Wheat Area Mapping in Afghanistan Based on Optical and SAR Time-Series Images in Google Earth Engine Cloud Environment

Varun Tiwari,Mir A Matin,Walter Lee Ellenburg,Waheedullah Yusafi,Begum Rabeya Rushi,Faisal M Qamer,Krishna Vadrevu,Birendra Bajracharya

doi:10.3389/fenvs.2020.00077

Abstract

Wheat is cultivated on more than 2.7 million hectares in Afghanistan annually, yet the country is dependent on imports to meet domestic demand. The timely estimation of domestic wheat production is highly critical to address any potential food security issues and has been identified as a priority by the Ministry of Agriculture Irrigation and Livestock (MAIL). In this study, we developed a system for in-season mapping of wheat crop area based on both optical (Sentinel-2) and synthetic aperture radar (SAR, Sentinel-1) data to support estimation of wheat cultivated area for management and food security planning. Utilizing a 2010 Food and Agriculture Organization(FAO) cropland mask, wheat sown area for 2017 was mapped integrating decision trees and machine learning algorithms in the Google Earth Engine cloud platform. Information from provincial crop calendars in addition to training and validation data from field-based surveys, and high-resolution Digitalglobe and Airbus Pleiades images were used for classification and validation. The total irrigated and rainfed wheat area were estimated as 912,525 ha and 562,611 ha respectively for 2017. Province-wise accuracy assessments show the maximum accuracy of irrigated (IR) and rainfed (RF) wheat across provinces was 98.76 % and 99% respectively, whereas the minimum accuracy was found to be 48% (IR) and 73% (RF). The lower accuracy is attributed to the unavailability of reference data, cloud cover in the satellite images and overlap of spectral reflectance of wheat with other crops, especially in the opium poppy growing provinces. While the method is designed to provide estimation at different stages of the growing season, the best accuracy is achieved at the end of harvest using time-series satellite data for the whole season. The approach followed in the study can be used to generate wheat area maps for other years to aid in food security planning and policy decisions.

Highlights

The agricultural sector in Afghanistan supports the livelihoods of nearly three-quarters of the total population and contributes nearly 28% to the Gross Domestic Product (GDP) (Muradi and Boz, 2018)
Through collaborative efforts with Ministry of Agriculture Irrigation and Livestock (MAIL) and other organizations in Afghanistan, we present a detailed study that develops a map of wheat sown areas utilizing advanced satellite remote sensing techniques which can be used to address food security planning and management in the country
Crop growth patterns for Laghman province are shown in Figures 5A, 6A which depict vineyards having distinct signals compared to wheat areas during the sowing season

Summary

Introduction

The agricultural sector in Afghanistan supports the livelihoods of nearly three-quarters of the total population and contributes nearly 28% to the Gross Domestic Product (GDP) (Muradi and Boz, 2018). About 1 million tons (equivalent to 25% of internal demand) of wheat are imported annually to meet internal requirements (Martínez and Gilabert, 2009). And effective management and estimation of wheat production in Afghanistan are of high importance for overall food security. It can help in managing local food demand and provide stability for social security (Tilman et al, 2011). It can support decision-makers in national-level planning for formulation and implementation of policies related to food procurement, pricing, importexport, transportation and storage, advance planning, etc. It can support decision-makers in national-level planning for formulation and implementation of policies related to food procurement, pricing, importexport, transportation and storage, advance planning, etc. (United Nations, 2013; Pham et al, 2017)

Methods

Results

Conclusion