration of the spatial-temporal characteristics of urban expansion have significant relevance for urban planning and management. The local-optimal thresholding method was refined for the quantitative extraction of urban built-up area information within the Baiyangdian Basin, and the extraction process utilized PANNDA nighttime light data and Landsat series data from four periods: 1990, 2000, 2010, and 2020. Subsequently, an analysis of the spatial-temporal characteristics of urban built-up area expansion in the basin over the past 30 years was conducted using the urban expansion index and landscape index. The results show the optimized local-optimal thresholding method is successfully used to extract the data of the built-up areas in the basin for all phases, and it is confirmed that the method exhibits enhanced applicability compared to its pre-optimization state. The urban built-up area in the Baiyangdian Basin experienced significant expansion throughout the study period, with a growth rate of 154.48%. The sizes of the built-up areas across the 35 cities in the basin exhibited high heterogeneity. Temporally, the expansion of urban built-up areas predominantly exhibited an accelerating trend, with a widening disparity in the pace of expansion among the cities within the basin. Spatially, the built-up area to the left of the Zhengding-Zhuozhou line was less developed than that to the right. Notable expansion trends were observed in municipal districts or county-level cities such as Lianchi District, Jingxiu District, and Gaobeidian City. Based on the results of the landscape index, the expansion of urban built-up areas in Baiyangdian Basin shows the spatial characteristics of “dispersion-fusion” during the study period, and the boundary of built-up areas showed the evolution characteristics of “regular-complex-regular”.

Multivariate time series classification is a key problem in many fields, but the current research on multivariate time series classification is faced with some problems, such as high dimensionality of original data, low accuracy, and lack of interpretability, which limits the performance improvement of models and makes it difficult to meet the actual requirements. Aiming at above problem, a multivariate time series classification method based on Shapelets was proposed. Firstly, unsupervised Shapelet learning of adaptive neighbors was used to automatically learn significant multivariate Shapelets by combining Shapelets transform and adaptive weights. Then, the method was combined with Shapelet similarity and class label constraint to enhance the interpretability and classification accuracy of the model. Finally, the optimization strategy of the model was proposed to obtain the best Shapelets to further improve the classification accuracy of the model. Three different types of 11 algorithms were compared on 11 public data sets, and the experimental results show that the proposed algorithm has high classification accuracy.

A geomagnetic storm is a periodic natural disaster in which the changing geomagnetic field can induce an induced geoelectric field. A geomagnetic induced current (GIC) loop is formed between the transmission line and the earth conductor through the neutral points of grounding transformers. GIC seriously threatens the safe and stable operation of extra-high and ultra-high voltage AC transmission systems. There are many types of terrain and complex structures in our country, which makes the influence of geological landforms on induced geoelectric fields very significant. A finite element calculation method for GIC was proposed based on a three-dimensional earth conductivity model to address the difficulties in modeling and calculating GIC. Firstly, a three-dimensional earth conductivity model was established considering the anisotropy of geological structures. Meanwhile, a calculation model for electromagnetic field penetration depth under multi-layer geological conditions was given. Secondly, a mathematical model based on time-varying electromagnetic fields was established. Combined with the topology of the power grid, an equivalent calculation model for the power grid GIC was derived. Finally, taking the Shache-Turpan 750 kV transmission line in Xinjiang area as an example, a corresponding physical model was built in COMSOL Multiphysics finite element simulation software. The three-dimensional distribution of the induced ground electric field in the power grid was obtained through geometric modeling, boundary condition setting, grid division, and iterative solution. Furthermore, the GIC flowing through the neutral point of the 750 kV transformer was obtained. The research results indicatethat the overall level of GIC obtained by the 3D model is higher than that of the 2D model. Besides, the 3D model considers the geometric angle between the transmission line and different terrains, which can provide a more detailed distribution of induced geoelectric fields. The research results verify the effectiveness of the method proposed, which provides a reference basis for scientific planning of ultra-high and ultra-high voltage transmission corridors.

In order to study the prevention and control of power disaster induced by coal mining process, Brazilian splitting test of raw coal specimen was carried out to study the energy evolution law in the process of coal body tensile damage destruction, and the precursor information of coal body destabilization and destruction was identified. The results show that the coal body tensile damage process has significant nonlinear evolution characteristics, and it is possible to identify the critical point, destabilization point, and damage point of coal body damage. The energy evolution characteristics of coal body tensile damage in each stage are significantly different. In the elastic deformation stage, the input energy is mainly converted into elastic energy, and the dissipation energy remains stable, while in the destabilization stage, the dissipation-elasticity ratio shows a jumping growth. By calculating the energy release rate and energy dissipation rate, it is found that the index has abnormal response characteristics at the critical point, destabilization point and damage point of the coal body tensile process, and the appearance of the characteristic points all have significant precursor information. The nature of coal destabilization is the result of energy accumulation and dissipation, and the energy index of coal body can reveal the abnormal characteristics of energy evolution in the process of damage and destruction of the specimen, and identify the precursor information of coal body catastrophe, which is conducive to the over-warning, and escort for the safe mining of coal.

Shared bikes represent a crucial component of urban transportation. The randomness of user demand for shared bikes with fixed piles leads to unbalanced demand in time and space, and even the difficulty in renting a bike, which cannot meet the user demand during peak hours. Therefore, high-frequency users frequently travel to nearby stations to rent a bike for serving, which means that there are implicit demands. As for the hidden demand, firstly, the state changes of the site were described by the rental number and the return number, and the critical state of the reference site was determined by mining the user travel conditions of nearby sites. The hidden demand of the site was determined based on the site state change diagram and the demand judgment model. Then, according to the real needs of the site, the long short-term memory(LSTM) network prediction model was established, and the regional scheduling model of shared bicycles based on the real needs was established. The model takes the cost minimization as the goal, and obtains the path with minimum scheduling cost through genetic algorithm, which provides a reference for balanced scheduling based on real demand. The results demonstrate that, when transportation costs are similar, the scheduling method under real demand can alleviate the problem of users’ difficulty in renting a bike, thereby reducing the loss of high-frequency users.

Addressing the challenge of insufficient accuracy in building regional cultural heritage 3D models using single-image modeling techniques, a method for optimizing regional ancient architectural three-dimensional models through the fusion of laser and imagery was proposed. Initially, imagery data of the target area was acquired through drone-based cross-flight aerial photography combined with close-range photography. Subsequently, laser scanning data was obtained using a 3D laser scanner to cover blind spots from drone aerial photography. Then, the laser scanning data was fused and registered with the imagery data to generate a complete point cloud model of the target area, which is then used to reconstruct a refined 3D model of the regional cultural heritage. Finally, the superiority of the proposed method was validated through error analysis of the fused heterogeneous data and comparative analysis of accuracy and texture completeness with single-image modeling results. The results indicate that the fused heterogeneous data achieves high fitting accuracy, and the resulting regional ancient architectural 3D model exhibits high accuracy and texture completeness, thereby providing valuable technical reference for the detailed modeling of ancient architectural complexes within the target scope and holding broad application prospects in enhancing the digital archive storage of ancient architectural three-dimensional models.

The tension string system with concentrated viscous damping belongs to a hybrid dynamic system in mechanical models. Approximate methods are typically used to solve its inherent problems for engineering applications. In order to further clarify the vibration characteristics of the system, two centrally damped symmetrical damping string systems were taken as the basic research object, and their complex eigenvalues were solved analytically. The complex frequency equation and the eigenvalue expression of the system were derived, and the transformation of the complex frequency equation beyond the function form was treated as algebraic form, and the explicit solution of the complex eigenvalue of the system was given by the algebraic equation. The structure and properties of the complex eigenvalues of the system were analyzed, and the variation of vibration characteristics with damping coefficient was discussed. The results show that the eigenvalue solution of the system can be divided into three branches, in which the real part of the eigenvalue(the inverse is the decay rate) does not change with the order of the system motion, but the imaginary part of the eigenvalue(the frequency) increases with the order of the motion. The decay rate curves corresponding to each solution branch increase first and then decrease with the damping coefficient, and in the damping range of the decay rate curve, the frequencies of each order of the system are equal.

Based on Monte Carlo method, Python and Abaqus interface were used for secondary development, and an interfacial transition zone was generated to distinguish between natural coarse aggregates and new and old interfacial transition zone(ITZ) and recycled aggregate concrete (RAC) 2D meso-five phase model of new and old mortar. An improved moisture-chloride ion coupling model under dry-wet cycles was proposed, and the computational results of this model were compared and validated against physical experiments, with good agreement. This model was then applied to analyze the effects of dry-wet cycle periods, ITZ permeability, water-cement ratio, and natural aggregate volume fraction on chloride ion transport properties. The numerical results show that as the number of dry-wet cycles increases, the diffusion depth and concentration of chloride ions in RAC also increases. When the ratio of ITZ diffusion coefficient to the new mortar diffusion coefficient increases, the chloride ion concentration in the diffusion region increases significantly, especially at the front end of the diffusion zone. In addition, there is a positive correlation between RAC materials with different water-cement ratios and chloride ion transport capacity, with little variation in chloride ion transport performance within the high water-cement ratio range. Finally, the volume fraction of recycled aggregates has a significant impact on the chloride ion permeability of RAC, indicating that the ITZ and new and old mortar have an important influence on the transport of chloride ions.