Decision support system for bioleaching processes

Demergasso, Cecilia; Véliz, Roberto; Galleguillos, Pedro A.; Marín, Sabrina; Acosta, Mauricio; Zepeda, Víctor J.; Zeballos, Jaqueline; Henríquez, Felipe; Pizarro, Rodrigo; Bekios-Calfa, Juan

doi:10.1016/j.hydromet.2018.08.009

Cited by 20 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These changes in microbial community composition can often occur in a predictable manner. SML has been used in both natural and industrial settings to use microbial information to aid in predicting environmental quality [85] , contamination state [86] , [87] as well as rates of various processes including copper bioleaching [88] , Previous studies have used microbial biomarkers as indicators of particular environmental processes or outcomes. Indicator species analysis has been used to identify taxa that are related to particular phenomena or treatments that could be used as biomarkers for that phenomena.…”

Section: Optimizing Model Construction and Evaluationmentioning

confidence: 99%

Machine learning applications in microbial ecology, human microbiome studies, and environmental monitoring

Ghannam

Techtmann

2021

Computational and Structural Biotechnology Journal

143

View full text Add to dashboard Cite

show abstract

Section: Optimizing Model Construction and Evaluationmentioning

confidence: 99%

Machine learning applications in microbial ecology, human microbiome studies, and environmental monitoring

Ghannam

Techtmann

2021

Computational and Structural Biotechnology Journal

143

View full text Add to dashboard Cite

show abstract

“…A decision tree (DT) , is a supervised learning machine that makes decisions based on some logical rules, which does not depend on the predefined relationship between input features and predicted output results, ignoring the magnitude of input features. The decision tree is divided by searching features to pursue the effect of uniform output distribution, and the output of the decision tree is optimized by parameters.…”

Section: Data Processing and Machine Learning Modelsmentioning

confidence: 99%

Application of Machine Learning in a Mineral Leaching Process─Taking Pyrolusite Leaching as an Example

Zhang

et al. 2022

ACS Omega

View full text Add to dashboard Cite

In this study, several machine learning models were used to analyze the process variables of electric-field-enhanced pyrolusite leaching and predict the leaching rate of manganese, and the applicability of those models in the leaching process of hydrometallurgy was compared. It showed that there was no correlation between the six leaching conditions; in addition to the leaching time, the concentrations of sulfuric acid and ferrous sulfate had great influences on the leaching of pyrolusite. The results of the prediction models showed that the support vector regression model has the best prediction performance, with regression index (R 2) = 0.92 and mean square error = 25.04, followed by the gradient boosting regression model (R 2 > 0.85). In this research, machine learning models were applied to the optimization of the manganese leaching process, and the research process and methods were also applicable to other hydrometallurgical processes for majorization and result prediction.

show abstract

“…The information obtained from the validated real-time PCR array was incorporated in the development of one of the modules of a decision-support system (DSS) based on decision rules that transform the obtained knowledge into recommendations to the plant operator of the bioleaching process [ 23 , 24 ], assisting with the mine site. This kind of DSS is popularly used, e.g., in evidence-based medicine, to improve healthcare delivery [ 25 ].…”

Section: Introductionmentioning

confidence: 99%

“…The construction of the DSS for bioleaching processes considers a database for industrial data logging and storage, a knowledge base acquired by suitable statistical and computational tools, and finally, the translation of knowledge into action by applying recommendations that come to terms with operational limitations. The DSS is composed of five reasoning modules: (1) the impact of mineralogy/mineralization in the metallurgical performance, (2) microbial activity and copper recovery, (3) estimated temperature inside the heap, (4) marker genes for critical issues, and (5) inoculation/reinoculation requirements [ 23 ].…”

Section: Introductionmentioning

confidence: 99%

From Laboratory towards Industrial Operation: Biomarkers for Acidophilic Metabolic Activity in Bioleaching Systems

Marín

Cortés

Acosta

et al. 2021

Genes

Self Cite

View full text Add to dashboard Cite

In the actual mining scenario, copper bioleaching, mainly raw mined material known as run‐of‐mine (ROM) copper bioleaching, is the best alternative for the treatment of marginal resources that are not currently considered part of the profitable reserves because of the cost associated with leading technologies in copper extraction. It is foreseen that bioleaching will play acomplementary role in either concentration—as it does in Minera Escondida Ltd. (MEL)—or chloride main leaching plants. In that way, it will be possible to maximize mines with installed solvent‐extraction and electrowinning capacities that have not been operative since the depletion of their oxide ores. One of the main obstacles for widening bioleaching technology applications is thelack of knowledge about the key events and the attributes of the technology’s critical events at the industrial level and mainly in ROM copper bioleaching industrial operations. It is relevant to assess the bed environment where the bacteria–mineral interaction occurs to learn about the limiting factors determining the leaching rate. Thus, due to inability to accurately determine in‐situ key variables, their indirect assessment was evaluated by quantifying microbial metabolic‐associated responses. Several candidate marker genes were selected to represent the predominant components of the microbial community inhabiting the industrial heap and the metabolisms involved in microbial responses to changes in the heap environment that affect the process performance. The microbial community’s predominant components were Acidithiobacillus ferrooxidans, At. thiooxidans, Leptospirillum ferriphilum, and Sulfobacillus sp. Oxygen reduction, CO2 and N2 fixation/uptake, iron and sulfur oxidation, and response to osmotic stress were the metabolisms selected regarding research results previously reported in the system. After that, qPCR primers for each candidate gene were designed and validated. The expression profile of the selected genes vs. environmental key variables in pure cultures, column‐leaching tests, and the industrial bioleaching heap was defined. We presented the results obtained from the industrial validation of the marker genes selected for assessing CO2 and N2 availability, osmotic stress response, as well as ferrous iron and sulfur oxidation activity in the bioleaching heap process of MEL. We demonstrated that molecular markers are useful for assessing limiting factors like nutrients and air supply, and the impact of the quality of recycled solutions. We also learned about the attributes of variables like CO2, ammonium, and sulfate levels that affect the industrial ROM‐scale operation.

show abstract

Decision support system for bioleaching processes

Cited by 20 publications

References 17 publications

Machine learning applications in microbial ecology, human microbiome studies, and environmental monitoring

Machine learning applications in microbial ecology, human microbiome studies, and environmental monitoring

Application of Machine Learning in a Mineral Leaching Process─Taking Pyrolusite Leaching as an Example

From Laboratory towards Industrial Operation: Biomarkers for Acidophilic Metabolic Activity in Bioleaching Systems

Contact Info

Product

Resources

About