Scientific Research Journal CIDI

Evolution of Deep Learning models for forecasting flow rates in basins, 2026

Thu, 09 Apr 2026 00:00:00 +0000

Flow forecasting is a crucial tool for water resource management, flood risk reduction, and hydraulic system planning. In recent decades, forecasting techniques have advanced from physical and conceptual hydrological models to data-driven methods, with a particularly strong focus on Machine Learning (ML) and Deep Learning (DL) techniques. This review explores the evolution of deep learning models applied to the estimation, calculation, and prediction of river flows in watersheds to date. Numerous methodological advances, model structures, data requirements, and evaluation criteria used in recent studies have been presented.

Special emphasis is placed on hybrid and deep architectures, such as Deep Belief Networks (DBN), Artificial Neural Networks (ANN), Support Vector Regression (SVR), and Wavelet Artificial Neural Networks (WANN). The results of this research indicate that traditional machine learning methods are very effective for short-term forecasts, while hybrid models are more efficient at capturing non-linearity over longer time horizons. Finally, current challenges are addressed, such as data scarcity, model interpretability, and uncertainty assessment, as well as new trends including physics-guided neural networks, graph neural networks, and mutable architectures.

Distribution, Seasonal Variability, and Bioaccumulation of Heavy Metals in Water, Sediments, and Vegetation in Pueblo Nuevo Lircay, Huancavelica

Wed, 22 Apr 2026 00:00:00 +0000

The present study evaluated the spatial distribution, seasonal variability, and relationships among concentrations of arsenic (As), cadmium (Cd), lead (Pb), and zinc (Zn) in surface water, sediments, and vegetation within a mining-influenced high-Andean area in Huancavelica, Peru. A quantitative approach was applied using a non-experimental longitudinal design, comparing two sampling campaigns: the rainy season (March 2025) and the dry season (August 2025).
The results revealed a differential behavior among environmental matrices. In water, Zn showed the highest exceedances relative to environmental quality standards during the dry season, associated with concentration processes due to reduced flow. In sediments, As reached the highest concentrations, particularly in the lagoon, confirming its role as a geochemical sink. Vegetation exhibited the strongest signal of environmental impact, with significant bioaccumulation of metals and exceedance of maximum tolerable values, especially for Cd and Pb.
It is concluded that the dynamics of heavy metals are strongly modulated by seasonality and the interaction among environmental matrices, highlighting the need for multicompartment monitoring in mining-influenced areas.

Editorial for the Journal 2026-I

Manuel Alberto Luis Manrique-Nugent — Mon, 05 Jan 2026 00:00:00 +0000

Science does not advance merely through the accumulation of data, but through humanity’s ability to question, create, and share knowledge with purpose. At the beginning of the 2026 academic year, scientific research takes on an even more strategic role in the face of the social, technological, and environmental challenges confronting our societies. Publishing today is an act of intellectual responsibility and a direct contribution to sustainable development and collective well-being.

At Scientific Research Journal CIDI, we view scientific dissemination as a living bridge between theory and practice, between academia and society. During this first semester of 2026, we renew our commitment to strengthening an inclusive, rigorous, and open editorial space for researchers, teachers, and students who seek to give visibility to their contributions and generate real impact in their communities and beyond.