Currently, most mining companies conduct chemical analyses by X-ray fluorescence performed in the laboratory to evaluate the quality of Fe ore, where the focus is mainly on the Fe content and the presence of impurities. However, this type of analysis requires the investment of time and money, and the results are often available only after the ore has already been sent by the processing plant. Reflectance spectroscopy is an alternative method that can significantly contribute to this type of application as it consists of a nondestructive analysis technique that does not require sample preparation, in addition to making the analyses available in more active ways. Among the challenges of working with reflectance spectroscopy is the large volume of data produced. However, one way to optimize this type of approach is to use machine learning techniques. Thus, the main objective of this study was the calibration and evaluation of models to analyze the quality of Fe from Sinter Feed collected from deposits in the Carajás Mineral Province, Brazil. To achieve this goal, machine learning models were tested using spectral libraries and X-ray fluorescence data from Sinter Feed samples. The most efficient models for estimating Fe were the Adaboost and support vector machine and our results highlight the possibility of application in the samples without the need for preparation and optimization of the analysis time, providing results in a timely manner to contribute to decision-making in the production chain.

The development of miniaturized sensors has become relevant for the detection of chemical/biological substances, since they use and detect low concentrations, such as flocculants based on amines for the mining industry. In this study, buckypaper (BP) films based on carboxylic acid functionalized multi-walled carbon nanotubes (f-MWCNTs) were produced through vacuum filtration on cellulose filter paper to carry out sensory function in samples containing ether-amine (volumes: 1%, 5%, 10% and 100%). The morphological characterization of the BPs by scanning electron microscopy showed f-MWCNT aggregates randomly distributed on the cellulose fibers. Vibrational analysis by Raman spectroscopy indicated bands and sub-bands referring to f-MWCNTs and vibrational modes corresponding to chemical bonds present in the ether-amine (EA). The electrical responses of the BP to the variation in analyte concentration showed that the sensor differentiates deionized water from ether-amine, as well as the various concentrations present in the different analytes, exhibiting response time of 3.62 ± 0.99 min for the analyte containing 5 vol.% EA and recovery time of 21.16 ± 2.35 min for the analyte containing 10 vol.% EA, revealing its potential as a real-time response chemiresistive sensor.