Eyes on the Wild: Visual Data in SANParks
Have you ever wondered how ecologists and conservationists uncover the hidden lives of plants and animals in our fynbos, forests, grasslands, savannas, and the deep blue sea?
The answer lies in the power of conservation technology and the data (information) extracted from it. Over the years, technological advancements have changed how we view, study, and understand the natural world. From camera traps and drones, to baited remote underwater video surveys (BRUVS) and fixed-point photographs, visual data has become a key research and monitoring tool for scientists in SANParks. As part of the 2-year JRS Biodiversity Foundation-funded Biodiversity Data Management project, SANParks is taking important steps towards standardizing and modernizing its systems to manage visual data, such as photographs and videos, collected through multimedia devices like camera traps, drones, and BRUVS.
Camera trapping is a non-intrusive wildlife monitoring technique used to take pictures of animals with a motion sensor or infrared camera. These photographs can be used to identify different species, understand animal behaviour patterns, and study habitat preferences. Camera traps can be left in the field for several weeks or months, providing a cost-effective way to collect data over very large areas, for long periods. SANParks staff are currently using camera traps in 16 national parks for various research and monitoring purposes. These include researching and monitoring species such as the Black rhino (Diceros bicornis), the Knysna Elephant (Loxodonta africana), human-wildlife interactions, species diversity, and relative abundance of species, to mention a few.

Setting up a camera trap in the Garden Route National Park. © Melanie de Morney

Animals snapped on camera traps in some of the National Parks. © SANParks

Deployment of a stereo-BRUV in the Robben Island Marine Protected Area. © Georg Beyer

A Great White Shark (Carcharodon carcharias) and a Pyjama shark (Poroderma africanum) captured by the Baited Remote Underwater Video System. © SANParks
In the marine environment, SANParks uses different techniques and devices to monitor biodiversity. Baited Remote Underwater Video Systems (BRUVS) are used to see and count fish, while fixed-point photographs are used to monitor rocky shores. Photo surveys can identify individual sharks, benthic photograph quadrats examine mudprawn holes in the Knysna Estuary, and underwater cameras survey the endemic Knysna seahorse (Hippocampus capensis).

A Broadnose Sevengill Shark (Notorynchus cepedianus) captured by the Baited Remote Underwater Video System. © SANParks
Drones are used to monitor plant cover and the density of invasive alien plants in some National Parks. Drones take photographs and videos that can be analyzed to determine the densities and age classes of these alien plant species. This type of information can be used to check the success of invasive alien plant-clearing programs. The personal and private use of drones is prohibited in National Parks and Protected Areas in South Africa. Drones may only be used for official purposes when authorized with special permission from the Management Authority.
Fixed-point photographs have been used in parks to monitor changes in vegetation, for example in Camdeboo National Park (previously known as Karoo Nature Reserve), photographs dating from 1988 to 2011 are stored at the Scientific Services Kimberley offices. These fixed-point photographs were used for vegetation monitoring, veld condition assessments, monitoring Spekboom utilization, as well as aerial photographs for monitoring wood utilization. In other parks, fixed-point photographs have been used to monitor changes in vegetation due to factors, such as elephant populations. In Kruger National Park, both fixed-point and aerial photographic surveys have been conducted to monitor environmental changes, and fixed-point photographs are used to monitor the presence and status of species of special concern, for example, Cycads (Encephalartos species). Species of Special Concern are plants and animals that are threatened, protected, and fit other Park specific conservation concern and criteria. However, not all the species of special concern can feasibly be monitored, but there is a selection of priority species that are monitored by SANParks.

Fixed-point photographs taken in Camdeboo National Park (left is 2003, and right is 2010). © SANParks
There are of course limitations and challenges faced with the use of these types of conservation technology. This includes the sheer volume of data collected. For example, camera traps can produce thousands of images per camera deployed, the size of those data files is relatively big, and often there is limited space to store data files. The process involved in uploading or transferring data files is also very tedious. Behind the scenes, scientists working with this type of data often manually sort through the 10 000 plus images collected to group or classify the images for analysis. Just imagine what a daunting task that is!
With this project, we aim to explore different Machine Learning models and Artificial Intelligence software or platforms to improve and speed up the process of working with these types of data. This will allow our scientists to spend more time finding exciting information about our ecosystems from the data. By standardizing and modernizing its data processing systems, SANParks is taking important steps towards better managing and conserving biodiversity using conservation technology. The data collected through these innovative techniques provide important insights into species distribution, behaviour patterns, and habitat preferences, leading to better conservation efforts and greater public support for wildlife protection.