The impact of agricultural transformation on water quality in a data-scarce, dryland landscape-a case study in the Bot River, South Africa.

Transformation of natural vegetation to cultivated fields has resulted in marked increases in water quality degradation and nutrient loading of rivers globally. In many developing countries, monitoring and evaluating the impacts of agriculture on water quality are limited by financial constraints and focus is given to large water bodies. This paper presents and discusses the results of a year-long monitoring of a typical river system in an agricultural setting, namely the Bot River, Western Cape, South Africa. Results show seasonal increases in N concentrations and SRP driven by surrounding agricultural activities. Water chemistry and changes to nutrient loads were found to be site specific, which demonstrates that monitoring programmes focussing on one or two sites are not representative of the entire catchment. Monitoring and reporting of small river systems are thus un(der)-represented in large databases such as the UN Global Environment Monitoring System for Freshwater (GEMS/Water) programme. The results highlight the importance of selecting appropriate and representative monitoring sites for these rivers when budgetary constraints limit the number of points that can be monitored sustainably. The findings should also be applicable to similar catchments in the Western Cape and beyond as they demonstrate the magnitude of seasonal nutrient fluxes in the system.

Investigating the Utility of Oblique Tree-Based Ensembles for the Classification of Hyperspectral Data.

Ensemble classifiers are being widely used for the classification of spectroscopic data. In this regard, the random forest (RF) ensemble has been successfully applied in an array of applications, and has proven to be robust in handling high dimensional data. More recently, several variants of the traditional RF algorithm including rotation forest (rotF) and oblique random forest (oRF) have been applied to classifying high dimensional data. In this study we compare the traditional RF, rotF, and oRF (using three different splitting rules, i.e., ridge regression, partial least squares, and support vector machine) for the classification of healthy and infected Pinus radiata seedlings using high dimensional spectroscopic data. We further test the robustness of these five ensemble classifiers to reduced spectral resolution by spectral resampling (binning) of the original spectral bands. The results showed that the three oblique random forest ensembles outperformed both the traditional RF and rotF ensembles. Additionally, the rotF ensemble proved to be the least robust of the five ensembles tested. Spectral resampling of the original bands provided mixed results. Nevertheless, the results demonstrate that using spectral resampled bands is a promising approach to classifying asymptomatic stress in Pinus radiata seedlings.

Corrigendum: Evolution of tandem repeats is mirroring post-polyploid cladogenesis in Heliophila (Brassicaceae).

[This corrects the article DOI: 10.3389/fpls.2020.607893.].

Evolution of Tandem Repeats Is Mirroring Post-polyploid Cladogenesis in Heliophila (Brassicaceae).

The unigeneric tribe Heliophileae encompassing more than 100 Heliophila species is morphologically the most diverse Brassicaceae lineage. The tribe is endemic to southern Africa, confined chiefly to the southwestern South Africa, home of two biodiversity hotspots (Cape Floristic Region and Succulent Karoo). The monospecific Chamira (C. circaeoides), the only crucifer species with persistent cotyledons, is traditionally retrieved as the closest relative of Heliophileae. Our transcriptome analysis revealed a whole-genome duplication (WGD) ∼26.15-29.20 million years ago, presumably preceding the Chamira/Heliophila split. The WGD was then followed by genome-wide diploidization, species radiations, and cladogenesis in Heliophila. The expanded phylogeny based on nuclear ribosomal DNA internal transcribed spacer (ITS) uncovered four major infrageneric clades (A-D) in Heliophila and corroborated the sister relationship between Chamira and Heliophila. Herein, we analyzed how the diploidization process impacted the evolution of repetitive sequences through low-coverage whole-genome sequencing of 15 Heliophila species, representing the four clades, and Chamira. Despite the firmly established infrageneric cladogenesis and different ecological life histories (four perennials vs. 11 annual species), repeatome analysis showed overall comparable evolution of genome sizes (288-484 Mb) and repeat content (25.04-38.90%) across Heliophila species and clades. Among Heliophila species, long terminal repeat (LTR) retrotransposons were the predominant components of the analyzed genomes (11.51-22.42%), whereas tandem repeats had lower abundances (1.03-12.10%). In Chamira, the tandem repeat content (17.92%, 16 diverse tandem repeats) equals the abundance of LTR retrotransposons (16.69%). Among the 108 tandem repeats identified in Heliophila, only 16 repeats were found to be shared among two or more species; no tandem repeats were shared by Chamira and Heliophila genomes. Six "relic" tandem repeats were shared between any two different Heliophila clades by a common descent. Four and six clade-specific repeats shared among clade A and C species, respectively, support the monophyly of these two clades. Three repeats shared by all clade A species corroborate the recent diversification of this clade revealed by plastome-based molecular dating. Phylogenetic analysis based on repeat sequence similarities separated the Heliophila species to three clades [A, C, and (B+D)], mirroring the post-polyploid cladogenesis in Heliophila inferred from rDNA ITS and plastome sequences.

Impact of ecological redundancy on the performance of machine learning classifiers in vegetation mapping.

Vegetation maps are models of the real vegetation patterns and are considered important tools in conservation and management planning. Maps created through traditional methods can be expensive and time-consuming, thus, new more efficient approaches are needed. The prediction of vegetation patterns using machine learning shows promise, but many factors may impact on its performance. One important factor is the nature of the vegetation-environment relationship assessed and ecological redundancy. We used two datasets with known ecological redundancy levels (strength of the vegetation-environment relationship) to evaluate the performance of four machine learning (ML) classifiers (classification trees, random forests, support vector machines, and nearest neighbor). These models used climatic and soil variables as environmental predictors with pretreatment of the datasets (principal component analysis and feature selection) and involved three spatial scales. We show that the ML classifiers produced more reliable results in regions where the vegetation-environment relationship is stronger as opposed to regions characterized by redundant vegetation patterns. The pretreatment of datasets and reduction in prediction scale had a substantial influence on the predictive performance of the classifiers. The use of ML classifiers to create potential vegetation maps shows promise as a more efficient way of vegetation modeling. The difference in performance between areas with poorly versus well-structured vegetation-environment relationships shows that some level of understanding of the ecology of the target region is required prior to their application. Even in areas with poorly structured vegetation-environment relationships, it is possible to improve classifier performance by either pretreating the dataset or reducing the spatial scale of the predictions.

Random Forest (RF) Wrappers for Waveband Selection and Classification of Hyperspectral Data.

Hyperspectral data collected using a field spectroradiometer was used to model asymptomatic stress in Pinus radiata and Pinus patula seedlings infected with the pathogen Fusarium circinatum. Spectral data were analyzed using the random forest algorithm. To improve the classification accuracy of the model, subsets of wavebands were selected using three feature selection algorithms: (1) Boruta; (2) recursive feature elimination (RFE); and (3) area under the receiver operating characteristic curve of the random forest (AUC-RF). Results highlighted the robustness of the above feature selection methods when used in conjunction with the random forest algorithm for analyzing hyperspectral data. Overall, the Boruta feature selection algorithm provided the best results. When discriminating F. circinatum stress in Pinus radiata seedlings, Boruta selected wavebands (n = 69) yielded the best overall classification accuracies (training error of 17.00%, independent test error of 17.00% and an AUC value of 0.91). Classification results were, however, significantly lower for P. patula seedlings, with a training error of 24.00%, independent test error of 38.00%, and an AUC value of 0.65. A hybrid selection method that utilizes combinations of wavebands selected from the three feature selection algorithms was also tested. The hybrid method showed an improvement in classification accuracies for P. patula, and no improvement for P. radiata. The results of this study provide impetus towards implementing a hyperspectral framework for detecting stress within nursery environments.

Predicting runoff-induced pesticide input in agricultural sub-catchment surface waters: linking catchment variables and contamination.

An urgent need exists for applicable methods to predict areas at risk of pesticide contamination within agricultural catchments. As such, an attempt was made to predict and validate contamination in nine separate sub-catchments of the Lourens River, South Africa, through use of a geographic information system (GIS)-based runoff model, which incorporates geographical catchment variables and physicochemical characteristics of applied pesticides. We compared the results of the prediction with measured contamination in water and suspended sediment samples collected during runoff conditions in tributaries discharging these sub-catchments. The most common insecticides applied and detected in the catchment over a 3-year sampling period were azinphos-methyl (AZP), chlorpyrifos (CPF) and endosulfan (END). AZP was predominantly found in water samples, while CPF and END were detected at higher levels in the suspended particle samples. We found positive (p < 0.002) correlations between the predicted average loss and the concentrations of the three insecticides both in water and suspended sediments (r between 0.87 and 0.94). Two sites in the sub-catchment were identified as posing the greatest risk to the Lourens River mainstream. It is assumed that lack of buffer strips, presence of erosion rills and high slopes are the main variables responsible for the high contamination at these sites. We conclude that this approach to predict runoff-related surface water contamination may serve as a powerful tool for risk assessment and management in South African orchard areas.