دانشگاه مازندران

 آمار

تعداد نشریات32
تعداد شماره‌ها581
تعداد مقالات5,665
تعداد مشاهده مقاله8,610,298
تعداد دریافت فایل اصل مقاله6,280,627
Alidmat, Afaf, ALe'damat, Ayed, Mashaqbh, Nour, rather, khalid ul islam. (1405). A COMPARATIVE ANALYSIS OF TRADITIONAL STATISTICAL AND MACHINE LEARNING APPROACHES FOR SALINITY PREDICTION. پژوهشنامه مدیریت اجرایی, (), -. doi: 10.22080/cjms.2026.31613.1844
Afaf Alidmat; Ayed ALe'damat; Nour Mashaqbh; khalid ul islam rather. "A COMPARATIVE ANALYSIS OF TRADITIONAL STATISTICAL AND MACHINE LEARNING APPROACHES FOR SALINITY PREDICTION". پژوهشنامه مدیریت اجرایی, , , 1405, -. doi: 10.22080/cjms.2026.31613.1844
Alidmat, Afaf, ALe'damat, Ayed, Mashaqbh, Nour, rather, khalid ul islam. (1405). 'A COMPARATIVE ANALYSIS OF TRADITIONAL STATISTICAL AND MACHINE LEARNING APPROACHES FOR SALINITY PREDICTION', پژوهشنامه مدیریت اجرایی, (), pp. -. doi: 10.22080/cjms.2026.31613.1844
Alidmat, Afaf, ALe'damat, Ayed, Mashaqbh, Nour, rather, khalid ul islam. A COMPARATIVE ANALYSIS OF TRADITIONAL STATISTICAL AND MACHINE LEARNING APPROACHES FOR SALINITY PREDICTION. پژوهشنامه مدیریت اجرایی, 1405; (): -. doi: 10.22080/cjms.2026.31613.1844

A COMPARATIVE ANALYSIS OF TRADITIONAL STATISTICAL AND MACHINE LEARNING APPROACHES FOR SALINITY PREDICTION

Caspian Journal of Mathematical Sciences
مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 08 مرداد 1405
نوع مقاله: Research Articles
شناسه دیجیتال (DOI): 10.22080/cjms.2026.31613.1844
نویسندگان
Afaf Alidmat1؛ Ayed ALe'damat2؛ Nour Mashaqbh1؛ khalid ul islam rather* 3
1National Center for Agricultural Research, Ministry of Agricultural, Jordan.
2Department of Mathematics, AL Hussain Bin Talal University, ma'an, Jordan
3Sher-e-Kashmir univeristy of agricultural sciences and technology jammu
تاریخ دریافت: 08 اردیبهشت 1405،  تاریخ بازنگری: 24 اردیبهشت 1405،  تاریخ پذیرش: 28 اردیبهشت 1405 
چکیده
Accurate salinity prediction is essential for sustainable agriculture, water resource management, and environmental planning. This study presents a comparative evaluation of traditional statistical models and machine learning approaches for salinity prediction using environmental and hydro-climatic data. Linear and multiple regression models are compared with advanced machine learning techniques including support vector machines, random forests, gradient boosting, and artificial neural networks. Model performance is evaluated using R2, RMSE, and MAE. Results indicate that machine learning models demonstrate improved predictive capability in capturing nonlinear relationships, while linear regression exhibits strong interpretability and stable generalization. Feature importance analysis identifies key environmental drivers influencing salinity dynamics. The findings provide valuable insights into model selection for environmental applications.
کلیدواژه‌ها
Salinity prediction؛ Machine learning؛ Regression؛ Environmental modelling؛ Hydro-climatic variables
آمار
تعداد مشاهده مقاله: 12


سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب