Document Type : Original Research Paper

Authors

• Marco Antonio Cotrina-Teatino ¹
• Jairo Jhonatan Marquina-Araujo ¹
• Solio Marino Arango-Retamozo ¹
• Luis Alex Rios-LLaure ¹
• Jose Nestor Mamani-Quispe ²
• Salomon Ortiz-Quintanilla ³

¹ Department of Mining Engineering, Faculty of Engineering, National University of Trujillo, Trujillo, Peru

² Faculty of Chemical Engineering, National University of the Altiplano of Puno, Puno, Peru

³ Faculty of Engineering, Mining Engineering School, Universidad Nacional Jorge Basadre Grohmann, Tacna, Peru

Abstract

This work aimed to optimize fuel consumption and CO₂ emissions in mining haul trucks through a sustainability focused machine learning approach in a gold mine in La Libertad, Peru. The methodology comprised three stages. First, operational data from 26 m³ haul trucks (10,103 records over 12 months) were normalized using Z-score scaling. Second, a Ridge regression model was trained to predict fuel consumption based on variables such as truck utilization, trips, road gradient, material type, haul distance, and operating hours. Finally, three operational strategies were simulated: Controlled Reduction (CRS), Balanced Efficiency (BES), and Maximum Utilization (MUS), to evaluate environmental, economic, and social impacts. The results indicated that the Ridge model achieved strong predictive performance in estimating fuel consumption (R² = 0.83; MSE = 38.16). According to the simulated scenarios, environmentally, CRS reduced fuel consumption by 30% and CO₂ emissions by 1,481.3 tons; BES achieved 7.99% savings and 394.9 tons less CO₂. Economically, CRS saved USD 664,924.6 in fuel costs and BES USD 177,276.3. Socially, the carbon cost decreased by USD 11,406.1 (CRS) and USD 3,041.0 (BES). MUS increased emissions by 864.3 tons and fuel costs by USD 387,966.4. This research proposes a novel integration of machine learning and sustainability analysis applied to haul trucks in open-pit mining material transport. It also offers a replicable, data-driven framework for mining companies to reduce emissions, optimize costs, and align their operations with sustainability goals.

Keywords

• Energy efficiency
• Carbon dioxide
• Ridge regression
• Operational sustainability
• Fuel consumption

Main Subjects

• Simulation & Optimization