Alisher Saduov

Mr. Alisher Saduov

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 May 2025 in Applied Computing and Geosciences
Verified
Journal Article
Open access
ASAbish Sharapatov
Abish Sharapatov
ASAlisher Saduov
Alisher Saduov
NANazerke Assirbek
Nazerke Assirbek
MAMadiyar Abdyrov
Madiyar Abdyrov
BZBeibit Zhumabayev
Beibit Zhumabayev

27 June 2026 in Herald of the Kazakh-British technical university
Verified
Journal Article
Closed access
ASAlisher Saduov
Alisher Saduov
This study presents an unsupervised workflow for delineating prospectivity zones for stratiform copper-cobalt mineralization in the southern margin of the Central African Copperbelt, Zambia, using only airborne geophysical data (gravity, magnetics, radiometry, terrain). Three clustering algorithms-K-Means, Fuzzy C-Means (FCM), and Self-Organizing Maps (SOM)-were applied, followed by consensus clustering to isolate robust target zones. Key geophysical filters (tilt derivative, total horizontal derivative, analytic signal) and radiometric ratios (U/Th, U/K) were computed and compared across clusters. The most prospective cluster was validated against literature-calibrated geophysical thresholds and was found to match known exploration criteria and regional structural trends. A final probabilistic prospectivity map was generated from FCM membership, classifying targets into three confidence levels. While lack of drill-hole data prevents quantitative accuracy assessment, this approach demonstrates that fully unlabeled machine learning on airborne data can effectively guide early-stage exploration in data-sparse regions. The proposed workflow offers a reproducible framework for AI-driven prospectivity mapping in frontier terrains.

29 December 2023 in Горный журнал Казахстана
Verified
Journal Article
Closed access
АША. Шарапатов
А. Шарапатов
БЖБ.т. Жумабаев
Б.т. Жумабаев
ASAlisher Saduov
Alisher Saduov
НАН. Асирбек
Н. Асирбек
В петрофизических исследованиях установлена связь между значениями магнитных свойств (намагниченность, магнитная восприимчивость и проницаемость) геологического состава (среды) с его состоянием и изменениями в нем. Результаты носят более локальный характер. В магниторазведке (магнитометрии), когда наблюдения магнитного поля объекта изучения (среды, явления) осуществляются дистанционно, результаты отличаются объемом, глубинностью в пространстве и продолжительностью во времени. Результативность использования магнитных свойств пород и их поля при изучении состава, глубинного строения структур и процессов в недрах Земли подтверждены на конкретных примерах. Совершенствование методов, методики и техники наблюдений, алгоритмов обработки и истолкования геомагнитных данных увеличивает вероятность получения однозначных результатов при изучении состава, состояния геологической среды и прогнозе природных явлений Петрофизикалық зерттеулерде геологиялық құрамның (ортаның) магниттік қасиеттері (магниттелу, магнит қабылдағыштық және өтімділік) мәндерінің оның күйімен және ондағы өзгерістермен байланысы анықталды. Нәтижелер жергілікті сипатта болады. Магниттік барлауда (магнитометрия) зерттеу объектісінің (ортаның, құбылыстың) магнит өрісін бақылау қашықтан жүргізіледі, нәтижелер кеңістікте көлемімен, тереңдігімен және уақыт бойынша ұзақтығымен ерекшеленеді. Жер қойнауындағы құрылымдардың құрамын, тереңдік құрылысын және ондағы процестерді зерттеуде таужыныстардың магниттік қасиеттері мен олардың өрістерін қолданудың тиімділігі нақты мысалдар арқылы дәлелденді. Бақылау әдістерін, әдістемесін және техникасын, геомагниттік деректерді өңдеу және түсіндіру алгоритмдерін жетілдіру геологиялық ортаның құрамын, күйін зерттеуде және ондағы табиғи құбылыстарды болжау кезінде нәтижелер алу ықтималдығын арттырады In petrophysical studies, a connection has been established between the values of magnetic properties (magnetization, magnetic susceptibility, and permeability) of the geological composition (environment) with its state and changes in it. The results are more local in nature. In magnetic prospecting (magnetometry), when observations of the magnetic field of an object of study (environment, phenomenon) are carried out remotely, the results differ in volume, depth in space and duration in time. The effectiveness of using the magnetic properties of rocks and their fields in studying the composition, deep structure of structures and processes in the bowels of the Earth has been confirmed using specific examples. Improving the methods, techniques and technology of observations, algorithms for processing and interpreting geomagnetic data increases the likelihood of obtaining unambiguous results when studying the composition, state of the geological environment and forecasting natural phenomena

6 December 2023 in Горный журнал Казахстана
Verified
Journal Article
Closed access
АША. Шарапатов
А. Шарапатов
ASAlisher Saduov
Alisher Saduov
НАН. Асирбек
Н. Асирбек
Внедрение методов искусственного интеллекта – машинного и глубокого обучения, в решение задач геологии представляет собой существенный прорыв в технологии решения геопрогнозных задач. Анализ и сравнение эффективности различных алгоритмов машинного и глубокого обучения позволяет дать оценку их способностям адаптироваться к разным геологическим сценариям/заданиям, определить возможности технологии в интерпретации геологических данных и оптимизации объемов работ. В качестве объектов анализа и элементов изучения привлечены различные типы геоданных, алгоритмов машинного и глубокого обучения, геологических задач. Проведен сравнительный анализ производительности, точности алгоритмов в разных геологических контекстах. В анализе и обобщении возможностей алгоритмов искусственного интеллекта использован метод сравнения. Результаты показали актуальность их использования в обработке и интерпретации геоданных Геология мәселелерін шешуге жасанды интеллект әдістерін – машиналық және терең оқытуды енгізу, геоболжау тапсырмаларын орындау технологиясындағы елеулі серпіліс болып табылады. Машиналық және терең оқытудың әртүрлі алгоритмдерінің тиімділігін талдау және салыстыру олардың әртүрлі геологиялық сценарийлерге/тапсырмаларға бейімделу мүмкіндіктерін бағалауға, геологиялық деректерді түсіндіруде және жұмыс көлемін оңтайландыруда технологияның ықпалын анықтауға мүмкіндік береді. Талдау объектілері және зерттеу элементтері ретінде геодеректердің түрлері, машиналық және терең оқыту алгоритмдері, геологиялық тапсырмалар қамтылды. Әртүрлі геологиялық контексттердегі алгоритмдердің өнімділігі мен дәлдігіне салыстырмалы талдау жүргізілді. Жасанды интеллект алгоритмдерінің мүмкіндіктерін сараптау мен топтамалауда салыстыру әдісі қолданылды. Нәтижелер оларды геодеректерді өңдеу мен түсіндіруде қолданудың өзектілігін көрсетті The implementation of artificial intelligence methods – machine and deep learning – in solving geological tasks represents a significant breakthrough in the technology of solving geopredictive problems. Analysis and comparison of the effectiveness of various machine and deep learning algorithms allow us to assess their ability to adapt to different geological scenarios/tasks, determine the potential of technology in the interpretation of geological data, and optimize the volume of work. Various types of geodata, algorithms of machine and deep learning, and geological tasks were used as objects of analysis and elements of study. A comparative analysis of the performance and accuracy of algorithms in different geological contexts was conducted. In the analysis and generalization of the capabilities of artificial intelligence algorithms, the comparison method was used. The results showed the relevance of their use in processing and interpreting geodata

28 August 2026 in Minerals
Verified
Journal Article
Open access
PDF file
ASAlisher Saduov
Alisher Saduov
GZGeroy Zh. Zholtaev
Geroy Zh. Zholtaev
Kuanysh TogizovKuanysh Togizov
Kuanysh Togizov
ZUZamzagul Umarbekova
Zamzagul Umarbekova
NZNurbakyt Zhumabay
Nurbakyt Zhumabay
NANursat Amangeldi
Nursat Amangeldi
Mineral prospectivity mapping (MPM) increasingly relies on machine learning classifiers, but model performance may be overstated when spatial dependence, extrapolation beyond the training domain, and poorly calibrated prediction scores are not adequately addressed. This study presents a reproducible workflow for regional Au-Ag prospectivity mapping in Nevada that integrates positive–unlabeled learning with Random Forest models and spatial GroupKFold cross-validation. Predictions were restricted to the Area of Applicability (AOA), defined using the 0.95 quantile of a training-derived feature-space dissimilarity index, resulting in areal coverage of 54.331% for Ag and 73.118% for Au. Discrimination based on pooled out-of-fold (OOF) predictions was strong for both commodities (Ag:AP = 0.745, ROC-AUC = 0.908; Au:AP = 0.777, ROC-AUC = 0.912). Post hoc OOF calibration with isotonic regression reduced Brier scores and improved probability reliability within the supported prediction domain. Area-based validation showed that the highest-ranked 10% of the AOA captured 85.6% of the Ag and 84.2% of the Au pooled-OOF positives, corresponding to targeting efficiencies of 8.6-fold and 8.4-fold relative to random spatial selection. Ensemble dispersion was used to map predictive uncertainty and to identify areas where additional data may be most useful for reducing uncertainty. SHAP importance and partial-dependence diagnostics consistently highlighted proximity to Quaternary faults, elevated slip and dilation tendency, and potential-field edges associated with intrusive or volcanic contacts, while surface heat flow acted mainly as a permissive control. The resulting AOA-masked prospectivity maps, uncertainty layers, and top-k targeting products provide a transparent regional framework for prioritizing follow-up exploration and allocating reconnaissance effort.

26 September 2026 in Mining of Mineral Deposits
Verified
Journal Article
Closed access
GOGulnara Omarova
Gulnara Omarova
BSBulat M. Sukurov
Bulat M. Sukurov
SASaltanat Assubayeva
Saltanat Assubayeva
ASAlisher Saduov
Alisher Saduov
STSymbat Tugambay
Symbat Tugambay
Yalkunzhan ArshamovYalkunzhan Arshamov
Yalkunzhan Arshamov
Purpose. To establish the mineral-formforming sequence and clarify the features of gold-telluride-sulfide mineralization at the Kokkiya deposit based on the study of mineral assemblages, typomorphic characteristics of ore minerals, modes of occurrence of native gold and tellurides, and their spatial and paragenetic relationships. Methods. A total of 120 ore and host-rock samples collected from drill core were studied. The analytical methods included optical microscopy in reflected and transmitted light, scanning electron microscopy, electron-probe microanalysis, EDS/WDS analysis, and EDS mapping. Gold fineness and composition were additionally compared with depth, pyrite generations, structural and textural characteristics of the ores, and hypogene and supergene mineral assemblages. Findings. Two main stages of mineralization were distinguished: hypogene and supergene. Four successive stages were identified within the hypogene stage: pre-ore hydrothermal-metasomatic, early pyrite, main telluride-polymetallic, and late pyrite-polymetallic. Pyrite is the principal ore mineral and is represented by several generations differing in morphology and paragenesis. Native gold is associated with pyrite, quartz, sericite, galena, and tellurides. The later stages are characterized by calaverite, petzite, altaite, tsumoite, native tellurium, and Bi-bearing minerals. Gold fineness in intergrowths with altaite and calaverite ranges from 944-977‰, whereas in oxidized ores it ranges from 634-820‰. EDS mapping confirmed the close spatial association of micron-scale gold inclusions with telluride phases. The most intense mineralization is confined to the inner, most strongly altered parts of the metasomatic zonation. Originality. The mineralogical-genetic model of the Kokkiya deposit has been refined by linking pyrite generations, gold fineness, telluride mineralization, and the sequence of ore-forming stages. The distribution of gold and tellurides is shown to reflect the multistage evolution of the hydrothermal system and subsequent supergene alteration. Practical implications. Sericitolites, Te- and Bi-bearing minerals, characteristics of pyrite generations, and gold-telluride associations can be used as mineralogical exploration criteria for evaluating prospective zones and the potential continuation of productive mineralization at depth.