This study presents a comprehensive mathematical forecasting approach for hydroecological parameters in small urban river systems using an integrally-modified Streeter-Phelps model. The research focuses on the Kamyanka River, a small tributary within Zhytomyr city, Ukraine, which experiences significant anthropogenic influence from urban development. The modified model incorporates advanced computational algorithms implemented in Python programming environment to predict dissolved oxygen concentration and biochemical oxygen demand dynamics over a 25-year period (2020-2045). Model verification using observational data from 2020-2023 demonstrated high accuracy with R²=0.87 and root mean square deviation of ±0.2 mg/L for dissolved oxygen predictions. The results reveal a positive trend in oxygen regime optimization, with dissolved oxygen concentrations projected to increase from 8.5 mg/L to 11.0 mg/L, while biochemical oxygen demand is expected to decrease from 4.0 to 3.0 mg O₂/L. Statistical analysis confirmed model reliability through Nash-Sutcliffe efficiency coefficient (NSE = 0.84) and cross-validation metrics (R²ᶜᵛ = 0.83). The developed forecasting system provides robust framework for environmental management and supports long-term planning strategies for ecological rehabilitation of urbanized river ecosystems.
Document Layout Analysis (DLA) is a critical step in intelligent document processing and is essential for accurately reconstructing the hierarchical structure of pages. While modern convolutional neural networks exhibit high performance, their effectiveness heavily depends on the quality and representativeness of training data, limiting their application in scenarios where labeled datasets are scarce. This paper proposes a method for enhancing DLA through synthetic generation of training data. A formalized mathematical model for generating document layouts has been developed, allowing control over element placement density, sizes, and spatial distribution. An experimental study investigated the impact of various data generation strategies on the training of the YOLO11m model, including median and threshold-based element splitting as well as different block sampling schemes. The experiments showed that employing median element splitting combined with random sampling from a large shuffled pool of synthetic data yields consistent improvements of 2–4% across all key metrics: precision, recall, mAP@50, and mAP@50:95, as compared with simple data generation strategies. These results demonstrate that targeted optimization of the data preparation process can enhance the performance of convolutional models in DLA tasks without increasing architectural complexity. The practical applicability of the method is validated through integration into the MinerU system. Future research will focus on extending the proposed model to complex layouts in scientific journals, technical reports, and handwritten documents.