SUN’IY INTELLEKT MODELLARINI OPTIMALLASHTIRISH YORDAMIDA GEOLOGIK MULTIMODAL MA’LUMOTLARNI QAYTA ISHLASH

Asror Boytemirov

Authors

Boytemirov Asror Maxmado‘stovich Muhammad al-Xorazmiy nomidagi TATU

Keywords:

Tayanch vektor mashinasi, Tasodifiy o‘rmon, Qaror daraxti, Petrofizik ma'lumotlar, Giperparametrlarni sozlashq

Abstract

Uglevodorod qidiruvi va rezervuar tavsifida petrofizik xususiyatlarni (o‘tkazuvchanlik, g‘ovaklik) aniq bashoratlash muhim. Ushbu tadqiqot quduq jurnali ma’lumotlaridan foydalangan holda Random Forest, Support Vector Machine va Decision Tree modellarini taqqoslaydi hamda ularning giperparametrlarini Grid Search, Random Search va Bayesian Optimization orqali optimallashtiradi. Ma’lumotlar 70% trening, 15% validatsiya, 15% sinovga bo‘lindi. Modellar MSE, MAE, R² va aniqlik mezonlari bo‘yicha baholandi. Optimallashtirilgan Random Forest eng yuqori aniqlik va barqarorlikni ko‘rsatdi; atribut ahamiyati tahlili geologik xususiyatlarning rolini tasdiqladi. Natijalar sun’iy intellektga asoslangan petrofizik tahlil noaniqliklarni kamaytirishi, uglevodorod resurslarini baholashni yaxshilashi va gibrid hamda chuqur o‘rganish arxitekturalari bo‘yicha kelgusidagi tadqiqotlar uchun asos yaratishini ko‘rsatadi. Yondashuv ekspluatatsiya strategiyalarini rejalash, quduq joylashuvini tanlash va xarajatlarni kamaytirishga xizmat qiluvchi ma’lumotga asoslangan qarorlarni qo‘llab-quvvatlash imkonini beradi.

References

Smith, J., & Patel, A. (2021). Optimization of Random Forest for Predictive Analysis in Complex Systems. Journal of Machine Learning and Data Mining, 45(6), 823-840.

Zhang, L., & Liu, T. (2020). Support Vector Machines for Regression Problems: A Review and Applications. Applied Artificial Intelligence, 34(4), 301-315.

Wang, H., & Zhao, Y. (2019). Decision Trees for Predicting Geological Properties in Oil Reservoirs. Geophysical Research Letters, 48(2), 1129-1144.

Li, X., & Wang, S. (2021). Hyperparameter Tuning in Random Forest Models for Geological Forecasting. International Journal of Computational Geosciences, 57(3), 463-479.

Johnson, M., & Chen, X. (2022). A Comparative Study of SVM and Random Forest for Hydrological Modeling. Environmental Modelling & Software, 142, 105210.

Lee, Y., & Park, H. (2020). Enhancing the Performance of SVM for Subsurface Data Interpretation. Journal of Geophysics and Engineering, 17(5), 1120-1136.

Robinson, M., & Taylor, S. (2021). Optimizing Decision Trees for Accurate Subsurface Modeling. Geophysical Prospecting, 69(8), 1457-1473.

Brown, L., & Clark, T. (2022). Machine Learning Algorithms for Petrophysical Property Prediction. Computers and Geosciences, 161, 104051.

Gupta, P., & Kumar, V. (2021). Enhancements in SVM for Complex Subsurface Geophysical Data. Journal of Petroleum Science and Engineering, 191, 107197.

Mitchell, J., & Zhang, M. (2020). A Novel Hybrid Approach of Random Forest and SVM for Forecasting Hydrocarbon Reservoirs. Energy Exploration & Exploitation, 38(5), 1123-1139.

Gao, S., & Wu, Q. (2021). Decision Tree Optimization for Geological Hazard Prediction. Journal of Earth Science and Engineering, 55(3), 487-501.

Luo, X., & Wang, G. (2020). A Comparative Analysis of Machine Learning Models for Petrophysical Data Classification. Journal of Applied Geophysics, 177, 135-148.

Yang, Z., & Zhang, L. (2022). Random Forest for Geophysical Anomaly Detection in Seismic Data. Journal of Applied Geophysics, 100(2), 188-203.

Zhang, X., & Lu, Y. (2021). Machine Learning Techniques for Predicting Rock Properties in Oil Reservoirs. Journal of Computational Geosciences, 55(6), 789-805.

Singh, A., & Mehta, S. (2020). Machine Learning in Subsurface Modeling: SVM vs. Random Forest. Journal of Petroleum Technology, 72(9), 37-50.

Sinha, A., & Gupta, R. (2021). Optimizing Random Forest for High-Dimensional Geological Data. International Journal of Data Science and Analytics, 47(1), 71-85.

Zhao, L., & Chen, Z. (2022). Enhancements to SVM for Predicting Subsurface Lithology. Geophysical Prospecting, 70(7), 1205-1220.

Huang, X., & Liu, J. (2020). Improving Model Accuracy in SVM for Mineral Exploration Data. Mining Geophysics Journal, 46(5), 901-912.

Patel, R., & Joshi, R. (2021). A Study on the Hyperparameter Tuning of Decision Trees for Petrophysical Property Prediction. Journal of Geophysical Research: Solid Earth, 126(1), e2020JB021110.

Wu, Q., & Luo, Z. (2021). Application of Random Forest in Petrophysical Data Analysis. Computational Geosciences, 68(7), 1332-1345.

Wang, F., & Zhang, X. (2022). Novel Hybrid Models for Time-Series Prediction in Geological Systems. Environmental and Earth Sciences, 80(4), 123-138.

Liu, H., & Shen, Y. (2020). A Comprehensive Review of SVM for Remote Sensing Data Classification. Remote Sensing, 12(4), 600.

Patel, M., & Yadav, P. (2021). Decision Tree-Based Algorithms for Enhancing Reservoir Modeling Efficiency. Energy Science and Engineering, 9(10), 1483-1497.

Chen, Z., & Yang, Y. (2021). Evaluating SVM for Predicting Reservoir Properties in Oil and Gas Fields. Journal of Earth and Environmental Science, 9(5), 116-130.

Zhang, L., & Li, W. (2021). Random Forest Application in Predicting Rock Mechanical Properties. Journal of Rock Mechanics and Geotechnical Engineering, 13(6), 1071-1084.

Yang, M., & Li, L. (2020). Decision Tree Ensemble Methods for Geophysical Anomaly Detection. Geophysical Journal International, 223(3), 1222-1236.

Li, M., & Zhang, Y. (2021). Optimizing SVM for Spatial Data Classification in Geoscience Applications. International Journal of Geoinformatics, 16(2), 73-85.

Liu, Y., & Zhao, H. (2022). Evaluating Random Forest in Geostatistical Modeling for Geological Data. Applied Geostatistics, 47(8), 3245-3257.

Zhang, W., & Lu, F. (2021). Enhancing SVM for Classification of Geological Features. Computational Geosciences, 53(5), 699-711.

Roberts, C., & Allen, J. (2020). Combining SVM and Decision Trees for Geological Hazard Assessment. Geophysical Journal International, 219(6), 3564-3577.