Lyazat Naizabayeva

Scopus Publications

Air Pollution Forecasting in Almaty using Ensemble Machine Learning Models
Lyazat Naizabayeva
Journal of Applied Data Sciences, 2025
This study develops an advanced forecasting methodology for air pollution levels in Almaty, Kazakhstan, focusing on fine Particulate Matter (PM2.5) and carbon monoxide concentrations. Air pollution poses significant risks to public health, and Almaty’s basin location exacerbates the problem. Addressing the limitations of traditional statistical forecasting methods, we propose an ensemble machine learning approach that integrates Seasonal-Trend decomposition with gradient boosting algorithms to capture complex temporal and nonlinear patterns. The objective is to develop and validate an effective methodology for forecasting atmospheric air pollution in Almaty using machine learning methods, in particular STL decomposition, XGBoost, LightGBM models, and their ensemble combination. The novelty lies in the integration of STL decomposition with an ensemble of gradient boosting models for high-accuracy air pollution forecasting in the complex urban environment of Almaty. The dataset includes hourly measurements from over 20 monitoring stations, enabling seasonal and spatial analysis. Rigorous preprocessing techniques were applied, including outlier removal, normalization, and time series decomposition into seasonal, trend, and residual components. Two gradient boosting models, XGBoost and LightGBM, were trained separately and combined into a weighted ensemble, with optimal weights determined through cross-validation. Figures and tables illustrate data preprocessing flow, model architectures, feature importance analysis, and evaluation of predictive performance. The ensemble outperformed individual models, achieving high accuracy with coefficient of determination values exceeding 0.98 for PM2.5 and 0.83 for carbon monoxide. The findings demonstrate that integrating Seasonal-Trend decomposition with ensemble learning provides a robust and effective approach to forecasting air pollution in complex urban environments. The methodology shows strong potential for practical application in real-time air quality monitoring and warning systems, aiding policymakers and public health authorities. Future research will expand the dataset by incorporating additional factors such as traffic flow, industrial emissions, and satellite remote sensing data to enhance predictive accuracy and model interpretability.
Hybrid Physics–Machine Learning Framework for Forecasting Urban Air Circulation and Pollution in Mountain–Valley Cities
Lyazat Naizabayeva, Gulbakyt Sembina, Gulnara Tleuberdiyeva
Applied Sciences Switzerland, 2025
Background: Almaty, located in a mountain–valley basin, frequently experiences stagnant conditions that trap pollutants and cause sharp diurnal contrasts in air quality. Current forecasting systems either offer detailed physical realism at high computational cost or yield statistically accurate but physically inconsistent results. Urban air quality in mountain–valley cities is strongly shaped by thermal inversions and weak nocturnal ventilation that trap pollutants close to the surface. We present a hybrid physics–machine-learning framework that combines a Navier–Stokes surface-layer model with data-driven post-processing to produce short-term forecasts of wind, temperature, and particulate matter while preserving physical consistency. The approach captures diurnal ventilation patterns and the well-known negative linkage between near-surface wind and particulate loadings during wintertime inversions. Compared with purely statistical baselines, the hybrid system improves short-range forecast skill and maintains interpretability through physically grounded diagnostics. Beyond Almaty, the workflow is transferable to other mountain–valley environments and is directly actionable for early warning, traffic and heating-related emission management, and health-risk communication. By uniting physically meaningful fields with lightweight Machine Learning correction, the method offers a practical bridge between computational fluid dynamics and operational decision support for cities facing recurrent stagnation episodes. Aim: Develop and verify a method for the diagnostics and short-term forecasting of surface circulation and particle concentrations in Almaty (2024), ensuring physical consistency of fields, increased forecast accuracy on 6–24 h horizons, and interpretability of risk factors. Compared to purely statistical baselines (R2 ≈ 0.55 for PM forecasts), our hybrid framework achieved a 16% gain in explained variance and reduced RMSE by 25%. This improvement was most evident during winter inversion episodes. Methods: This study introduces a hybrid modeling framework that integrates the Navier–Stokes equations with machine-learning algorithms to diagnose and forecast surface air circulation and particulate matter concentrations. The approach ensures both physical consistency and improved predictive accuracy for short-term horizons (6–24 h). The Navier–Stokes equations in the Boussinesq approximation, the energy equation, and K-closure particulate matter transport were used. The numerical solution is based on the projection method (convection—TVD/QUICK, pressure—Poisson equation). The ML module is gradient boosting and decision trees for meteorological parameters, lags, and diagnostic quantities. The 2024 data are cleaned, normalized, and visualized. Results: The hybrid model reproduces the diurnal cycle of ventilation and concentrations, especially during winter inversions. For 6 h: wind RMSE ≈ 1.2 m/s (R2 ≈ 0.71), temperature RMSE ≈ 1.8 °C (R2 ≈ 0.78), and particles RMSE ≈ 0.012 mg/m3 (R2 ≈ 0.64). Errors are higher for 24 h. A negative relationship between wind and concentration was established: +1 m/s reduces the median by 10–15% during winter nights. Conclusions: The approach can be generalized to other mountain–valley cities beyond Almaty. Combining the physical model and ML correction improves short-term predictive ability and maintains physical consistency. The method is applicable for air quality risk assessment and decision support; further clarification of emissions and consideration of urban canyon geometry are required. The results support early-warning systems, health risk communication, and urban planning.
Simulation-Based Assessment of Urban Pollution in Almaty: Influence of Meteorological and Environmental Parameters
Lyazat Naizabayeva, Kateryna Kolesnikova, Victoriia Khrutba
Applied Sciences Switzerland, 2025
Background: Air pollution is a persistent and critical challenge for Almaty, Kazakhstan’s largest city. The city’s unique topographical and meteorological conditions—being located in a mountain basin with dense urban development—restrict natural ventilation and contribute to frequent exceedances of air quality standards. These factors make accurate assessment and management of atmospheric pollution particularly urgent for the region. Aim: This study aims to develop and apply a novel, high-resolution three-dimensional numerical model to analyze the spatial distribution of key atmospheric indicators—air velocity, temperature, and pollutant concentrations in Almaty. The goal is to provide a comprehensive understanding of how meteorological and urban factors influence air quality, with a focus on both horizontal and vertical stratification. Methods: A three-dimensional computational model was constructed, integrating real meteorological data and detailed urban topography. The model solves the compressible Navier–Stokes, energy, and pollutant transport equations using the finite volume method over a 1000 × 1000 × 500 m domain. Meteorological fields are synthesized along all spatial axes to account for vortex structures, urban heat islands, and stratification effects. This approach enables the simulation of atmospheric parameters with unprecedented spatial resolution for Almaty. Results: The simulation reveals significant spatial heterogeneity in atmospheric parameters. Wind velocity ranges from 0.31 to 5.76 m/s (mean: 2.14 m/s), temperature varies between 12.03 °C and 19.47 °C (mean: 16.12 °C), and pollutant concentrations fluctuate from 5.02 to 102.35 μg/m3 (mean: 44.87 μg/m3). Notably, pollutant levels in the city center exceed those at the periphery by more than two-fold (68.23 μg/m3, 29.14 μg/m3), and vertical stratification leads to a marked decrease in concentrations with altitude. These findings provide, for the first time, a comprehensive and quantitative picture of air quality dynamics in Almaty. Conclusion: The developed model advances the scientific understanding of urban air pollution in complex terrains and offers practical tools for city planners and policymakers. By identifying pollution hotspots and elucidating the influence of meteorological factors, the model supports the optimization of urban infrastructure, zoning, and environmental monitoring systems. This research lays the groundwork for evidence-based strategies to mitigate air pollution and improve public health in Almaty and similar urban environments.
Integrating statistical analysis into everyday business operations using mobile technologies
Ceur Workshop Proceedings, 2025
SIMULATING URBAN CLIMATE AND AIR POLLUTION IN ALMATY: A NUMERICAL MODELING APPROACH
L. K. Naizabayeva, V. O. Khrutba, G. I. Tleuberdiyeva
Herald of the Kazakh British Technical University, 2025
The aim of this study is to analyze the spatial and temporal distribution of temperature and air pollutant concentration in the urban atmosphere of Almaty using numerical modeling techniques. A two-dimensional advection-diffusion model was developed to simulate the diurnal dynamics across a territory of approximately 80 square kilometers. The model incorporates key physical processes such as wind-driven transport, turbulent diffusion, and localized emission sources that are typical of dense urban environments. Simulation results demonstrate a smoother spatial distribution of temperature, largely driven by solar radiation cycles, in contrast to highly localized peaks in pollutant concentrations associated with anthropogenic activities such as transportation and industry. These contrasting behaviors highlight the need for differentiated mitigation strategies. The findings of the study offer important insights for urban planning and the development of effective air quality management policies. The proposed model provides a practical tool for understanding environmental dynamics and evaluating the potential impact of pollution control measures in complex urban terrains.
Analysis of Meteorological and Soil Parameters for Predicting Ecosystem State Dynamics
Lyazat Naizabayeva, Saberikamarposhti Morteza, Nurgul Seilova
IEEE Access, 2025
This study presents a comprehensive quantitative analysis of the interplay between meteorological variables and soil conditions over the period 2018–2023 in the Almaty region. The investigation is grounded in high-resolution meteorological observations encompassing air temperature (mean annual variations ranging from −5°C to +30°C), atmospheric pressure (average values between 681 and 685 hPa), and wind velocity (0.5–12 m/s). Additionally, a systematic evaluation of soil characteristics was conducted to assess seasonal fluctuations in soil composition and physicochemical properties across spring, summer, and autumn. By employing advanced statistical methodologies, significant correlations between meteorological dynamics and soil parameters were elucidated. The findings reveal that the most pronounced deviations in soil conditions occur during the spring season, exhibiting a deviation coefficient of 0.7896, whereas the summer season demonstrates the most substantial negative deviation at -0.9566. Furthermore, the predictive model developed within this study exhibits high precision, yielding a coefficient of determination (R2) of 0.85, thereby enabling not only the real-time assessment of ecosystem status but also the reliable forecasting of its temporal evolution. The novelty of this research lies in the integration of classical Navier-Stokes equations with contemporary big data analytics, facilitating a sophisticated representation of atmospheric flow dynamics and their consequential impact on soil properties. This interdisciplinary approach enhances the accuracy of predictive environmental modeling, offering a robust framework for ecosystem monitoring and management.
Biochar as a tool to optimise Miscanthus sinensis resilience and phytoremediation efficiency: Case study of contamination by mixture of Ni and 4.4′-DDE
Asil Nurzhanova, Valentina Pidlisnyuk, Asiya Nurmagambetova, Zhadyra Zhumasheva, Lyazat Naizabayeva, Aigerim Mamirova
Environmental Chemistry and Ecotoxicology, 2025
This study investigated the effects of 1 % commercial sewage sludge-based biochar on the physiological, biochemical, and phytoremediation parameters of Miscanthus sinensis And. ( M. sinensis ) under greenhouse conditions. Biochar was applied to soils subjected to mono- and combined contaminations involving 4.4′-DDE and Ni ions. Biochar incorporation led to (a) a significant increase in plant yield (up to 121 %), (b) enhanced free proline (up to 366 %) and total protein content (up to 135 %), (c) increased levels of the auxiliary pigment chlorophyll b (up to 154 %), (d) partially restored electron transport in photosystem II (up to 36.9 %), and (e) reduced antioxidant enzyme activity in M. sinensis leaves. However, when applied to control soil, biochar induced plant stress, highlighting its suitability primarily for contaminated environments. Post-vegetation analysis confirmed that biochar sorbed Ni and Cr ions from the soil, desorbed Cu and Zn, and had no effect on Pb across all treatments. Furthermore, biochar incorporation significantly reduced plant uptake of 4.4′-DDE, decreasing its bioavailability by 38.9 % and 59.1 % under combined and mono-DDE contamination, respectively, compared to the respective unamended treatments. Under combined contamination, biochar exhibited selective sorption activity, enhancing 4.4′-DDE adsorption while reducing Ni ion retention, indicating that Ni stabilisation depends on both biochar properties and the nature of contamination. Additionally, biochar’s ability to desorb Cu and Zn suggests its potential use in agricultural soils with Cu and/or Zn deficiencies. These findings underscore biochar’s dual role in promoting M. sinensis growth and reducing pollutant bioavailability, demonstrating its potential to enhance the phytoremediation of complexly contaminated soils. • 1 % SSB enhanced M. sinensis biomass under organic and complex soil contamination. • SSB negatively affected M. sinensis morpho-physiology in non-spiked control soil. • SSB showed higher affinity for organic contaminants in complex contamination. • Due to biochar selectivity, Ni adsorption under complex contamination was inhibited. • To validate suitability of biochar in pot trials, granular particles are required.
Integrating Smart Traffic Systems with Real-Time Air Quality Monitoring to Minimize Emissions and Improve Urban Health
Lyazat Naizabayeva, Daniyar Zaitov, Nurgul Seilova
Procedia Computer Science, 2024
This article explores the integration of AI-driven adaptive traffic management systems with real-time air quality monitoring as a novel solution for reducing air pollution in Almaty, Kazakhstan. Utilizing advanced artificial intelligence algorithms and Internet of Things (IoT) sensors, the proposed system dynamically adjusts traffic signals and reroutes vehicles based on real-time data on traffic density, vehicle emissions, and environmental conditions. The study involves the creation of a simulated dataset to train and evaluate the performance of artificial neural networks (ANNs) and long short-term memory (LSTM) networks in predicting PM2.5 levels. Results indicate that the ANN model outperforms the LSTM model, demonstrating lower loss and mean absolute error (MAE), making it highly effective for real-time traffic management applications. Despite using simulated data, the study underscores the potential benefits of acquiring actual data for further validation. The findings highlight the significance of AI-driven solutions in urban planning, offering scalable strategies to improve air quality and urban health in cities facing similar challenges.
Use the neural networks in prediction of environmental processes
Kateryna Kolesnikova, Lyazat Naizabayeva, Ayaulym Myrzabayeva, Rostyslav Lisnevskyi
Sist 2024 2024 IEEE 4th International Conference on Smart Information Systems and Technologies Proceedings, 2024
Forecasting environmental phenomena using neural networks has become increasingly popular due to their ability to analyze complex datasets and provide accurate predictions. In this paper, we investigate the application of neural networks in predicting environmental processes, focusing specifically on their use in forecasting greenhouse gas emissions. We examine several types of neural networks, including recurrent neural networks (RNNs) such as Simple RNN, LSTM-RNN, and stacked LTSM-RNN, to assess their effectiveness in handling raw data and projecting emissions over different spatial and temporal scales. The study demonstrates that the Simple RNN model is highly accurate in outlier prediction. Moreover, the consistency of results obtained through decision tree construction with those from component and cluster analyses is highlighted. The scientific significance of this study lies in its comprehensive exploration of neural networks' ability to forecast environmental processes, with a specific emphasis on greenhouse gas emissions prediction. The findings suggest that neural networks, particularly recurrent architectures, show promise as powerful tools for monitoring and forecasting environmental changes, offering valuable insights for governmental agencies and environmental initiatives.
Study on a Data Warehousing for E-commerce Logistics
Ceur Workshop Proceedings, 2024
Development of Mathematical Model for Traffic Control at Signalized Intersections
Oleksii Kolesnikov, Lyazat Naizabayeva, Buitek Bayan, Kateryna Kolesnikova
Procedia Computer Science, 2024
Information system for remediation and cleanup of contaminated soil with machine learning
L. Naizabayeva, Ch.A. Nurzhanov, M.N. Satymbekov, V.Zh. Elle
Procedia Computer Science, 2024
IDENTIFICATION OF AN ALGORITHM FOR THE ANALYSIS AND STUDY OF URBAN ROAD NETWORK TRAJECTORIES
Lyazat Naizabayeva, Gulzat Turken, Zukhra Abdiakhmetova, Zhanerke Temirbekova, Maxatbek Satymbekov
Eastern European Journal of Enterprise Technologies, 2024
Using Data Analysis Methods for Predicting the Concentration of Toxic Elements in Soil
Lyazat Naizabayeva, Gulnara Zakirova
Proceedings of the IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems Technology and Applications Idaacs, 2023
Digital Technology in Agriculture: An Approach to Modelling Crop Productivity on Trace Elements Contaminated Soil
Chingiz Nurzhanov, Lyazat Naizabayeva, Talgat Mazakov
Sist 2023 2023 IEEE International Conference on Smart Information Systems and Technologies Proceedings, 2023
Research and Development of Enterprise Data Warehouse Based on SAP BW Modeling
Gulzat Turken, Lyazat Naizabayeva, Maxatbek Satymbekov, Zukhra Abdiakhmetova
Sist 2023 2023 IEEE International Conference on Smart Information Systems and Technologies Proceedings, 2023
One Dimensional Conv-BiLSTMNetwork with AttentionMechanism for IoT Intrusion Detection
Bauyrzhan Omarov, Zhuldyz Sailaukyzy, Alfiya Bigaliyeva, Adilzhan Kereyev, Lyazat Naizabayeva, Aigul Dautbayeva
Computers Materials and Continua, 2023
DEVELOPMENT OF REFERENCE INCIDENT MANAGEMENT MODEL
Gulbakyt Sembina, Karina Mayandinova, Lyazat Naizabayeva, Saule Sagnayeva
Eastern European Journal of Enterprise Technologies, 2022
Optimizing Neural Network Performance to Predict Coronary Heart Disease
Azat Kabdullin, Maxat Kabdullin, Lyazat Naizabayeva
Sist 2021 2021 IEEE International Conference on Smart Information Systems and Technologies, 2021
Research and trends in computer science and educational technology during 2016–2020: Results of a content analysis
C. Nurzhanov, V. Pidlisnyuk, L. Naizabayeva, M. Satymbekov
World Journal on Educational Technology Current Issues, 2021
Decision Support System with K-Means Clustering Algorithm for Detecting the Optimal Store Location Based on Social Network Events
Mohamed Ahmed Hamada, Lyazat Naizabayeva
2020 IEEE European Technology and Engineering Management Summit E Tems 2020, 2020
Research on predictive model based on classification with parameters of optimization
Turken Gulzat, Naizabayeva Lyazat, Vladimir Siladi, Sembina Gulbakyt, Satymbekov Maksatbek
Neural Network World, 2020
Multi-agent grid system Agent-GRID with dynamic load balancing of cluster nodes
M.N. Satymbekov, I.T. Pak, L. Naizabayeva, Ch.A. Nurzhanov
Open Engineering, 2017
Modeling performance management over corporate information system operability
Journal of Theoretical and Applied Information Technology, 2017
Solving mean-shift clustering using MapReduce Hadoop
Maksat N. Kalimoldayev, Vladimir Siladi, Maksat N. Satymbekov, Lyazat Naizabayeva
2017 IEEE 14th International Scientific Conference on Informatics Informatics 2017 Proceedings, 2017
Corporate environmental information system data storage development and management (Environmental Information System)
Naizabayeva Lyazat, Nurzhanov Chingiz, Orazbekov Zhassulan, Tleuberdiyeva Gulnara
Open Computer Science, 2017
Improvement of company's performance through information technology infrastructure library (ITIL) methodology
Social Sciences Pakistan, 2015
Development of the complex of software applications to control the state of total thermal energy of an elastic rod
Kanat Amirtayev, Akzhan Ibadullayeva, Lyazat Naizabayeva, Zhazira Shermentayeva
8th IEEE International Conference on Application of Information and Communication Technologies Aict 2014 Conference Proceedings, 2014
Development of intelligent systems for information security auditing and management: Review and assumptions analysis
Lyazzat Atymtayeva, Assel Akzhalova, Kanat Kozhakhmet, Lyazat Naizabayeva
2011 5th International Conference on Application of Information and Communication Technologies Aict 2011, 2011
Development of a software system with the view of automation of traffic flow management
N.I. Nugumanov, L. Naizabayeva, D. Nurlanov
2009 International Conference on Application of Information and Communication Technologies Aict 2009, 2009

Lyazat Naizabayeva

Scopus Publications

RECENT SCHOLAR PUBLICATIONS

MOST CITED SCHOLAR PUBLICATIONS