Alexander Bleasdale

I am a postdoctoral researcher specialising in the application of remote sensing and AI to vegetation studies. My current work explores the feasibility of using camera trap networks to monitor forest phenology and habitat provision. I aim to demonstrate the broader value of camera trapping beyond traditional wildlife research, and to establish links between camera trap data and satellite imagery to enhance our understanding of vegetation–wildlife interactions.

My research centres on developing and implementing low-cost, practical sensing methods for observing environmental phenomena. I believe that the more accessible these techniques become, the more widely they can be adopted, amplifying their overall benefit to environmental research. In addition, I am passionate about the responsible use of AI within academia, and how advances in image classification can enable large-scale, high-resolution environmental monitoring.

My research at SLU focuses on establishing a framework for utilising camera trap networks to monitor habitat provision parameters. I am investigating the potential and applicability of camera traps, supported by AI tools, to extract vegetation-related information from habitats. This includes identifying endangered and invasive species, counting flowers and fruit, and measuring forest structure and phenology. This work is part of Big Picture, a Biodiversa+ funded project that aims to develop data management and analytical tools to integrate and enhance professional and citizen science camera-trapping initiatives across Europe.

During my PhD, I explored the use of novel sensing systems and deep learning for vegetation monitoring in agricultural contexts. In my thesis, “The Early Detection of Apple Scab Using Multispectral Imagery Under Natural Illumination Conditions”, I developed a low-cost, high-resolution multispectral imaging system capable of detecting apple scab infections earlier than standard RGB cameras under natural environmental conditions. By applying deep convolutional neural networks to classify multispectral imagery, I demonstrated that apple scab and other common diseases could be identified both rapidly and accurately. I found that near-infrared imagery provided a superior approach for early disease detection, and that a rapid, accurate, and accessible method for automated orchard monitoring was achievable.

Currently, I am applying deep learning classifiers to existing camera trap datasets to observe vegetation phenological cycles, specifically green-up and senescence, of individual plant species within Swedish forests. I aim to investigate variations between locations, species, and satellite observations. Monitoring changes in the seasonal timing of plant life cycles is essential for understanding atmosphere–biosphere interactions and the timing of key wildlife events

2025 – Present: Post-doctoral Researcher - Department of Wildlife, Fish and Environmental Studies, Swedish University of Agricultural Sciences, Sweden

2024 – 2025: Research Associate - Lancaster Environment Centre, Lancaster University, United Kingdom

2019 – 2024: Environmental Science (PhD) - Lancaster Environment Centre, Lancaster University, United Kingdom

2017 – 2018: Environmental Management (MSc) - Lancaster Environment Centre, Lancaster University, United Kingdom

2013 – 2017: Mechanical Engineering (Beng) - Coventry University, United Kingdom

Bleasdale, A.J. and Whyatt, J.D., 2025. Classifying early apple scab infections in multispectral imagery using convolutional neural networks. Artificial Intelligence in Agriculture, 15(1), pp.39-51. https://doi.org/10.1016/j.aiia.2024.10.001

Bleasdale, A., 2024. The Early Detection of Apple Scab Using Multispectral Imagery Under Natural Illumination Conditions (Doctoral dissertation, Lancaster University (United Kingdom)).

Bleasdale, A.J., Blackburn, G.A. and Whyatt, J.D., 2022. Feasibility of detecting apple scab infections using low-cost sensors and interpreting radiation interactions with scab lesions. International Journal of Remote Sensing, 43(13), pp.4984-5005. https://doi.org/10.1080/01431161.2022.2122895