We are researching AI-powered crop identification using satellite imagery, aerial data, and machine learning to classify different crop types across agricultural areas. This work aims to support better monitoring of land use, crop distribution, and agricultural activity over time.

By identifying crops more accurately and consistently, this research can help authorities, farmers, and organisations improve planning, reporting, and decision-making in the agricultural sector.

We are exploring methods to detect and monitor vacant and derelict land using geospatial data, satellite imagery, and AI-based analysis. This research focuses on identifying unused, abandoned, or underutilised land areas that may require further inspection, rehabilitation, or policy action.

The goal is to provide clearer visibility over land condition and usage, helping support urban planning, environmental management, and sustainable land development.

We are researching how satellite imagery, vegetation indices, agronomic data, and soil health information can support better fertilisation planning and crop management. This includes analysing crop health, vegetation patterns, soil conditions, and field variability to better understand where agricultural inputs may be needed and how management practices can improve overall crop productivity and soil performance.

This research aims to support more efficient farming practices, reduce unnecessary fertiliser use, and improve decision-making for healthier and more productive crops.

We are investigating the use of satellite imagery and environmental indicators to monitor desertification and land degradation. This research focuses on detecting changes in vegetation cover, soil exposure, and land condition over time.

By identifying early signs of degradation, this work can help support mitigation strategies, environmental monitoring, and long-term land preservation efforts.