Olzhas Kurmanbayev

Olzhas Kurmanbayev

Auto-generated profile, based on publicly available information

Olzhas Kurmanbayev

Al-Farabi Kazakh National University

Research Focus & Metrics

Representative Publications

View All Publications
21 September 2026 in Water
Verified
Journal Article
Open access
PDF file
SKSholpan KULBEKOVA
Sholpan KULBEKOVA
AKAbzal Kalygulov
Abzal Kalygulov
RARanida Arystanova
Ranida Arystanova
AAAsset Arystanov
Asset Arystanov
OKOlzhas Kurmanbayev
Olzhas Kurmanbayev
SLSangchul Lee
Sangchul Lee
In data-sparse Central Asian watersheds, machine learning and Geographic Information Systems (GIS) are increasingly applied to hydrological hazard classification. This article compares Random Forest (RF), XGBoost, and Long Short-Term Memory (LSTM) models for daily elevated-discharge classification in the Koksu River basin, Zhetysu Region, Kazakhstan (1614 km2, semi-arid, snowmelt- and glacier-influenced climate; 2005–2023), using verified discharge, precipitation, and temperature records from four monitoring stations. The elevated-discharge threshold (80th percentile, ~90.5 m3/s) was computed using only the training period (2005–2017) to avoid temporal data leakage into validation and test periods. Class imbalance, addressed via class weighting, was moderate under this threshold. All models were benchmarked against a naive persistence baseline. Contrary to expectation, the persistence baseline achieved the highest Critical Success Index (CSI = 0.821, 95% block-bootstrap CI [0.725, 0.891]), narrowly ahead of XGBoost (CSI = 0.813, [0.703, 0.897]), Random Forest (CSI = 0.809, [0.691, 0.897]), and LSTM (CSI = 0.763, [0.630, 0.873]); the confidence intervals overlap substantially, indicating no statistically distinguishable advantage of any trained model over simple persistence in this basin. Feature-importance and ablation analyses confirmed that lagged discharge, not precipitation, drove nearly all predictive skill: a discharge-lags-only model performed as well as or better than the complete pipeline, while a meteorology-and-seasonality-only model performed markedly worse (CSI ≈ 0.57–0.59). As a preliminary, exploratory illustration rather than a core result, Gumbel-derived return-period discharges (Q10, Q25, and Q100) were separately translated into illustrative, uncalibrated, DEM-proximity-based inundation extents, a candidate direction for future work rather than an engineering-grade flood-mapping contribution of this study. These results indicate that, in this basin and period, machine learning classifiers provide no clearly demonstrated advantage over simple discharge persistence, underscoring the necessity of routine persistence benchmarking before adopting machine learning approaches for early warning in Central Asian watersheds facing increasing flood risk under climate change.

23 July 2026 in Water
Verified
Journal Article
Open access
PDF file
ASAizhan Skakova
Aizhan Skakova
RARaushan Amanzholova
Raushan Amanzholova
Daniel D SnowDaniel D Snow
Daniel D Snow
Arman UtepovArman Utepov
Arman Utepov
RARanida Arystanova
Ranida Arystanova
MKMarzhan Kalmakhanova
Marzhan Kalmakhanova
Kazakhstan faces growing water security and environmental management challenges and needs more practice-oriented environmental science education. This study examines two complementary Kazakhstan-based cases. Case Study 1 analyzes faculty and student surveys from the 2022 Science with a Purpose project, which delivered short courses in water quality, air quality, remediation, sampling methods, and scientific communication. Case Study 2 examines the 2025 pilot adaptation of the Nebraska-based Know Your Well (KYW) participatory-science model. An exploratory comparative two-case-study design drew on survey responses, project documentation, instructional materials, participant feedback, workflow analysis, and two illustrative laboratory water analyses. In Case Study 1, 22 of 25 faculty members responded (88.0%); student response rates were 14 of 18 (77.8%) before and 10 of 18 (55.6%) after the courses. Participants generally rated practice-oriented content positively. In the KYW pilot (N = 15), 14 participants (93.3%) reported that the training met expectations, and 14 (93.3%) considered the skills fully or partially applicable. The pilot demonstrated a feasible workflow linking preparation, field activity, sample handling, and laboratory-supported interpretation. Although the findings do not establish national representativeness, intervention effects, long-term learning outcomes, or large-scale monitoring impact, they support complementary capacity-building pathways for Kazakhstan.

9 April 2026 in Mine Surveying and Subsurface Use
Verified
Journal Article
Closed access
Kanay RysbekovKanay Rysbekov
Kanay Rysbekov
SSSaule B. Sherubay
Saule B. Sherubay
YAYergali S. Auelkhan
Yergali S. Auelkhan
Janay SaginJanay Sagin
Janay Sagin
OBOrynbassar Baiturbay
Orynbassar Baiturbay
The article investigates the main sources of water resource pollution in the Republic of Kazakhstan, including groundwater. The aim of the study is to examine the contamination of water resources by heavy metals resulting from the activities of several mining and ore-processing enterprises located along the shore of Lake Balkhash, and to develop an approach for pollution prevention based on remote monitoring technologies. A remote monitoring method for water resource contamination has been proposed, enabling continuous control of groundwater quality and condition. The research results have been implemented at mining enterprises in Kazakhstan and are used in the educational process at Satbayev University.

9 April 2026 in Mine Surveying and Subsurface Use
Verified
Journal Article
Closed access
AKAigul Kenesbayeva
Aigul Kenesbayeva
OKOlzhas S. Kurmanbayev
Olzhas S. Kurmanbayev
RKRuslan S. Kurmanbayev
Ruslan S. Kurmanbayev
LZLutpulla L. Zhalilov
Lutpulla L. Zhalilov
This article examines the modeling of earth's surface deformation processes within an oil and gas field using the finite element method. The Severnye Buzachi hydrocarbon field, located in the Mangystau region, is used as a case study. Based on geodynamic observations conducted at the field, relative deformation components are calculated and a spatial model of the deformation field is constructed using the finite element method. The resulting model reflects the geodynamic situation throughout the entire field, identifies areas of the most intense displacements, and determines the spatial distribution of deformation processes. This approach enables an objective assessment of the impact of oil and gas field development on the stress-strain state of the geological environment and contributes to improved field safety.

3 June 2025 in Горный журнал Казахстана
Verified
Journal Article
Open access
ЖАЖ.н. Алишева
Ж.н. Алишева
ОКО.с. Курманбаев
О.с. Курманбаев
АКА. Кумар
А. Кумар
Компьютерное моделирование в нефтедобыче способствует повышению производительности, эффективности и разработке инновационных методов увеличения нефтеотдачи. Важную роль в сырьевой базе нефтяной отрасли Казахстана и других стран играют запасы тяжелых и битумных нефтей. Этот вид углеводородов с потенциалом в более чем 14 миллиардов тонн добычи ежегодно привлекает внимание нефтяных компаний. Среди перспективных методов воздействия выделяются физические поля: магнитные, ультразвуковые, вибрационные. Они разрушают структуры нефтяных ассоциатов, снижая вязкость нефти. Математическое моделирование и компьютерные расчеты подтвердили эффективность ультразвукового воздействия на флюидосодержащие системы, подтвердив данные лабораторных исследований Мұнай өндіруде компьютерлік модельдеу өнімділікті, тиімділікті арттыруға және мұнай қайтарымын көбейтудің инновациялық әдістерін әзірлеуге ықпал етеді. Қазақстан мен басқа да елдердің мұнай өнеркәсібінің шикізат базасында ауыр және битумды мұнай қоры маңызды рөл атқарады. Жыл сайын өндірілетін 14 миллиард тоннадан астам әлеуеті бар бұл көмірсутек түрі мұнай компанияларының назарын аударуда. Әсер етудің болашағы зор әдістерінің арасында магниттік, ультрадыбыстық, вибрациялық сияқты физикалық өрістер ерекшеленеді. Олар мұнай ассоциаттарының құрылымын бұзып, оның тұтқырлығын төмендетеді. Математикалық модельдеу мен компьютерлік есептеулер сұйықтықпен қаныққан жүйелерге ультрадыбыстық әсер етудің тиімділігін және зертханалық зерттеулердің нәтижелерін растады Computer modeling in oil production enhances productivity, efficiency, and the development of innovative methods to increase oil recovery. Heavy and bituminous oil reserves play a significant role in the resource base of Kazakhstan’s oil industry and other countries. This type of hydrocarbon, with a production potential exceeding 14 billion tons annually, continues to attract the attention of oil companies. Among the promising methods of influence are physical fields such as magnetic, ultrasonic, and vibrational fields. These methods break down the structures of oil associates, reducing oil viscosity. Mathematical modeling and computer simulations have confirmed the effectiveness of ultrasonic impact on fluid-containing systems, supporting the findings of laboratory studies

26 September 2026 in Mining of Mineral Deposits
Verified
Journal Article
Closed access
KZKanat Zhunussov
Kanat Zhunussov
SASeidulla Abdullayev
Seidulla Abdullayev
RKRashida Kadyrova
Rashida Kadyrova
OKOlzhas Kurmanbayev
Olzhas Kurmanbayev
Nurzhigit SarybayevNurzhigit Sarybayev
Nurzhigit Sarybayev
MMMaxat Mamadiyarov
Maxat Mamadiyarov
Purpose. To substantiate solutions for improving energy efficiency in the mining industry through the integration of renewable energy sources (RES), energy management systems (EMS), and hybrid energy technologies, considering their energy, environmental, and economic performance. Methods. The study used theoretical analysis, comparative assessment, mathematical calculations, and data processing based on scientific publications and international reports. The main indicators of RES, EMS, and hybrid systems were compared using common energy, environmental, and economic parameters. Calculations were performed using Python with NumPy and Pandas libraries and SMath Solver. Three scenarios were considered: conventional energy consumption, RES integration, and hybrid energy supply. Findings. The results indicate that RES integration can reduce energy consumption by 10-30%, while hybrid systems provide a reduction of 15-35% and reported system-efficiency values of 70-90%. EMS can reduce energy consumption by 8-25%, peak loads by 10-30%, and CO2 emissions by 6-20%. Total investment costs for RES projects were estimated at 57.5-156 million USD. For hybrid systems, the required investment ranges from USD 2.5 to 7.5 million, with annual savings of USD 0.5 to 1.2 million and a payback period of up to 10 years, whereas EMS require substantially lower capital investment and have a payback period of up to 6 years. Originality. A comparative assessment of RES, EMS, and hybrid energy technologies was performed using a common set of energy, environmental, and economic indicators, which made it possible to identify differences in their efficiency, investment requirements, and implementation conditions. Practical implications. The obtained results can be used to support the selection of energy-efficiency solutions for mining enterprises depending on production scale, investment capacity, infrastructure readiness, and expected energy savings.