Jorge L. V. Mariz

Dr. Jorge L. V. Mariz

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
11 April 2024 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
JMJorge L. V. Mariz
Jorge L. V. Mariz
MBMohammad Mahdi Badiozamani
Mohammad Mahdi Badiozamani
RPRodrigo de Lemos Peroni
Rodrigo de Lemos Peroni
RSRicardo Martins de Abreu Silva
Ricardo Martins de Abreu Silva

1 March 2023 in REM - International Engineering Journal
Verified
Journal Article
Open access
JMJorge L. V. Mariz
Jorge L. V. Mariz
SRSuelen Silva Rocha
Suelen Silva Rocha
JSJúlio César de Souza
Júlio César de Souza
GMGleicon Roberto de Sousa Maior
Gleicon Roberto de Sousa Maior

26 May 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JMJorge L. V. Mariz
Jorge L. V. Mariz
TFTertius Ferraz
Tertius Ferraz
MLMarinésio Pinheiro De Lima
Marinésio Pinheiro De Lima
RSRicardo M. A. Silva
Ricardo M. A. Silva
HJHyongdoo Jang
Hyongdoo Jang
Dilution in underground mining refers to the unintended incorporation of waste material into the ore, reducing ore grade, revenue, and operational safety. Unplanned dilution, specifically, occurs due to overbreak caused by blasting inefficiencies or poor rock stability. To mitigate this issue, various factors related to rock quality, stope geometry, drilling, and blasting must be carefully considered. This study introduces a statistically rigorous methodology for the prediction of dilution in underground mining operations. The proposed framework incorporates a 10-fold cross-validation procedure with 30 repetitions, along with the application of nonparametric statistical tests. A total of eight supervised machine learning algorithms were investigated, with their hyperparameters systematically optimized using two distinct genetic algorithm (GA) strategies evaluated under varying population sizes. The models include support vector machines, neural networks, and tree-based approaches. Using a dataset of 120 samples, the results indicate that the GA-ANN model outperforms other approaches, achieving MAE, R2, and RMSE values of 0.2986, 0.8457, and 0.3928 for the training dataset, and 0.1882, 0.9508, and 0.2283 for the testing dataset, respectively. Furthermore, four stacking models were constructed by aggregating the top-performing base learners, giving rise to ensemble metamodels applied, for the first time, to the task of dilution prediction in underground mining.

1 January 2024 in REM - International Engineering Journal
Verified
Journal Article
Open access
PDF file
JMJorge L. V. Mariz
Jorge L. V. Mariz
RPRodrigo de Lemos Peroni
Rodrigo de Lemos Peroni
RSRicardo Martins de Abreu Silva
Ricardo Martins de Abreu Silva
Since the open-pit precedence-constrained production scheduling problem is an NP-hard problem, solving it is always a challenging task, especially from a long-term perspective because a mineral deposit containing millions of blocks would require several million precedence arcs as constraints, making the solution time grow exponentially and making a direct approach unfeasible. Therefore, different strategies have been employed since the 1960s to reduce the size of this problem, such as determining the ultimate pit limit, subdividing it into phases, segmenting the production scheduling problem into long-, mid-, and short-term plans, as well as aggregating blocks into clusters, thus significantly reducing the number of precedence arcs. Different modeling and clustering strategies have already been employed in an attempt to reduce the size of the mine sequencing problem, such as layer modeling, re-blocking, bench-phase clustering, or polygon (mining cut) clustering based on a similarity function. The mining cut clustering problem has been solved lately by machine learning and heuristics techniques, and this approach can also introduce operational constraints to the mine sequencing problem, such as equipment size, minimum pit width, and preferential mining direction. In this study, we propose a mining cut clustering model based on Mixed Integer Linear Programming (MILP). Then we solve it by an exact approach and by Constraint Programming (CP), analyzing the strengths and weaknesses of the Constraint Optimization Problem (COP) and Constraint Satisfaction Problem (CSP) techniques. Numerical experiments were carried out on the Bench 15 of the Newmanl dataset, demonstrating the superiority of the COP approach.

31 January 2025 in Mining, Metallurgy & Exploration
Verified
Journal Article
Closed access
PDF file
MBMarcel Antonio Arcari Bassani
Marcel Antonio Arcari Bassani
OGOctávio R. A. Guimarães
Octávio R. A. Guimarães
FTFlávio H. Tavares
Flávio H. Tavares
BCBreno Cantadori
Breno Cantadori
RVRicardo Vicenzi
Ricardo Vicenzi
RPRodrigo de Lemos Peroni
Rodrigo de Lemos Peroni

1 January 2025 in REM - International Engineering Journal
Verified
Journal Article
Open access
GMGleicon Roberto de Sousa Maior
Gleicon Roberto de Sousa Maior
RPRodrigo de Lemos Peroni
Rodrigo de Lemos Peroni
JMJorge L. V. Mariz
Jorge L. V. Mariz
The longitudinal grade and rolling resistance of mining haul roads are critical factors that significantly influence transportation costs and productivity in open-pit mining. Inadequate geometric design and high rolling resistance can lead to increased energy consumption, higher rates of mechanical failure, and greater maintenance requirements, ultimately shortening the lifespan of trucks and tires and negatively affecting overall operational efficiency. The geometric layout of mining roads is influenced by factors such as the mining method, orebody geometry, and topography, and is often determined through empirical knowledge or arbitrary decision-making, rather than an adequate methodology. This article proposes a practical methodology to assess how the combination of different longitudinal grades and rolling resistances affect haul truck efficiency in terms of fuel consumption and productivity. The methodology is straightforward and suitable even for small mines. It consists of four stages: (1) data collection using unmanned aerial vehicles (UAVs); (2) processing of aerial imagery to create a digital elevation model; (3) assessing of road design under different rolling resistance scenarios; and (4) evaluating fuel consumption and truck productivity. A case study in a Brazilian iron ore mine was proposed, and the results indicate that optimizing longitudinal grades and managing rolling resistance can reduce truck cycle time by up to 15%, save up to 13% on fuel consumption, and improve per-truck productivity by up to 17%, thus enabling a smaller truck fleet without compromising overall output.