Laser-Induced Breakdown Spectroscopy Associated with the Design of Experiments and Machine Learning for Discrimination of Brachiaria brizantha Seed Vigor.

Laser-induced breakdown spectroscopy (LIBS) associated with machine learning algorithms (ML) was used to evaluate the Brachiaria seed physiological quality by discriminating the high and low vigor seeds. A 23 factorial design was used to optimize the LIBS experimental parameters for spectral analysis. A total of 120 samples from two distinct cultivars of Brachiaria brizantha seeds exhibiting high vigor (HV) and low vigor (LV) in standard tests were studied. The raw LIBS spectra were normalized and submitted to outlier verification, previously to the reduction data dimensionality from principal component analysis. Supervised machine learning algorithm parameters were chosen by leave-one-out cross-validation in the test samples, and it was tested by external validation using a new set of data. The overall accuracy in external validation achieved 100% for HV and LV discrimination, regardless of the cultivar or the classification algorithm.

Total phosphorus determination in eutrophic tropical river sediments by laser-induced breakdown spectroscopy techniques.

Total phosphorus (TP) in sediments is an important chemical variable in the study of the extent of eutrophication in water bodies. Two methods, based on single pulse (SP) and double pulse (DP) laser-induced breakdown spectroscopy (LIBS), were developed for determining TP in the sediment cores of Brazilian rivers upstream from the Barra Bonita reservoir. TP concentration in the sediments was determined by inductively coupled plasma optical emission spectrometry (ICP OES) on digested samples. Besides, a LIBS system operating in SP and DP modes was used to develop methods for TP quantification in sediment pellets. In LIBS, the most appropriate wavelength to measure P was 214.91 nm. The calibration curves showed correlation coefficients of 0.93 and 0.92 and limits of detection of 709 mg kg-1 and 349 mg kg-1 for SP and DP LIBS, respectively. The two proposed methods were validated and the average percentage errors were 14% and 10% for SP and DP LIBS, respectively. The ICP OES and SP and DP LIBS data showed that the most superficial layers of the Piracicaba River, all the sedimentary layers of the Tietê River, and the confluence region present a high concentration of TP, according to the Brazilian sediment quality criterion. In conclusion, SP and DP LIBS were confirmed as promising alternative tools to traditional analytical methods for monitoring the TP content in the sediments that come from different hydrographic units. The proposed method using DP LIBS proved more sensitive than SP LIBS, but the SP LIBS method demonstrated enough precision for determining TP in eutrophic river sediments.