In the present study transcriptone sequencing and RT-PCR detection of leaf sample of Commelina communis L. were investigated. A diseased leaf sample was selected for transcriptome sequencing and two contigs with lengths of 5845 and 3450 nucleotides (nt) were obtained. They were confirmed by RT-PCR with seven pairs of primers, and RNA1 and RNA2 (GenBank MZ571836 and MZ571837) were determined to be 5880 nt and 3478 nt, respectively. Homology analysis and evolutionary relationship analysis showed the highest homology with BBWV2 (MN786954 and MN786955), for 97.5 and 88.4% at the nt and amino acid (aa) levels, respectively. This is the first report of BBWV2 infection in C. communis in the world. Specific primers R2-2F/R were used to assess the association of BBWV2 with C. communis disease, and positive fragments were obtained only in the diseased plants, indicating the association of BBWV2 with the disease. Bangladesh J. Bot. 52(2): 569-574, 2023 (June) Special

To address the current issues in soil organic carbon (SOC) content prediction where data preprocessing relies on expert experience to formulate fixed rules, resulting in a lack of uniform standards and insufficient consideration of regional soil heterogeneity; while hyperparameter tuning faces problems of high computational costs and excessively long runtimes, this study proposes an intelligent modeling workflow driven by Large Language Models (LLM). This workflow focuses on optimizing two key aspects of SOC Random Forest modeling: data preprocessing and hyperparameter tuning. Results: The LLM-defined rules achieved sample retention rates of 55.33% and 61.90% in the two regions, respectively, showing more significant differences compared to traditional hard-coded rules (56.2% and 59.3%), and the mean soil organic carbon content deviations (30.27% and 20.05%) were both lower than those of traditional hard-coding. At the same time, the mean soil organic carbon content values in both regions closely matched the effectiveness of other methods, indicating that the large language model has effectively captured regional soil differences. With only a single evaluation of hyperparameter optimization, the adaptive model achieved test set R² values of 0.394 and 0.694 in the black soil region and the aeolian sandy soil region, respectively, with root mean square error values of 8.76 g/kg and 6.07 g/kg—its performance is comparable to that of Grid Search and Random Search, while computational efficiency improved by over 95%. Performance comparisons with eXtreme Gradient Boosting (XGBoost) and Partial Least Squares Regression (PLSR) show that the LLM-optimized Random Forest achieved R² = 0.394 and RMSE = 8.76 g/kg in the black soil region, and R² = 0.694 and RMSE = 6.07 g/kg in the windblown sandy soil region, demonstrating practical application value.

Understanding the vertical heterogeneity of soil organic carbon (SOC) and its non-linear regulation is essential for predicting terrestrial C feedback to climate change. We integrated a national gridded SOC dataset for China with harmonized environmental covariates to assess SOC at three depth intervals (0–30, 30–60, and 60–100 cm). Random forest models were used to quantify depth-specific predictor importance, and segmented regressions were applied to identify candidate breakpoints in selected SOC–environment relationships. SOC displayed a “high periphery–low center” distribution pattern, with accumulation hotspots in the cold northeast and alpine southwest. Vertically, SOC mainly accumulated in the 0–30 cm layer, showing a pronounced decrease as soil depth increased. Although total nitrogen consistently exhibited high predictive importance, the relative contributions of other environmental controls changed with depth: soil texture exerted greater influence in topsoil, whereas pH and hydroclimatic conditions became increasingly important in subsoil. SOC responses to pH, mean annual temperature, mean annual precipitation, clay content, and sand content were distinctly nonlinear and frequently differed among depth intervals. Candidate breakpoints were identified at approximately pH 6.8–7.2, a mean annual temperature of 18.0 °C, and a mean annual precipitation of 55.33 cm, while texture-related breakpoints showed greater depth dependence. These patterns are consistent with depth-dependent differences in carbon–nitrogen coupling, mineral-associated protection, moisture limitation, and temperature-related decomposition. By resolving how SOC controls vary among soil depths and environmental regions, this study provides a basis for region- and depth-specific soil carbon assessment and management in China.

Soil organic carbon (SOC) is a key indicator of cropland quality, soil fertility, and the carbon sequestration potential of agroecosystems. Accurate characterization of its spatial distribution is essential for black soil conservation and regional soil carbon management. However, regional-scale SOC prediction is often constrained by limited field observations, which can reduce model generalizability and predictive reliability. In this study, we developed a limited-sample SOC prediction framework for the Liaohe Plain using 310 surface (0–20 cm) soil samples collected in 2025 and multi-source environmental covariates, including climate, vegetation, soil spectral, and terrain variables. The framework used the Tabular Prior-Data Fitted Network (TabPFN), whose performance was compared with that of Random Forest, Support Vector Machine, CatBoost, K-Nearest Neighbors, and XGBoost. Model performance was evaluated using 100 repetitions of random 80:20 holdout validation and repeated five-fold spatial cross-validation based on spatially constrained clustering, while sampling-induced relative uncertainty was quantified using 100 repeated random sampling and model-fitting runs. Under random holdout validation, TabPFN showed competitive predictive performance, with mean R² and RMSE values of 0.608 ± 0.038 and 4.026 ± 0.184 g kg⁻¹, respectively. Repeated spatial cross-validation yielded more conservative performance estimates, with mean R² and RMSE values of 0.535 ± 0.072 and 4.33 ± 0.31 g kg⁻¹, respectively, indicating that random splitting may overestimate model performance when sampling sites are spatially clustered. Spatial prediction showed that cropland SOC ranged from 4.63 to 27.04 g kg⁻¹, with generally lower values in the west and higher values in the northeast. Areas with high sampling-induced relative uncertainty were mainly concentrated in the northern, northeastern, and marginal regions. These findings provide a methodological basis for SOC mapping, supplementary sampling optimization, and regional soil carbon management under limited-sample conditions, although the temporal robustness of the results requires confirmation using independent data from additional years.