The use of remote sensing for forest health monitoring has increased in popularity over the years, with improved quality in spatial and spectral resolutions. However, satellite revisit times are generally too low to detect real-time changes at a pace fast enough to aid in early management actions. There exists a need to employ higher resolution monitoring to quantify the damage caused by biotic risks which are more difficult to detect, through the diverse affliction of damage spread through time. Sentinel-2 MSI (Multispectral Instrument) data has a spatial resolution varying from 10 - 60 m resolution, and a spectral range of 443 - 2190 nm. Using the strategically located bands and derived vegetation indices, the study achieved an overall accuracy of 89,34% with a Kappa of 0,85 using Extreme Gradient Boosting (XGboost). The following results were found: (1) Sentinel-2 was able to successfully identify baboon damage with high accuracy with field measured data and (2) different severities of damage could be distinguished. Of the various indices calculated it was found that soil adjusted vegetation index (SAVI) and structure insensitive pigment index (SIPI) were the most influential variables due to good discrimination of structural variations in the canopy. The proposed method provides an accurate and repeatable framework for rapid damage mapping at a sub-compartment scale.

Commercial forest plantations in South Africa are homogeneous monocultures of highly bred exotic species grown to deliver timber products of the best potential quality. As such, these stands are susceptible to adverse effects of biotic and abiotic factors, and therefore require intense management to mitigate these risks. A sustainable forest monitoring system that can detect real-time changes in the physiological state of these plantations is needed for timeous management intervention to reduce losses. The use of machine learning algorithms has recently become popular, with acceptable levels of success. This study explores the application of deep learning neural networks for early detection of damage caused by baboons in evergreen plantations of Pinus species. Using PlanetScope imagery (spectral band 590–860 nm), which is captured by a constellation of Dove nanosatellites, with a high temporal resolution available daily at 3 m spatial resolution, the study achieved an overall accuracy of 81.54%, with a kappa value of 0.69, using a deep neural network. In comparison, using a random-forest classifier produced 74.04% accuracy and a kappa value of 0.62. The study successfully mapped different levels of baboon damage within commercial pine forests. We provide a repeatable method for daily monitoring initiatives, and attest to the utility of higher-resolution imagery such as PlanetScope for mapping health and damage severity at the tree level.

The impacts of climate on forestry will influence the tree species planted for commercial use and the ability to adapt to drastic changes in the environment. These changes have promoted the use of technologies such as remote sensing, to monitor compartments, to aid management in decision-making and planning. The use of time series datasets can aid in the understanding and prediction of compartment functioning and health. This study tested the use of Landsat 8 (spectral range 435–2294 nm) level 2 surface reflectance data and climatic variables (such as solar radiation and vapour pressure deficit) to predict tree sap flow measurements over an 8-year period. Using RapidMiner studio for statistical analysis, gradient boosting trees (GBTs) proved successful in achieving an R ² of 0.97 and an RMSE of 2.39 LPD. It is noted that of all the species that were tested (i.e. Pinus radiata , P . elliotii , Ocotea bullata , Ilex mitis , Podocarpus latifolius , P . elliotii , Eucalyptus grandis x E . nitens and E . dunnii ), the RMSE was greatly reduced with the exclusion of the pine tree species, to a reduced error rate of 0.78. This suggests that using satellite data, for modelling tree sap flow of pine trees has more variation. Nevertheless, this study has proved successful in forecasting sap flow and will contribute to future research in forest health monitoring, as well as to refine the use of time series information to predict sap flow velocity in forest plantation trees.

Remote sensing has provided a means to cover large areas of forest compartments through monitoring health and improving, sustainability of forest stands. The continued threat of existing pathogens, as well as the introduction of new pests or diseases, will require monitoring to aid in these practices. Thus, there exists a need to acquire information from the physiological process of plants that can potentially be related to stress, to aid in management and planning. Foliar temperature is directly linked to plant functions such as transpiration and stomatal conductance. Furthermore, a constant increase in temperature may indicate a lack of plant cooling and thus indicate water or pathogen stress. Thus, there is potential for temperature to be used as a representative of forest health, by indicating the presence of stress. This study succeeded in classifying disease manifestation affecting tree performance at a compartment level, by investigating the applicability of the thermal capabilities of a handheld FLIR camera, Landsat 9 and drone images to detect foliar damage from a pathogen. All three sensors scored high in algorithm scoring. The highest correlation of 72.2%, was found between drone and Landsat 9 images. Accuracies of the algorithms used, namely Deep Learning and Generalized Linear Model, obtained 98.9% and 97.3% respectively. Both these algorithms are suited for future research. The findings in this study suggests that thermal applications can contribute to future research, as part of a framework of forest health monitoring.

Visual assessments of growing forest nursery plants are time-consuming and often result in a lack of information at a physiological level. There exists a need for health screening in nurseries, that is fast and efficient, to improve overall health monitoring and nursery productivity. Rapid handheld sensors such as rapid thermal devices, leaf porometers and moisture meters, can provide regular information at a physiological level, that can improve the understanding of the impact of stress on young plant cuttings and their decline in health over time. This paper evaluates the utility and reliability of contemporary sensor technologies, to operationally monitor stress phases in juvenile forest plant cuttings during progressive moisture (dry-down) conditions. Furthermore, to assess whether thermal sensors could be used as an indicator, in conjunction with other variables such as soil water content or stomatal conductance, is needed operationally for fast screening during limited planting windows. Near Infra-Red Analysis (NiRA) data was collected to understand detailed plant functions at a finer reflectance level. A relationship was found where the increase in thermal signals reflects a depletion of water content, resulting in an eventual decline in stomatal conductance and, ultimately, plant mortality. Several algorithms were used in a preliminary test, using RapidMiner software, to discriminate between the four phases of plant health decline using physiological variables and NiRA data. Both Gradient Boosting Trees (GBT) and Deep Learning (DL) showed the best performances, achieving favourable accuracies of 96.8% and 91.2% without NiRA data, 84.6% and 88.2% with NiRA data, with shorter training times. Using thermal technology weighted amongst the highest of the best performing variables using GBT, the utility and accuracy showed good discrimination between the stages of plant decline and is encouraged for future research in this field.