Wheat is a major crop and staple food covering 80% of the total cereal plantation area in Afghanistan. However, inadequate irrigation systems, climatic conditions such as droughts, changing farming practices, increased incidences of pests and crop disease, increased use of pesticides and insecticides, and inadequate or poor land preparation, among others, hamper wheat productivity. Despite being a significant producer of wheat, Afghanistan still imports the cereal from other countries.
The timely forecast of wheat production is highly important for planning and ensuring food security in cases where shortages are predicted. The Wheat Mapping Application provides information on wheat-growing areas in Afghanistan for 2017. It allows users to generate maps and disaggregated statistics on wheat-growing areas in irrigated and rain-fed land parcels at the provincial or national level in Afghanistan.
The application provides a visualization of data generated by a study on the “Estimation of Wheat Growing Areas in Afghanistan” carried out by the International Centre for Integrated Mountain Development (ICIMOD) and partners under its SERVIR Hindu Kush Himalaya (SERVIR-HKH) Initiative. The study estimated wheat-growing areas in Afghanistan using a phenology-based threshold approach, along with machine-learning classifiers with multi-temporal satellite imagery on the Google Earth Engine platform. In addition to Sentinel 1 and Sentinel 2 satellite imagery from November 2016 to August 2017, the study also used an agriculture mask generated from an FAO land cover map for Afghanistan; high-resolution Pléiades data from Airbus Defence and Space; and ground control points for wheat fields and poppy fields provided by the Ministry of Agriculture, Irrigation and Livestock (MAIL) – Government of Afghanistan and the United Nations Office on Drugs and Crime in Afghanistan for training and validation.
The satellite-derived wheat area estimates were vetted against reference sample points provided by field staff from MAIL. The mean overall accuracy for all provinces for irrigated and rain-fed wheat growing areas was 83.8% and 89.0%, respectively. The generated wheat maps can enable inter-annual comparison for national level planning purposes.
(For more information on accuracy assessment, please contact the author of the dataset.)
Update 24 June 2020
The team published an article "Wheat Area Mapping in Afghanistan Based on Optical and SAR Time-Series Images in Google Earth Engine Cloud Environment" in Frontiers in Environmental Science.
The SERVIR programme, NASA, USAID, and ICIMOD make no express or implied warranty of this application and associated data as to the merchantability or fitness for a particular purpose. Neither the US Government nor its contractors shall be liable for special, consequential, or incidental damages attributed to this application and associated data.
For additional queries on methodology and/or accuracy, please contact firstname.lastname@example.org