Aim Alaska's boreal forest is experiencing increasingly severe fires, droughts, and pest attacks that may destabilize carbon sequestration. Our aim was to understand boreal forest resilience to changing wildfire regimes using remote-sensed datasets validated with ground-truthing (GT).Location Five recently burned boreal forest sites (2010-2019) near Fairbanks, Alaska.Methods We used four AVIRIS-NG hyperspectral image datasets (425 spectral bands at 5-nm intervals; 3.5 x 43 km average swath) imaged by NASA in 2017-2018 during the Arctic-Boreal Vulnerability Experiment (ABoVE). Spectral analysis included fire fuel loads and random forest (RF) models constructed from key bands to describe common pre- and postburned vegetation classes. Models were validated with 89 GT plots inside the AVIRIS scenes. GT included tree stem densities, understory cover, soil characteristics, radial growth of 51 spruce trees from cores, and visual damage assays of 668 conifers and deciduous trees.Results Spectral evidence of high fuel loads in 2017 pre-dated a 2019 wildfire. Post-GT local models described vegetation more accurately than pre-GT, but accuracy decreased when spectral rulesets were broadened to increase overall classification. Soil temperature, basal area, slope, elevation, and tree density varied widely; thaw depth, soil moisture, moss cover, and canopy height varied mainly by vegetation class. Invasive species and thermokarst were insignificant. Deciduous seedlings were abundant in postburned sites; however, conifer seedling densities were similar to unburned forest. Upland spruce radial growth showed earlier drought sensitivity than lowland spruce.Conclusion Spectral analysis revealed fire vulnerability in some areas; however, local and temporal spectral variation presented challenges to accurately classify vegetation in AVIRIS scenes. GT suggests that recovering forests near Fairbanks may lack sufficient conifer recruitment to replace existing stands. Sites with stable seasonal thaw may offset drought stress under global warming.

This study investigates the application of machine learning (ML) algorithms for seismic damage classification of bridges supported by helical pile foundations in cohesive soils. While ML techniques have shown strong potential in seismic risk modeling, most prior research has focused on regression tasks or damage classification of overall bridge systems. The unique seismic behavior of foundation elements, particularly helical piles, remains unexplored. In this study, numerical data derived from finite element simulations are used to classify damage states for three key metrics: piers' drift, piles' ductility factor, and piles' settlement ratio. Several ML algorithms, including CatBoost, LightGBM, Random Forest, and traditional classifiers, are evaluated under original, oversampled, and undersampled datasets. Results show that CatBoost and LightGBM outperform other methods in accuracy and robustness, particularly under imbalanced data conditions. Oversampling improves classification for specific targets but introduces overfitting risks in others, while undersampling generally degrades model performance. This work addresses a significant gap in bridge risk assessment by combining advanced ML methods with a specialized foundation type, contributing to improved post-earthquake damage evaluation and infrastructure resilience.

The properties of soils are highly complex, and therefore, the classification system should be based on multiple perspectives of soil properties to ensure effective classification in geotechnical engineering. The current study of research demonstrates a lack of correlation between classification systems based on soil plasticity and those based on in-situ mechanical properties of soils. A CPTu-based plasticity classification system is proposed using the soil behaviour type index (Ic), with its reliability and limitations discussed. The results indicate that (1) Ic has the capacity to predict the stratigraphic distribution from the in-situ mechanical properties of soils. It showed a significant linear correlation with wL, which soil classification zone was similar to that of clay factor (CF); (2) A CPTu-plasticity classification system is proposed to characterize both plasticity and in-situ mechanical properties of soils. This system allows for the initial classification of soils solely based on CPTu data. Furthermore, it has been established that Ic = 2.95 can delineate the boundary between high- and low-compressibility soils. (3) The error is only 25.2% relative to the Moreno-Maroto classification chart, and the system tends to classify soils of intermediate nature as clay or silt. The distance between the data points and both the C-line and the new C-line (Delta Ip, Delta IpIc) showed a significant positive correlation. Only one data point was misclassified, considering human error in measuring Ip. (4) The new classification chart has been found to be more applicable to offshore and marine soils.

Background and AimsSoil salinization is a major cause of land degradation and ecological damage. Traditional soil salinity monitoring techniques are limited in coverage and scalability, while remote sensing offers broader applicability and efficiency. This study addresses spatiotemporal variations in soil salt content (SSC) inversion across crop types in Tongliao City, Inner Mongolia, China, using an innovative integration of multi-temporal data and crop cover types, improving remote sensing monitoring accuracy.MethodsField sampling data and Sentinel-2 images from June to September in 2021 and 2022 were utilized. The deep learning U-net model classified key crops, including sunflower (33%), beet (12%), and maize (55%), and analyzed the effects of crop coverage on SSC across multiple time series. Six spectral variables were selected using the SVR-RFE model (R2 = 0.994, MAE = 0.016). SSC prediction models were developed using three machine learning methods (DBO-RF, PSO-SVM, BO-BP) and a deep learning method (Transformer).ResultsConsidering crop coverage variations improved the sensitivity of spectral variables to SSC response, enhancing predictive accuracy and model stability. Crop classification showed that the salinity index (SIs) correlated more strongly with SSC than the vegetation index (VIs), with SI6 having the highest correlation coefficient of 0.50. The Transformer model, using multi-time series data, outperformed other algorithms, achieving an average R2 of 0.71. The SSC inversion map from the Transformer model closely matched field survey trends.ConclusionThis research provides a novel approach to soil salinity prediction using satellite remote sensing, offering a scalable solution for monitoring salinization and valuable insights for environmental management and agricultural planning.

The substantial development of desiccation cracks profoundly impacts the mechanical and hydraulic properties of clayey soils, potentially leading to various engineering challenges such as slope failures. Therefore, identifying the soil's cracking potential is crucial for guiding engineering design and construction processes. The aim of this study was to propose a method for cracking potential classification for clayey soils. To this end, standard cyclic wet-dry tests, capable of maximizing the soil's cracking potential, were proposed based on an analysis of the cracking behavior of lateritic soils under different wet-dry conditions. Subsequently, the cracking characteristics of several typical clayey soils (i.e., lateritic soil, kaolinite, bentonite, and attapulgite) were examined by standard cyclic wet-dry tests. Finally, a novel method for cracking potential classification of clayey soils was proposed incorporating the entropy weighting method. The results show that the most significant degree of cracking in lateritic soil is observed under vacuum saturation and 60 degrees C oven-drying, which is identified as the standard wet-dry condition. When the crack development stabilizes after multiple standard wet-dry cycles, the cracking potential of the soil is characterized by parameters such as the total crack length, maximum crack width, surface crack rate and the fractal dimension of the cracks. On this basis, a classification method is proposed to categorize the cracking potential of clayey soils into five levels: extremely weak, weak, medium, strong, and extremely strong. The cracking potential of different clayey soils was evaluated using this method, revealing that bentonite exhibited the highest cracking potential, classified as extremely strong.

Soil and water conservation structures are vital for environmental resilience but present maintenance challenges due to their wide distribution and remote locations. To tackle these issues, a method using unmanned aerial vehicles (UAVs) combined with 360 degree photography was developed. UAVs captured images that were processed into panoramic and 3D models, enabling precise inspections of structural damage. These models were integrated into the disaster environment review and update (DER&U) rating system, enhanced by a fuzzy inference classification mechanism for improved damage estimation. Additionally, a management platform was created to boost overall efficiency and provide decision-making support for relevant authorities. The UAV-assisted inspection method demonstrated promising results, though certain limitations were also noted.

The Polarimetric Interferometric Synthetic Aperture Radar (PolInSAR) system is a combination of polarimetric SAR and interferometric SAR, which can simultaneously obtain the power information, polarimetric information, and interferometric information of land cover. Traditional land cover classification methods fail to fully utilize these information types, resulting in limited classification types and low accuracy. This paper proposes a PolInSAR land cover classification method that fuses power information, polarimetric information, and interferometric information, aiming to enrich the classification types and improve the classification accuracy. Firstly, the land cover is divided into strong scattering areas and weak scattering areas by using the power information to avoid the influence of weak scattering areas on the classification results. Then, the weak scattering areas are distinguished into shadows and water bodies by combining the interferometric information and image corners. For the strong scattering areas, the polarimetric information is utilized to distinguish vegetation, buildings, and bare soil. For the vegetation area, the concept of vegetation ground elevation is put forward. By combining with the anisotropy parameter, the vegetation is further subdivided into tall coniferous vegetation, short coniferous vegetation, tall broad-leaved vegetation, and short broad-leaved vegetation. The effectiveness of the method has been verified by the PolInSAR data obtained from the N-SAR system developed by Nanjing Research Institute of Electronics Technology. The overall classification accuracy reaches 90.2%, and the Kappa coefficient is 0.876.

The city of A & iuml;n T & eacute;mouchent, located in northwest Algeria at the westernmost part of the Lower Cheliff Basin, has experienced several moderate earthquakes, the most significant of which occurred on 22 December 1999 (Mw 5.7, 25 fatalities, severe damage). In this study, ambient noise measurements from 62 sites were analyzed using the horizontal-to-vertical spectral ratio (HVSR) method to estimate fundamental frequency (f0) and amplitude (A0). The inversion of HVSR curves provided sedimentary layer thickness and shear wave velocity (Vs) estimates. Additionally, four spatial autocorrelation (SPAC) array measurements refined the Rayleigh wave dispersion curves, improving Vs profiles (150-1350 m/s) and sediment thickness estimates (up to 390 m in the industrial zone). Vs30 and vulnerability index maps were developed to classify soil types and assess liquefaction potential within the city.

Floods are considered to be among the most dangerous and destructive geohazards, leading to human victims and severe economic outcomes. Yearly, many regions around the world suffer from devasting floods. The estimation of flood aftermaths is one of the high priorities for the global community. One such flood took place in northern Libya in September 2023. The presented study is aimed at evaluating the flood aftermath for Derna city, Libya, using high resolution GEOEYE-1 and Sentinel-2 satellite imagery in Google Earth Engine environment. The primary task is obtaining and analyzing data that provide high accuracy and detail for the study region. The main objective of study is to explore the capabilities of different algorithms and remote sensing datasets for quantitative change estimation after the flood. Different supervised classification methods were examined, including random forest, support vector machine, na & iuml;ve-Bayes, and classification and regression tree (CART). The various sets of hyperparameters for classification were considered. The high-resolution GEOEYE-1 images were used for precise change detection using image differencing (pixel-to-pixel comparison and geographic object-based image analysis (GEOBIA) for extracting building), whereas Sentinel-2 data were employed for the classification and further change detection by classified images. Object based image analysis (OBIA) was also performed for the extraction of building footprints using very high resolution GEOEYE images for the quantification of buildings that collapsed due to the flood. The first stage of the study was the development of a workflow for data analysis. This workflow includes three parallel processes of data analysis. High-resolution GEOEYE-1 images of Derna city were investigated for change detection algorithms. In addition, different indices (normalized difference vegetation index (NDVI), soil adjusted vegetation index (SAVI), transformed NDVI (TNDVI), and normalized difference moisture index (NDMI)) were calculated to facilitate the recognition of damaged regions. In the final stage, the analysis results were fused to obtain the damage estimation for the studied region. As the main output, the area changes for the primary classes and the maps that portray these changes were obtained. The recommendations for data usage and further processing in Google Earth Engine were developed.

The generation of negative excess pore water pressure (u2) during cone penetration test (CPT) in a given environment represents a deviation from the actual situation, thereby affecting the accuracy of the parameter inversion. Dissipation tests have been conducted to ascertain the dissipation of the u2 over time, which in turn allows for the parameters to be corrected. However, the tip resistance (qc) and sleeve friction resistance (fs) in dissipation process also vary with time, despite its potential impact on the inversion process. In this paper, the evolution of qc and negative u2 with time is successfully obtained through the utilization of indoor CPTs on silt soils. In conjunction with a viscoelastic model, the existence of stress relaxation of qc is demonstrated and the causes of qc decay are analyzed. The detailed conclusions are as follows: (1) The CPT parameters obtained from the dissipation test can be employed to rectify the discrepancy in negative u2 that arises during soil classification. (2) The qc undergoes a gradual decrease, reaching a final equilibrium state during the dissipation process. The stress-time relationship is consistent with the Three-element viscoelasticity model, which represents a stress relaxation phenomenon. The relaxation process can be divided into three distinct phases: fast relaxation, decelerating relaxation, and residual relaxation. The residual stress is found to be correlated with the depth of the soil layer. (3) During residual phase, the loss rate of qc is observed to decrease in a linear fashion with the rate of u2, prior to which the relationship is exponential. As the penetration rate increases, the rate of u2 also increases.