Satellite-based tree cover mapping for forest conservation in the drylands of Sub Saharan Africa (SSA): Application to Burkina Faso gazetted forests

Q1 Economics, Econometrics and Finance

Development Engineering Pub Date : 2019-01-01 DOI:10.1016/j.deveng.2018.100039

Guigonan Serge Adjognon , Alexis Rivera-Ballesteros , Daan van Soest

{"title":"Satellite-based tree cover mapping for forest conservation in the drylands of Sub Saharan Africa (SSA): Application to Burkina Faso gazetted forests","authors":"Guigonan Serge Adjognon , Alexis Rivera-Ballesteros , Daan van Soest","doi":"10.1016/j.deveng.2018.100039","DOIUrl":null,"url":null,"abstract":"<div><p>While monitoring the effectiveness of forest conservation programs requires accurate data on (changes in) forest cover, many countries still lack the ability to map local forest inventory, especially in the drylands of Africa where forest areas are very sparsely covered. In this paper, we present a high resolution tree cover estimation of twelve gazetted forests in Burkina Faso using Random Forest-based supervised classification and Sentinel-2 satellite imagery sensed between March and April 2016. The methodology relies on ground truth sample points labeled manually over 10-m resolution images displaying a composite of near infrared (NIR), red and green bands extracted from Sentinel-2 multi-spectral satellite data to estimate tree cover with an average balanced accuracy rate of 80 percent. The output is a collection of rasters with binary values representing the combination of 10, and down-sampled 20 and 60-m bands indicating an estimate of the existence of trees or lack thereof, usable as a baseline for deforestation monitoring.</p></div>","PeriodicalId":37901,"journal":{"name":"Development Engineering","volume":"4 ","pages":"Article 100039"},"PeriodicalIF":0.0000,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.deveng.2018.100039","citationCount":"17","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Development Engineering","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2352728517300891","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Economics, Econometrics and Finance","Score":null,"Total":0}

引用次数: 17

Abstract

While monitoring the effectiveness of forest conservation programs requires accurate data on (changes in) forest cover, many countries still lack the ability to map local forest inventory, especially in the drylands of Africa where forest areas are very sparsely covered. In this paper, we present a high resolution tree cover estimation of twelve gazetted forests in Burkina Faso using Random Forest-based supervised classification and Sentinel-2 satellite imagery sensed between March and April 2016. The methodology relies on ground truth sample points labeled manually over 10-m resolution images displaying a composite of near infrared (NIR), red and green bands extracted from Sentinel-2 multi-spectral satellite data to estimate tree cover with an average balanced accuracy rate of 80 percent. The output is a collection of rasters with binary values representing the combination of 10, and down-sampled 20 and 60-m bands indicating an estimate of the existence of trees or lack thereof, usable as a baseline for deforestation monitoring.

查看原文本刊更多论文

用于撒哈拉以南非洲旱地森林保护的基于卫星的树木覆盖制图:在布基纳法索宪报公布的森林中的应用

虽然监测森林保护方案的有效性需要关于森林覆盖(变化)的准确数据，但许多国家仍然缺乏绘制当地森林清查图的能力，特别是在森林覆盖非常稀少的非洲旱地。在本文中，我们使用基于随机森林的监督分类和2016年3月至4月期间Sentinel-2卫星遥感图像，对布基纳法索12个公告森林进行了高分辨率的树木覆盖估算。该方法依赖于人工标记的地面真实样本点超过10米分辨率的图像，显示从Sentinel-2多光谱卫星数据中提取的近红外(NIR)，红色和绿色波段的复合图像，以估计树木覆盖，平均平衡准确率为80%。输出是一组栅格，其二进制值代表10米和20米和60米采样带的组合，表明树木存在或缺乏的估计，可用作森林砍伐监测的基线。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Development Engineering Economics, Econometrics and Finance-Economics, Econometrics and Finance (all)

CiteScore

4.90

自引率

0.00%

发文量

审稿时长

31 weeks

期刊介绍： Development Engineering: The Journal of Engineering in Economic Development (Dev Eng) is an open access, interdisciplinary journal applying engineering and economic research to the problems of poverty. Published studies must present novel research motivated by a specific global development problem. The journal serves as a bridge between engineers, economists, and other scientists involved in research on human, social, and economic development. Specific topics include: • Engineering research in response to unique constraints imposed by poverty. • Assessment of pro-poor technology solutions, including field performance, consumer adoption, and end-user impacts. • Novel technologies or tools for measuring behavioral, economic, and social outcomes in low-resource settings. • Hypothesis-generating research that explores technology markets and the role of innovation in economic development. • Lessons from the field, especially null results from field trials and technical failure analyses. • Rigorous analysis of existing development "solutions" through an engineering or economic lens. Although the journal focuses on quantitative, scientific approaches, it is intended to be suitable for a wider audience of development practitioners and policy makers, with evidence that can be used to improve decision-making. It also will be useful for engineering and applied economics faculty who conduct research or teach in "technology for development."