Moisture accumulation within road pavements, particularly in unbound granular materials with or without thin sprayed seals, presents significant challenges in high-rainfall regions such as Queensland. This infiltration often leads to various forms of pavement distress, eventually causing irreversible damage to the pavement structure. The moisture content within pavements exhibits considerable dynamism and directly influenced by environmental factors such as precipitation, air temperature, and relative humidity. This variability underscores the importance of monitoring moisture changes using real-time climatic data to assess pavement conditions for operational management or incorporating these effects during pavement design based on historical climate data. Consequently, there is an increasing demand for advanced, technology-driven methodologies to predict moisture variations based on climatic inputs. Addressing this gap, the present study employs five traditional machine learning (ML) algorithms, K-nearest neighbors (KNN), regression trees, random forest, support vector machines (SVMs), and gaussian process regression (GPR), to forecast moisture levels within pavement layers over time, with varying algorithm complexities. Using data collected from an instrumented road in Brisbane, Australia, which includes pavement moisture and climatic factors, the study develops predictive models to forecast moisture content at future time steps. The approach incorporates current moisture content, rather than averaged values, along with seasonality (both daily and annual), and key climatic factors to predict next step moisture. Model performance is evaluated using R2, MSE, RMSE, and MAPE metrics. Results show that ML algorithms can reliably predict long-term moisture variations in pavements, provided optimal hyperparameters are selected for each algorithm. The best-performing algorithms include KNN (the number of neighbours equals to 15), medium regression tree, medium random forest, coarse SVM, and simple GPR, with medium random forest outperforming the others. The study also identifies the optimal hyperparameter combinations for each algorithm, offering significant advancements in moisture prediction tools for pavement technology.

Permafrost temperature is a vital indicator of climate and permafrost changes, benefiting ecosystem development and informing local climate strategies. Alpine grasslands impact moisture and heat exchange between the surface and atmosphere, thereby affecting the thermal state of underlying permafrost. This study analyzed permafrost temperatures (2004-2019) from various alpine grasslands (including alpine meadow, alpine steppe, alpine desert grassland, and barren land) in the Beiluhe region of the Tibetan Plateau and revealed their connections to climate change and controlling factors, using time-frequency analysis. The findings revealed that in the time-frequency domain, permafrost temperatures exhibited multiple time scales characteristics, driven by climate fluctuations. Changes in the active layer closely followed monthly climate variations, while permafrost dynamics responded to annual climate changes. Significant oscillations with periods of 10-11, 8-9, and 14 years were observed in the surface, permafrost table, and deep permafrost layers, respectively. Among the different types of alpine grasslands, alpine meadows proved to be the most sensitive to climate change, with the intensity of periodic fluctuations initially decreasing and then increasing with depth in alpine meadows, while it consistently decreased with depth in the other three alpine grasslands. The impact of air temperature, precipitation, and wind speed on permafrost dynamics exhibited depth-dependent variations in the time-frequency domain, contrasting with the time domain where permafrost temperature changes were predominantly associated with air temperature across all depths.

Soil is an irreplaceable natural resource, with irreplaceable ecosystem functions. One of the greatest risks of soil degradation in the Czech Republic is accelerated erosion, which causes numerous damages to soil properties with negative impacts on the environment. The climate development in recent decades and its forecasts may further intensify these processes. This article deals with the analysis of the impacts of changes in selected climatic factors on the development of erosion processes, which in the conditions of the Czech Republic are influenced mainly by the development of precipitation in the growing season and the development of the values of erosion potential of water released by snowmelt in the winter (non -growing) period. The analysis was carried out on a total area of 459.5 km2, in different morphological and climatic conditions. The impact of climate change was assessed using historical and updated values of rain erosivity and snow erosion potential factors. The results show an increase in the risk of erosive loss in the growing season for all the analysed areas, while the values of erosive loss in the non -growing period differ from each other depending on the climatic and morphological conditions of the areas under study.