This study presents an analysis of three models associated with artificial intelligence as tools to forecast the generation of urban solid waste in the city of Bogotá, in order to learn about this type of waste's behavior. The analysis was carried out in such a manner that different efficient alternatives are presented. In this paper, a possible decision-making strategy was explored and implemented to plan and design technologies for the stages of collection, transport and final disposal of waste in cities, while taking into account their particular characteristics. The first model used to analyze data was the decision tree which employed machine learning as a non-parametric algorithm that models data separation limitations based on the learning decision rules on the input characteristics of the model. Support vector machines were the second method implemented as a forecasting model. The primary advantage of support vector machines is their proper adjustment to data despite its variable nature or when faced with problems with a small amount of training data. Lastly, recurrent neural network models to forecast data were implemented, which yielded positive results. Their architectural design is useful in exploring temporal correlations among the same. Distribution by collection zone in the city, socio-economic stratification, population, and quantity of solid waste generated in a determined period of time were factors considered in the analysis of this forecast. The results found that support vector machines are the most appropriate model for this type of analysis.

The development of methodologies to support decision-making in municipal solid waste (MSW) management processes is of great interest for municipal administrations. Artificial intelligence (AI) techniques provide multiple tools for designing algorithms to objectively analyze data while creating highly precise models. Support vector machines and neuronal networks are formed by AI applications offering optimization solutions at different managing stages. In this paper, an implementation and comparison of the results obtained by two AI methods on a solid waste management problem is shown. Support vector machine (SVM) and long short-term memory (LSTM) network techniques have been used. The implementation of LSTM took into account different configurations, temporal filtering and annual calculations of solid waste collection periods. Results show that the SVM method properly fits selected data and yields consistent regression curves, even with very limited training data, leading to more accurate results than those obtained by the LSTM method.

Flood modelling in snow-fed river basins is critical for understanding the impacts of climate change on hydrological extremes. The Zhabay River in northern Kazakhstan exemplifies a basin highly vulnerable to seasonal floods, which pose significant risks to infrastructure, livelihoods, and water resource management. Traditional flood forecasting in Central Asia still relies on statistical models developed during the Soviet era, which are limited in their ability to incorporate non-stationary climate and anthropogenic influences. This study addresses this gap by applying the Soil and Water Integrated Model (SWIM) to project climate-driven changes in the hydrological regime of the Zhabay River. The study employs a process-based, high-resolution hydrological model to simulate flood dynamics under future climate conditions. Historical hydrometeorological data were used to calibrate and validate the model at the Atbasar gauge station. Future flood scenarios were simulated using bias-corrected outputs from an ensemble of General Circulation Models (GCMs) under Representative Concentration Pathways (RCPs) 4.5 and 8.5 for the periods 2011–2040, 2041–2070, and 2071–2099. This approach enables the assessment of seasonal and interannual variability in flood magnitudes, peak discharges, and their potential recurrence intervals. Findings indicate a substantial increase in peak spring floods, with projected discharge nearly doubling by mid-century under both climate scenarios. The study reveals a 1.8-fold increase in peak discharge between 2010 and 2040, and a twofold increase from 2041 to 2070. Under the RCP 4.5 scenario, extreme flood events exceeding a 100-year return period (2000 m³/s) are expected to become more frequent, whereas the RCP 8.5 scenario suggests a stabilization of extreme event occurrences beyond 2071. These findings underscore the growing flood risk in the region and highlight the necessity for adaptive water resource management strategies. This research contributes to the advancement of climate-resilient flood forecasting in Central Asian river basins. The integration of process-based hydrological modelling with climate projections provides a more robust framework for flood risk assessment and early warning system development. The outcomes of this study offer crucial insights for policymakers, hydrologists, and disaster management agencies in mitigating the adverse effects of climate-induced hydrological extremes in Kazakhstan.

This paper provides a detailed description of the findings and methodology related to the monitoring of microplastics in three lakes and one river of the Akmola Region in Kazakhstan. The concentration of microplastic particles and the analysis of water and sediment quality of the Yesil River and Kopa, Zerendinskoye, and Borovoe lakes have been analyzed. A total of 64 water samples were collected across the spring, summer, and autumn seasons, with subsequent analysis revealing a seasonal increase in microplastic concentrations. The average microplastic content ranged from 1.2 × 10⁻¹ particles/dm³ in spring to 4.5 × 10⁻¹ particles/dm³ in autumn. Lakes exhibited higher concentrations compared to the Yesil River. Correlation analysis highlighted a connection between microplastic content and turbidity, particularly notable during the spring season. Analysis of sediments revealed a decrease in microplastic concentrations from the coastal zone toward open waters sediments. Microplastic fibers were predominant in sediments (69.6%), followed by fragments (19.1%), films (7.4%), and granules (3.9%). Larger particles (>500 µm) were found in beach sediments, constituting an average of 40.5% of the total plastics found. This study contributes valuable insights into the spatial and temporal distribution of microplastics, emphasizing the need for ongoing monitoring and management strategies to address this environmental concern.