This project utilises multi-temporal and spatial Earth observation data to identify agricultural features indicative of opium poppy cultivation in Afghanistan.
- DatesSeptember 2017 – December 2021
- Funded£90,000 (NERC-funded DREAM CDT)
- PartnersUnited Nations Office on Drugs and Crime
The United Nations Office on Drugs and Crime estimates opium poppy cultivation in Afghanistan has increased by 63 % since 2016. The spatial distribution of opium cultivation is constantly evolving due to varying environmental, social and economic pressures. The volume and variety of Earth observation data provides opportunities for agricultural dynamics associated with opium poppy to be extracted from legacy time-series datasets across Afghanistan. The aim of this project is to derive information about seasonal and annual changes in opium poppy cultivation using Earth observation Big Data analytics. This project will also take advantage of emerging cloud technologies for timely image processing of associated vegetation dynamics.
Related publications
- Simms DM, Hamer AM, Zeiler I, Vita L & Waine TW (2023) Mapping agricultural land in Afghanistan’s opium provinces using a generalised deep learning model and medium resolution satellite imagery, Remote Sensing, 15 (19) Article No. 4714.
- Hamer AM, Simms DM & Waine TW (2021) Replacing human interpretation of agricultural land in Afghanistan with a deep convolutional neural network, International Journal of Remote Sensing, 42 (8) 3017-3038. Dataset/s: 10.17862/cranfield.rd.13228634
- Simms DM (2020) Fully convolutional neural nets in-the-wild, Remote Sensing Letters, 11 (12) 1080-1089.
