Monitoring and forecasting desertification and land degradation using remote sensing and machine learning techniques in Sistan plain, Iran

IF 2.2 4区 地球科学 Q2 GEOSCIENCES, MULTIDISCIPLINARY
Zohreh Hashemi, Hamid Sodaeizadeh, Mohammad Hossien Mokhtari, Mohammad Ali Hakimzadeh Ardakani, Kazem Kamali Aliabadi
{"title":"Monitoring and forecasting desertification and land degradation using remote sensing and machine learning techniques in Sistan plain, Iran","authors":"Zohreh Hashemi,&nbsp;Hamid Sodaeizadeh,&nbsp;Mohammad Hossien Mokhtari,&nbsp;Mohammad Ali Hakimzadeh Ardakani,&nbsp;Kazem Kamali Aliabadi","doi":"10.1016/j.jafrearsci.2024.105375","DOIUrl":null,"url":null,"abstract":"<div><p>Monitoring and predicting desertification in arid regions are crucial for addressing environmental and societal challenges. Remote sensing is vital for tracking land surfaces and ecosystems changes. The study aims to use remote sensing-based data to monitor and predict desertification in the Sistan Plain through a data screening approach. The study's satellite data consisted of Landsat 5 and 8 images taken in June each year over 10 years (1990–2020). Remote sensing-based indices, including land use and land cover (LULC) map, normalized differential vegetation index (NDVI), improved vegetation index (EVI), vegetation condition index (VCI), surface temperature condition index (TCI), modified normalized differential water level index (MNDWI) and salinity index (SI) were used in the study. In addition to satellite data, environmental indices, including standardized precipitation index (SPI) and streamflow drought index (SDI), were used. The study employed the random forest (RF) method and the mixed model of automated cells and Markov chain (CA-Markov) to monitor desertification and quantitatively predict its condition in 2030. Root-mean-square error (RMSE) and mean-square error (MSE) indicators were used to evaluate the error. Based on the findings, the RF correlation coefficient (R2) and RMSE were obtained about 0.97 and 0.08, respectively. High coefficient values and low RMSE values indicate that the random forest model is highly efficient in assessing desertification for the study period from 1990 to 2020. The change detection method revealed that desertification increased from 1990 to 2010 but decreased from 2010 to 2020. The decreasing trend is expected to continue until 2030. The Kappa coefficient for the prediction of desertification in 2030 was found to be 0.94, which indicates a correct classification based on the collected samples. In addition, the study identified the SI and SDI as effective indices in the desertification process in the study area. Overall, this study provides valuable insights into monitoring and predicting desertification, which could help develop appropriate strategies for managing and controlling desertification in the Sistan Plain through remote sensing and machine learning techniques.</p></div>","PeriodicalId":14874,"journal":{"name":"Journal of African Earth Sciences","volume":"218 ","pages":"Article 105375"},"PeriodicalIF":2.2000,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of African Earth Sciences","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1464343X24002085","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GEOSCIENCES, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

Monitoring and predicting desertification in arid regions are crucial for addressing environmental and societal challenges. Remote sensing is vital for tracking land surfaces and ecosystems changes. The study aims to use remote sensing-based data to monitor and predict desertification in the Sistan Plain through a data screening approach. The study's satellite data consisted of Landsat 5 and 8 images taken in June each year over 10 years (1990–2020). Remote sensing-based indices, including land use and land cover (LULC) map, normalized differential vegetation index (NDVI), improved vegetation index (EVI), vegetation condition index (VCI), surface temperature condition index (TCI), modified normalized differential water level index (MNDWI) and salinity index (SI) were used in the study. In addition to satellite data, environmental indices, including standardized precipitation index (SPI) and streamflow drought index (SDI), were used. The study employed the random forest (RF) method and the mixed model of automated cells and Markov chain (CA-Markov) to monitor desertification and quantitatively predict its condition in 2030. Root-mean-square error (RMSE) and mean-square error (MSE) indicators were used to evaluate the error. Based on the findings, the RF correlation coefficient (R2) and RMSE were obtained about 0.97 and 0.08, respectively. High coefficient values and low RMSE values indicate that the random forest model is highly efficient in assessing desertification for the study period from 1990 to 2020. The change detection method revealed that desertification increased from 1990 to 2010 but decreased from 2010 to 2020. The decreasing trend is expected to continue until 2030. The Kappa coefficient for the prediction of desertification in 2030 was found to be 0.94, which indicates a correct classification based on the collected samples. In addition, the study identified the SI and SDI as effective indices in the desertification process in the study area. Overall, this study provides valuable insights into monitoring and predicting desertification, which could help develop appropriate strategies for managing and controlling desertification in the Sistan Plain through remote sensing and machine learning techniques.

利用遥感和机器学习技术监测和预测伊朗锡斯坦平原的荒漠化和土地退化情况
监测和预测干旱地区的荒漠化对于应对环境和社会挑战至关重要。遥感对于跟踪地表和生态系统变化至关重要。本研究旨在通过数据筛选方法,利用基于遥感的数据监测和预测锡斯坦平原的荒漠化。该研究的卫星数据包括 10 年内(1990-2020 年)每年 6 月拍摄的 Landsat 5 和 8 图像。研究采用了基于遥感的指数,包括土地利用和土地覆盖(LULC)图、归一化差异植被指数(NDVI)、改进植被指数(EVI)、植被状况指数(VCI)、地表温度状况指数(TCI)、修正归一化差异水位指数(MNDWI)和盐度指数(SI)。除卫星数据外,还使用了环境指数,包括标准化降水指数(SPI)和溪流干旱指数(SDI)。研究采用随机森林(RF)方法和自动单元与马尔科夫链混合模型(CA-Markov)监测荒漠化,并定量预测 2030 年的荒漠化状况。采用均方根误差(RMSE)和均方误差(MSE)指标对误差进行评估。结果表明,射频相关系数(R2)和均方根误差(RMSE)分别约为 0.97 和 0.08。较高的系数值和较低的均方误差值表明,随机森林模型在评估 1990 至 2020 年研究期间的荒漠化方面具有很高的效率。变化检测方法显示,荒漠化在 1990 年至 2010 年期间有所增加,但在 2010 年至 2020 年期间有所减少。预计这种下降趋势将持续到 2030 年。2030 年荒漠化预测的卡帕系数为 0.94,这表明根据收集的样本进行的分类是正确的。此外,研究还发现,SI 和 SDI 是研究区域荒漠化过程中的有效指数。总之,这项研究为监测和预测荒漠化提供了宝贵的见解,有助于通过遥感和机器学习技术为管理和控制锡斯坦平原的荒漠化制定适当的战略。
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
Journal of African Earth Sciences
Journal of African Earth Sciences 地学-地球科学综合
CiteScore
4.70
自引率
4.30%
发文量
240
审稿时长
12 months
期刊介绍: The Journal of African Earth Sciences sees itself as the prime geological journal for all aspects of the Earth Sciences about the African plate. Papers dealing with peripheral areas are welcome if they demonstrate a tight link with Africa. The Journal publishes high quality, peer-reviewed scientific papers. It is devoted primarily to research papers but short communications relating to new developments of broad interest, reviews and book reviews will also be considered. Papers must have international appeal and should present work of more regional than local significance and dealing with well identified and justified scientific questions. Specialised technical papers, analytical or exploration reports must be avoided. Papers on applied geology should preferably be linked to such core disciplines and must be addressed to a more general geoscientific audience.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信