The high dimensionality of hyperspectral data constitutes a challenge for species classification. This study assessed 1) whether tree species classification can be optimized with the selection of bands which relate to known plant properties and 2) whether a partial least square (PLS) transformation improve species classification above principal component analysis (PCA). Leaf spectra between 400 and 2500 nm were measured for six evergreen tree species in the spring of 2011, in the KwaZulu-Natal Province of South Africa. Twenty-two bands which relate to pigment, foliage biomass, nutrients, and leaf structural components were selected from the hyperspectral data set. The 2100 bands of 1 nm were resampled to 421 bands at 5 nm spectral resolution, ensuring the number of variables are less than the number of samples. The random forest (RF) classification algorithm was used to assess the accuracy for both PCA and PLS transformations on the 421 and 22 bands. The accuracy of individual species classes was calculated as the average of ten iterations, for each data reduction option. The three 22-band models resulted in comparable accuracies to the 421-band classifications (OA of 84 ± 4.9% for untransformed, 78 ± 5% for PCA, and 84 ± 4% for PLS) and no significant differences between the 421 and 22-band models (p > 0.4). The optimized PLS model (22 bands, 8 components) showed a 6% (p <; 0.01) increase in accuracy above the optimized PCA model (22 bands, 3 components). Reducing hyperspectral data to bands which relate to plant properties, and the use of PLS for data transformation, optimizes species classification.

The virus SARS-CoV-2 has resulted in numerous modelling approaches arising rapidly to understand the spread of the disease COVID-19 and to plan for future interventions. Herein, we present an SEIR model with a spatial spread component as well as four infectious compartments to account for the variety of symptom levels and transmission rate. The model takes into account the pattern of spatial vulnerability in South Africa through a vulnerability index that is based on socioeconomic and health susceptibility characteristics. Another spatially relevant factor in this context is level of mobility throughout. The thesis of this study is that without the contextual spatial spread modelling, the heterogeneity in COVID-19 prevalence in the South African setting would not be captured. The model is illustrated on South African COVID-19 case counts and hospitalisations.

This article reflects discussions German and South African Earth scientists, statisticians and risk analysts had on occasion of two bilateral workshops on Data Integration Technologies for Earth System Modelling and Resource Management. The workshops were held in October 2012 at Leipzig, Germany, and April 2013 at Pretoria, South Africa, and were attended by about 70 researchers, practitioners and data managers of both countries. Both events were arranged as part of the South African-German Year of Science 2012/2013. The South African National Research Foundation (NRF, UID 81579) has supported the two workshops as part of the South African–German Year of Science activities 2012/2013 established by the German Federal Ministry of Education and Research and the South African Department of Science and Technology.

Hyperspectral sensors capture and compute spectral reflectance of objects over many wavelength bands, resulting in a high-dimensional space with enough information to differentiate between spectrally similar objects. Due to the curse of dimensionality, high spectral dimensionality can also be difficult to handle and analyse, demanding complex processing and the use of advanced analytical techniques. Moreover, when hyperspectral measurements are taken at different temporal frequencies, separation is likely to improve; however, additional complexities in modelling time variability concurrently with this high spectral dimensionality may be created. As a result, the applicability of ensemble-based techniques suitable for high-dimensional data is examined in this research, together with the statistical evaluation of time-induced variability, since spectral measurements of tree species were taken at different time periods. Classification errors for the stochastic gradient boosting (SGB) and random forest (RF) methods ranged between 5.6% and 13.5%, respectively. Differences in classification accuracy or errors were also accounted for in the assessment of the models, with up to 46% of variation in classification error due to the effect of time in the RF model, indicating that measurement time is important in improving discrimination between tree species. This is because optical leaf characteristics can vary during the course of the year due to seasonal effects, health status, or the developmental stage of a tree. Different spectral properties (assumed from relevant wavelength bands) were found to be key factors impacting the models’ discrimination performance at various measurement times.

In South Africa, a team of analysts has for some years been using statistical techniques to predict election outcomes during election nights in South Africa. The prediction method involves using statistical clusters based on past voting patterns to predict final election outcomes, using a small number of released vote counts. With the US presidential elections in November 2016 hitting the global media headlines during the time period directly after successful predictions were done for the South African elections, the team decided to investigate adapting their meth-od to forecast the final outcome in the US elections. In particular, it was felt that the time zone differences between states would affect the time at which results are released and thereby provide a window of opportunity for doing election night prediction using only the early results from the eastern side of the US. Testing the method on the US presidential elections would have two advantages: it would determine whether the core methodology could be generalised, and whether it would work to include a stronger spatial element in the modelling, since the early results released would be spatially biased due to time zone differences. This paper presents a high-level view of the overall methodology and how it was adapted to predict the results of the US presidential elections. A discussion on the clustering of spatial units within the US is also provided and the spatial distribution of results together with the Electoral College prediction results from both a ‘test-run’ and the final 2016 presidential elections are given and analysed.