Savanna ecosystems are challenging to map and monitor as their vegetation is highly dynamic in space and time. Understanding the structural diversity and biomass distribution of savanna vegetation requires high-resolution measurements over large areas and at regular time intervals. These requirements cannot currently be met through field-based inventories nor spaceborne satellite remote sensing alone. UAV-based remote sensing offers potential as an intermediate scaling tool, providing acquisition flexibility and cost-effectiveness. Yet despite the increased availability of lightweight LiDAR payloads, the suitability of UAV-based LiDAR for mapping and monitoring savanna 3D vegetation structure is not well established. We mapped a 1 ha savanna plot with terrestrial-, mobile- and UAV-based laser scanning (TLS, MLS, and ULS), in conjunction with a traditional field-based inventory (n = 572 stems > 0.03 m). We treated the TLS dataset as the gold standard against which we evaluated the degree of complementarity and divergence of structural metrics from MLS and ULS. Sensitivity analysis showed that MLS and ULS canopy height models (CHMs) did not differ significantly from TLS-derived models at spatial resolutions greater than 2 m and 4 m respectively. Statistical comparison of the resulting point clouds showed minor over- and under-estimation of woody canopy cover by MLS and ULS, respectively. Individual stem locations and DBH measurements from the field inventory were well replicated by the TLS survey (R${}^2$ = 0.89, RMSE = 0.024 m), which estimated above-ground woody biomass to be 7% greater than field-inventory estimates (44.21 Mg ha${}^{-1}$ vs 41.08 Mg ha${}^{-1}$). Stem DBH could not be reliably estimated directly from the MLS or ULS, nor indirectly through allometric scaling with crown attributes (R${}^2$ = 0.36, RMSE = 0.075 m). MLS and ULS show strong potential for providing rapid and larger area capture of savanna vegetation structure at resolutions suitable for many ecological investigations; however, our results underscore the necessity of nesting TLS sampling within these surveys to quantify uncertainty. Complementing large area MLS and ULS surveys with TLS sampling will expand our options for the calibration and validation of multiple spaceborne LiDAR, SAR, and optical missions.

Vegetation plays a key role in the environmental function of wetlands. The Ramsar-listed wetlands of the Magela Creek floodplain in Northern Australia are identified as being at risk from weeds, fire and climate change. In addition, the floodplain is a downstream receiving environment for the Ranger Uranium Mine. Accurate methods for mapping wetland vegetation are required to provide contemporary baselines of annual vegetation dynamics on the floodplain to assist with analysing any potential change during and after minesite rehabilitation. The aim of this study was to develop and test the applicability of geographic object-based image analysis including decision tree classification to classify WorldView-2 imagery and LiDAR-derived ancillary data to map the aquatic vegetation communities of the Magela Creek floodplain. Results of the decision tree classification were compared against a Random Forests classification. The resulting maps showed the 12 major vegetation communities that exist on the Magela Creek floodplain and their distribution for May 2010. The decision tree classification method provided an overall accuracy of 78% which was significantly higher than the overall accuracy of the Random Forests classification (67%). Most of the error in both classifications was associated with confusion between spectrally similar classes dominated by grasses, such as Hymenachne and Pseudoraphis. In addition, the extent of the sedge Eleocharis was under-estimated in both cases. This suggests the method could be useful for mapping wetlands where statistical-based supervised classifications have achieved less than satisfactory results. Based upon the results, the decision tree method will form part of an ongoing operational monitoring program.

This study explores the efficacy of drone-acquired RGB images and the YOLO model in detecting the invasive species Siam weed (Chromolaena odorata) in natural environments. Siam weed is a perennial scrambling shrub from tropical and sub-tropical America that is invasive outside its native range, causing substantial environmental and economic impacts across Asia, Africa, and Oceania. First detected in Australia in northern Queensland in 1994 and later in the Northern Territory in 2019, there is an urgent need to determine the extent of its incursion across vast, rugged areas of both jurisdictions and a need for distribution mapping at a catchment scale. This study tests drone-based RGB imaging to train a deep learning model that contributes to the goal of surveying non-native vegetation at a catchment scale. We specifically examined the effects of input training images, solar illumination, and model complexity on the model’s detection performance and investigated the sources of false positives. Drone-based RGB images were acquired from four sites in the Townsville region of Queensland to train and test a deep learning model (YOLOv5). Validation was performed through expert visual interpretation of the detection results in image tiles. The YOLOv5 model demonstrated over 0.85 in its F1-Score, which improved to over 0.95 with improved exposure to the images. A reliable detection model was found to be sufficiently trained with approximately 1000 image tiles, with additional images offering marginal improvement. Increased model complexity did not notably enhance model performance, indicating that a smaller model was adequate. False positives often originated from foliage and bark under high solar illumination, and low exposure images reduced these errors considerably. The study demonstrates the feasibility of using YOLO models to detect invasive species in natural landscapes, providing a safe alternative to the current method involving human spotters in helicopters. Future research will focus on developing tools to merge duplicates, gather georeference data, and report detections from large image datasets more efficiently, providing valuable insights for practical applications in environmental management at the catchment scale.