- Remote Sensing in Agriculture
- Land Use and Ecosystem Services
- Smart Agriculture and AI
- Remote Sensing and LiDAR Applications
- Soil Geostatistics and Mapping
- Species Distribution and Climate Change
- Rangeland Management and Livestock Ecology
- Crop Yield and Soil Fertility
- Agriculture Sustainability and Environmental Impact
- Rangeland and Wildlife Management
- Ecology and Vegetation Dynamics Studies
- Remote-Sensing Image Classification
- Wildlife Ecology and Conservation
- Spectroscopy and Chemometric Analyses
- Sustainable Agricultural Systems Analysis
Institute for Soil, Climate and Water
2021-2024
Agricultural Research Council of South Africa
2021-2024
University of Pretoria
2021-2022
Wheat is an important staple crop in the global food chain. The production of wheat many regions constrained by lack use advanced technologies for monitoring. Unmanned Aerial Vehicles (UAVs) platform remote sensing providing near real-time farm-scale information. This information aids making recommendations monitoring and improving management to ensure security. study appraised scientific research trends on UAV studies between 2005 2021, using a bibliometric method. 398 published documents...
Optimizing the prediction of maize (Zea mays L.) yields in smallholder farming systems enhances crop management and thus contributes to reducing hunger achieving one Sustainable Development Goals (SDG 2—zero hunger). This research investigated capability unmanned aerial vehicle (UAV)-derived data machine learning algorithms estimate yield evaluate its spatiotemporal variability through phenological cycle Bronkhorstspruit, South Africa, where UAV collection took over four dates...
Remote sensing data play a crucial role in precision agriculture and natural resource monitoring. The use of unmanned aerial vehicles (UAVs) can provide solutions to challenges faced by farmers managers due its high spatial resolution flexibility compared satellite remote sensing. This paper presents UAV spectral datasets collected from different provinces South Africa, covering crops at the farm level as well resources. consist five multispectral bands corrected for atmospheric effects...
Monitoring crop growth conditions during the growing season provides information on available soil nutrients and health status, which are important for agricultural management practices. Crop frequently varies due to site-specific climate farm These variations might arise from sub-field-scale heterogeneities in composition, moisture levels, sunlight, diseases. Therefore, properties biophysical data useful predict field-scale development. This study investigates spectral indices derived...
Reducing food insecurity in developing countries is one of the crucial targets Sustainable Development Goals (SDGs). Smallholder farmers play a role combating insecurity. However, local planning agencies and governments do not have adequate spatial information on smallholder farmers, this affects monitoring SDGs. This study utilized Sentinel-1 multi-temporal data to develop framework for mapping maize farms estimate production area as parameter supporting We used Principal Component Analysis...
Weed invasion of crop fields, such as maize, is a major threat leading to yield reductions or right-offs for smallholder farming, especially in developing countries. A synoptic view and timeous detection weed invasions can save the crop. The sustainable development goals (SDGs) have identified food security focus point. objectives this study are to: (1) assess precision mapping maize-weed infestations using multi-temporal, unmanned aerial vehicle (UAV), PlanetScope data by utilizing machine...
Nitrogen is one of the key nutrients that indicate soil quality and an important component for plant development. Accurate knowledge management nitrogen crucial food security in rural communities, especially smallholder maize farms. However, less research has been done on generating digital maps these farmers. This study examines utility Sentinel-2 satellite data environmental variables to map at Three machine learning algorithms—random forest (RF), gradient boosting (GB), extreme (XG) were...
Rural communities rely on smallholder maize farms for subsistence agriculture, the main driver of local economic activity and food security. However, their planted area estimates are unknown in most developing countries. This study explores use Sentinel-1 Sentinel-2 data to map farms. The random forest (RF), support vector (SVM) machine learning algorithms model stacking (ST) were applied. Results show that classification combined improved RF, SVM ST by 24.2%, 8.7%, 9.1%, respectively,...
Monitoring crop height during different growth stages provides farmers with valuable information important for managing and improving expected yields. The use of synthetic aperture radar Sentinel-1 (S-1) Optical Sentinel-2 (S-2) satellites useful datasets that can assist in monitoring development. However, studies exploring synergetic SAR S-1 optical S-2 satellite data biophysical parameters are limited. We utilized a time-series monthly independently then used synergistically to model...
An Earth observation system (EOS) is essential in monitoring and improving our understanding of how natural managed agricultural landscapes change over time or respond to climate overgrazing. Such changes can be quantified using a pasture model (PM), critical tool for pastures driven by the growing population demands change-related challenges thus ensuring sustainable food production system. This study used bibliometric method assess global scientific research trends EOS PM studies from 1979...
Invasive alien plants (IAPs) are responsible for loss in biodiversity and the depletion of water resources natural ecosystems. Prosopis species IAPs previously introduced by farmers to provide shade fodder livestock. In Northern Cape, spp. invasions associated with native resulting overgrazing degrading rangelands. Mapping glandulosa is essential management initiatives assist government minimising spread impact IAPs. This study aims evaluate performance two machine learning algorithms i.e.,...
Crop growth and yield often vary, not only between farms, but also at the sub-field level. These variations can stem from heterogeneities of soil plant biophysical parameters. This means that data be used to predict intra-field crop variability. study properties vegetation indices (VIs) derived unmanned aerial vehicle (UAV) imagery as predictor variables, monthly measurements height (cm) a response variable rate in two winter wheat farms South Africa. datasets were analyzed using regression...
Grasslands cover approximately 40% of the Earth’s surface. Thus, they play a pivotal role in supporting biodiversity, ecosystem services, and human livelihoods. These ecosystems provide crucial habitats for specialized plant animal species, act as carbon sinks to mitigate climate change, are vital agriculture pastoralism. However, grasslands face ongoing threats from certain factors, like land use changes, overgrazing, change. Geospatial technologies have become indispensable manage protect...
Mapping smallholder maize farms in complex and uneven rural terrain is a major barrier to accurately documenting the spatial representation of farming units. Remote sensing technologies rely on various satellite products for differentiating cropland cover from other land types. The potential multi-temporal Sentinel-1 synthetic aperture radar (SAR), Sentinel-2, digital elevation model (DEM) precipitation data obtained Climate Hazards Group InfraRed Precipitation with Station (CHIRPS) version...