Monitoring of Antarctica's Fragile Vegetation Using Drone-Based Remote Sensing, Multispectral Imagery and AI.

Vegetation in East Antarctica, such as moss and lichen, vulnerable to the effects of climate change and ozone depletion, requires robust non-invasive methods to monitor its health condition. Despite the increasing use of unmanned aerial vehicles (UAVs) to acquire high-resolution data for vegetation analysis in Antarctic regions through artificial intelligence (AI) techniques, the use of multispectral imagery and deep learning (DL) is quite limited. This study addresses this gap with two pivotal contributions: (1) it underscores the potential of deep learning (DL) in a field with notably limited implementations for these datasets; and (2) it introduces an innovative workflow that compares the performance between two supervised machine learning (ML) classifiers: Extreme Gradient Boosting (XGBoost) and U-Net. The proposed workflow is validated by detecting and mapping moss and lichen using data collected in the highly biodiverse Antarctic Specially Protected Area (ASPA) 135, situated near Casey Station, between January and February 2023. The implemented ML models were trained against five classes: Healthy Moss, Stressed Moss, Moribund Moss, Lichen, and Non-vegetated. In the development of the U-Net model, two methods were applied: Method (1) which utilised the original labelled data as those used for XGBoost; and Method (2) which incorporated XGBoost predictions as additional input to that version of U-Net. Results indicate that XGBoost demonstrated robust performance, exceeding 85% in key metrics such as precision, recall, and F1-score. The workflow suggested enhanced accuracy in the classification outputs for U-Net, as Method 2 demonstrated a substantial increase in precision, recall and F1-score compared to Method 1, with notable improvements such as precision for Healthy Moss (Method 2: 94% vs. Method 1: 74%) and recall for Stressed Moss (Method 2: 86% vs. Method 1: 69%). These findings contribute to advancing non-invasive monitoring techniques for the delicate Antarctic ecosystems, showcasing the potential of UAVs, high-resolution multispectral imagery, and ML models in remote sensing applications.

Aerial Mapping of Forests Affected by Pathogens Using UAVs, Hyperspectral Sensors, and Artificial Intelligence.

The environmental and economic impacts of exotic fungal species on natural and plantation forests have been historically catastrophic. Recorded surveillance and control actions are challenging because they are costly, time-consuming, and hazardous in remote areas. Prolonged periods of testing and observation of site-based tests have limitations in verifying the rapid proliferation of exotic pathogens and deterioration rates in hosts. Recent remote sensing approaches have offered fast, broad-scale, and affordable surveys as well as additional indicators that can complement on-ground tests. This paper proposes a framework that consolidates site-based insights and remote sensing capabilities to detect and segment deteriorations by fungal pathogens in natural and plantation forests. This approach is illustrated with an experimentation case of myrtle rust (Austropuccinia psidii) on paperbark tea trees (Melaleuca quinquenervia) in New South Wales (NSW), Australia. The method integrates unmanned aerial vehicles (UAVs), hyperspectral image sensors, and data processing algorithms using machine learning. Imagery is acquired using a Headwall Nano-Hyperspec ® camera, orthorectified in Headwall SpectralView ® , and processed in Python programming language using eXtreme Gradient Boosting (XGBoost), Geospatial Data Abstraction Library (GDAL), and Scikit-learn third-party libraries. In total, 11,385 samples were extracted and labelled into five classes: two classes for deterioration status and three classes for background objects. Insights reveal individual detection rates of 95% for healthy trees, 97% for deteriorated trees, and a global multiclass detection rate of 97%. The methodology is versatile to be applied to additional datasets taken with different image sensors, and the processing of large datasets with freeware tools.

UAVs and Machine Learning Revolutionising Invasive Grass and Vegetation Surveys in Remote Arid Lands.

The monitoring of invasive grasses and vegetation in remote areas is challenging, costly, and on the ground sometimes dangerous. Satellite and manned aircraft surveys can assist but their use may be limited due to the ground sampling resolution or cloud cover. Straightforward and accurate surveillance methods are needed to quantify rates of grass invasion, offer appropriate vegetation tracking reports, and apply optimal control methods. This paper presents a pipeline process to detect and generate a pixel-wise segmentation of invasive grasses, using buffel grass (Cenchrus ciliaris) and spinifex (Triodia sp.) as examples. The process integrates unmanned aerial vehicles (UAVs) also commonly known as drones, high-resolution red, green, blue colour model (RGB) cameras, and a data processing approach based on machine learning algorithms. The methods are illustrated with data acquired in Cape Range National Park, Western Australia (WA), Australia, orthorectified in Agisoft Photoscan Pro, and processed in Python programming language, scikit-learn, and eXtreme Gradient Boosting (XGBoost) libraries. In total, 342,626 samples were extracted from the obtained data set and labelled into six classes. Segmentation results provided an individual detection rate of 97% for buffel grass and 96% for spinifex, with a global multiclass pixel-wise detection rate of 97%. Obtained results were robust against illumination changes, object rotation, occlusion, background cluttering, and floral density variation.

Towards the Automatic Detection of Pre-Existing Termite Mounds through UAS and Hyperspectral Imagery.

The increased technological developments in Unmanned Aerial Vehicles (UAVs) combined with artificial intelligence and Machine Learning (ML) approaches have opened the possibility of remote sensing of extensive areas of arid lands. In this paper, a novel approach towards the detection of termite mounds with the use of a UAV, hyperspectral imagery, ML and digital image processing is intended. A new pipeline process is proposed to detect termite mounds automatically and to reduce, consequently, detection times. For the classification stage, several ML classification algorithms' outcomes were studied, selecting support vector machines as the best approach for their role in image classification of pre-existing termite mounds. Various test conditions were applied to the proposed algorithm, obtaining an overall accuracy of 68%. Images with satisfactory mound detection proved that the method is "resolution-dependent". These mounds were detected regardless of their rotation and position in the aerial image. However, image distortion reduced the number of detected mounds due to the inclusion of a shape analysis method in the object detection phase, and image resolution is still determinant to obtain accurate results. Hyperspectral imagery demonstrated better capabilities to classify a huge set of materials than implementing traditional segmentation methods on RGB images only.

Are A-not-B errors caused by a belief about object location?

Eight- to 12-month-olds might make A-not-B errors, knowing the object is in B but searching at A because of ancillary (attention, inhibitory, or motor memory) deficits, or they might genuinely believe the object is in A (conceptual deficit). This study examined how diligently infants searched for a hidden object they never found. An object was placed in A twice, and then in B. In a different task the object was placed beside A twice, and then in B. Infants made more A-not-B errors in the former task, and perseverating infants searched diligently in A rather than in B. Infants seemed to believe the object was in A, suggesting that both a conceptual deficit and ancillary deficits account for A-not-B errors.

Are there any agricultural effects on the capture rates of male euglossine bees (Apidae: Euglossini)?

During 30 days male euglossine bees were bait-sampled at 12 sites, in the central Pacific coast of Colombia (ten days and four sites at each of three adjacent habitats: farmlands, highly disturbed forest and less disturbed forest) and 487 individuals were captured. Most captured individuals belonged to six species, five widely distributed through the American tropics and an endemic species. Two of the frequently captured species presented no different abundances between habitats, while the other four (67.97% of all the captured individuals), all of them big sized or long-tongued, were more frequently captured at the farmlands. A cluster analysis of the data matrix for the 23 captured species and the 12 sampling sites, grouped together the farmland sites, apart from the forest sites. It is proposed that male euglossine bees from generalist, long-tongued or big sized species, forage frequently at the farmlands, where fragrance or nectar resources may be clumped, less diverse, and present an access restricted by deep corollas or by microclimatic conditions of high temperature and low humidity.