The soil packing, influenced by variations in grain size and the gradation pattern within the soil matrix, plays a crucial role in constituting the mechanical properties of sandy soils. However, previous modeling approaches have overlooked incorporating the full range of representative parameters to accurately predict the soaked California bearing ratio (CBRs) of sandy soils by precisely articulating soil packing in the modeling framework. This study presents an innovative artificial intelligence (AI)-based approach for modeling the CBRs of sandy soils, considering grain size variability meticulously. By synthesizing extensive data from multiple sources, i.e. extensive tailored testing program undertaking multiple tests and extant literature, various modeling techniques including genetic expression programming (GEP), multi-expression programming (MEP), support vector machine (SVM), and multi-linear regression (MLR) are utilized to develop models. The research explores two modeling strategies, namely simplified and composite, with the former incorporating only sieve analysis test parameters, while the latter includes compaction test parameters alongside sieve analysis data. The models' performance is assessed using statistical key performance indicators (KPIs). Results indicate that genetic AI-based algorithms, particularly GEP, outperform SVM and conventional regression techniques, effectively capturing complex relationships between input parameters and CBRs. Additionally, the study reveals insights into model performance concerning the number of input parameters, with GEP consistently outperforming other models. External validation and Taylor diagram analysis demonstrate the GEP models' superiority over existing literature models on an independent dataset from the literature. Parametric and sensitivity analyses highlight the intricate relationships between grain sizes and CBRs, further emphasizing GEP's efficacy in modeling such complexities. This study contributes to enhancing CBRs modeling accuracy for sandy soils, crucial for pertinent infrastructure design and construction rapidly and cost-effectively. (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/).

Blueberries are the most popular small berries, in order to solve the problem of unbalanced blueberry resources in different regions of China. In this study, 18 blueberries were analyzed by chromatography and mass spectrometry for 9 soil elements, 6 anthocyanins, 7 phenolic acids, 9 organic acids, and 12 flavonoids. The result showed that blueberry physico-chemical indicators were significantly variable across production regions by Wenn and volcano maps, chlorogenic acid, ascorbic acid, citric acid, catechin were the main antioxidant active components, soil pH was significantly correlated with low content of anthocyanins and organic acids, soil elements were not significantly correlated with fruits antioxidant activity by the network correlation analysis. Cluster analysis and principal component analysis classified the antioxidant activity and fruit quality: represented by YNorthland, SNorthland, JSharpblue. It provides theoretical support for screening high quality blueberries and promoting the development of blueberry industry.

The soil matrix, salt crystals, ice crystals, and pore solutions constitute the composite geological material of saturated saline frozen soil. The destruction mode and dynamic constitutive model of saturated saline frozen soil need to be studied because infrastructure construction is increasingly being extended to regions with saturated saline frozen soil. Based on the split Hopkinson pressure bar device, uniaxial impact compression tests were conducted on frozen soil samples with different salt contents under different strain rates. The strain rate of saturated saline frozen soil must be emphasized based on the results. The gradient of the elastic segment and maximum stress of the soil are negatively correlated with the salt content increase. To further explore the failure mechanism, the study examined the damage and failure behavior of saturated saline frozen soil, along with the absorption energy in the failure process. According to the test results, the saturated saline frozen soil was similar to a particle-reinforced composite. Subsequently, the debonding damage of the ice-salt eutectic and the mechanical-chemical damage of the soil matrix were considered. The test results could be predicted accurately from the results of the model, verifying that the influences of the salt content and strain rate are reasonably considered by the constructed model.