Artificial neural networks and adaptive neuro-fuzzy inference systems for prediction of soil respiration in forested areas southern Brazil.

The purpose of this study was to estimate the temporal variability of CO2 emission (FCO2) from O2 influx into the soil (FO2) in a reforested area with native vegetation in the Brazilian Cerrado, as well as to understand the dynamics of soil respiration in this ecosystem. The database is composed of soil respiration data, agroclimatic variables, improved vegetation index (EVI), and soil attributes used to train machine learning algorithms: artificial neural network (ANN) and an adaptive neuro-fuzzy inference system (ANFIS). The predictive performance was evaluated based on the mean absolute error (MEA), root mean square error (RMSE), mean absolute percentage error (MAPE), agreement index (d), confidence coefficient (c), and coefficient of determination (R2). The best estimation results for validation were FCO2 with multilayer perceptron neural network (MLP) (R2 = 0.53, RMSE = 0.967 µmol m-2 s-1) and radial basis function neural network (RBF) (R2 = 0.54, RMSE = 0.884 µmol m-2 s-1) and FO2 with MLP (R2 = 0.45, RMSE = 0.093 mg m-2 s-1) and RBF (R2 = 0.74, 0.079 mg m-2 s-1). Soil temperature and macroporosity are important predictors of FCO2 and FO2. The best combination of variables for training the ANFIS was selected based on trial and error. The results were as follows: FCO2 (R2 = 16) and FO2 (R2 = 29). In all models, FCO2 outperformed FO2. A primary factor analysis was performed, and FCO2 and FO2 correlated best with the weather and soil attributes, respectively.

Machine learning for prediction of soil CO2 emission in tropical forests in the Brazilian Cerrado.

Soil CO2 emission (FCO2) is a critical component of the global carbon cycle, but it is a source of great uncertainty due to the great spatial and temporal variability. Modeling of soil respiration can strongly contribute to reducing the uncertainties associated with the sources and sinks of carbon in the soil. In this study, we compared five machine learning (ML) models to predict the spatiotemporal variability of FCO2 in three reforested areas: eucalyptus (RE), pine (RP) and native species (RNS). The study also included a generalized scenario (GS) where all the data from RE, RP and RNS were included in one dataset. The ML models include generalized regression neural network (GRNN), radial basis function neural network (RBFNN), multilayer perceptron neural network (MLPNN), adaptive neuro-fuzzy inference system (ANFIS) and random forest (RF). Initially, we had 32 attributes and after pre-processing, including Pearson's correlation, canonical correlation analysis (CCA), and biophysical justification, only 21 variables remained. We used as input variables 19 soil properties and climate variables in reforested areas of eucalyptus, pine and native species. RF was the best model to predict soil respiration to RE [adjusted coefficient of determination (R2 adj): 0.70 and root mean square error (RMSE): 1.02 µmol m-2 s-1], RP (R2 adj: 0.48 and RMSE: 1.07 µmol m-2 s-1) and GS (R2 adj: 0.70 and RMSE: 1.05 µmol m-2 s-1). Our findings support that RF and GRNN are promising for predicting soil respiration of reforested areas which could help to identify and monitor potential sources and sinks of the main additional greenhouse gas over ecosystems.

Complete chloroplast genome of Myracrodruon urundeuva and its phylogenetics relationships in Anacardiaceae family.

Continuous exploratory use of tree species is threatening the existence of several plants in South America. One of these threatened species is Myracroduron urundeuva, highly exploited due to the high quality and durability of its wood. The chloroplast (cp) has been used for several evolutionary studies as well traceability of timber origin, based on its gene sequences and simple sequence repeats (SSR) variability. Cp genome organization is usually consisting of a large single copy and a small single copy region separated by two inverted repeats regions. We sequenced the complete cp genome from M. urundeuva based on Illumina next-generation sequencing. Our results show that the cp genome is 159,883 bp in size. The 36 SSR identified ranging from mono- to hexanucleotides. Positive selection analysis revealed nine genes related to photosystem, protein synthesis, and DNA replication, and protease are under positive selection. Genome comparison a other Anacardiaceae chloroplast genomes showed great variability in the family. The phylogenetic analysis using complete chloroplast genome sequences of other Anacardiaceae family members showed a close relationship with two other economically important genera, Pistacia and Rhus. These results will help future investigations of timber monitoring and population and evolutionary studies. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s12298-021-00989-1.

Development of microsatellite markers for Myracrodruon urundeuva (F.F. & M.F. Allemão), a highly endangered species from tropical forest based on next-generation sequencing.

Myracrodruon urundeuva is a tree species of high economic importance due the strength and durability of its wood. Threatened of extinction in Brazil, it is present only in a few forest remnants, mostly in conservation units. Currently, there is little information on the genetic diversity of natural populations in Brazil and even less information about the genome of this species. Here, new species-specific microsatellite loci were developed based on next-generation sequencing (Illumina). More than 100,000 loci were identified in the run, with di- to hexanucleotides motifs. Of these, 20 loci were selected for validation in 30 individuals, with 15 successfully polymorphic loci detected. The number of alleles ranged among loci from 3 to 16, with an average of 7.73, expected (H e ) and observed (H o ) heterozygosity ranged from 0.246 to 0.902 and from 0.103 to 0.867, respectively. These results point out that these new set of markers has a great potential for use in population genetic studies for genetic conservation of the species.