Spatial prediction of soil salinity: Remote sensing and machine learning approach

IF 1.7 4区 地球科学 Q3 GEOSCIENCES, MULTIDISCIPLINARY
Thenmozhi Thangarasu , Hanan Abdullah Mengash , Randa Allafi , Hany Mahgoub
{"title":"Spatial prediction of soil salinity: Remote sensing and machine learning approach","authors":"Thenmozhi Thangarasu ,&nbsp;Hanan Abdullah Mengash ,&nbsp;Randa Allafi ,&nbsp;Hany Mahgoub","doi":"10.1016/j.jsames.2025.105440","DOIUrl":null,"url":null,"abstract":"<div><div>Soil salinity significantly affects agricultural productivity and land sustainability, necessitating efficient monitoring and predictive strategies. This study leverages remote sensing data and machine learning algorithms to spatially predict soil salinity across the Puerto Vallarta region, covering an area of 716.03 km<sup>2</sup>. To enhance prediction accuracy, a diverse set of indices were employed, including Salinity Indices (SI 1, SI 2, SI 3, and SI 11), Intensity Indices (INT 1 and INT 2), Brightness Index (BI), Soil-Adjusted Vegetation Index (SAVI), Enhanced Vegetation Index (EVI), Normalized Difference Vegetation Index (NDVI), and the ratio of spectral bands (B2 and B5). These indices deliver appreciated understandings into soil and vegetation properties, allowing accurate classification and salinity assessment. Soil salinity was categorized into five classes: Very Low (16.54%), Low (23.16%), Moderate (21.97%), High (19.95%), and Very High (18.38%). The machine learning models employed for this study included Random Forest (RF), Artificial Neural Network (ANN), and Support Vector Machine (SVM). Among these, RF exhibited the highest prediction accuracy (92.1%), followed by ANN (89.5%) and Support Vector Machine (86.2%). These results underscore the potential of RF as a robust tool for analyzing spatially complex environmental datasets. Integrating remote sensing parameters and machine learning algorithms demonstrates an effective approach for mapping and managing soil salinity. The findings support sustainable land management by pinpointing critical salinity zones that need urgent intervention. Furthermore, the methodology established in this learning can be practical to other regions facing parallel challenges. This research highlights the significance of data-driven approaches in environmental monitoring and resource management.</div></div>","PeriodicalId":50047,"journal":{"name":"Journal of South American Earth Sciences","volume":"156 ","pages":"Article 105440"},"PeriodicalIF":1.7000,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of South American Earth Sciences","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0895981125001026","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"GEOSCIENCES, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

Soil salinity significantly affects agricultural productivity and land sustainability, necessitating efficient monitoring and predictive strategies. This study leverages remote sensing data and machine learning algorithms to spatially predict soil salinity across the Puerto Vallarta region, covering an area of 716.03 km2. To enhance prediction accuracy, a diverse set of indices were employed, including Salinity Indices (SI 1, SI 2, SI 3, and SI 11), Intensity Indices (INT 1 and INT 2), Brightness Index (BI), Soil-Adjusted Vegetation Index (SAVI), Enhanced Vegetation Index (EVI), Normalized Difference Vegetation Index (NDVI), and the ratio of spectral bands (B2 and B5). These indices deliver appreciated understandings into soil and vegetation properties, allowing accurate classification and salinity assessment. Soil salinity was categorized into five classes: Very Low (16.54%), Low (23.16%), Moderate (21.97%), High (19.95%), and Very High (18.38%). The machine learning models employed for this study included Random Forest (RF), Artificial Neural Network (ANN), and Support Vector Machine (SVM). Among these, RF exhibited the highest prediction accuracy (92.1%), followed by ANN (89.5%) and Support Vector Machine (86.2%). These results underscore the potential of RF as a robust tool for analyzing spatially complex environmental datasets. Integrating remote sensing parameters and machine learning algorithms demonstrates an effective approach for mapping and managing soil salinity. The findings support sustainable land management by pinpointing critical salinity zones that need urgent intervention. Furthermore, the methodology established in this learning can be practical to other regions facing parallel challenges. This research highlights the significance of data-driven approaches in environmental monitoring and resource management.
土壤盐分空间预测:遥感与机器学习方法
土壤盐分严重影响农业生产力和土地可持续性,因此需要有效的监测和预测策略。本研究利用遥感数据和机器学习算法对巴亚尔塔港地区的土壤盐度进行了空间预测,该地区面积为716.03平方公里。为了提高预测精度,采用了盐度指数(SI 1、SI 2、SI 3和SI 11)、强度指数(INT 1和INT 2)、亮度指数(BI)、土壤调整植被指数(SAVI)、增强植被指数(EVI)、归一化植被指数(NDVI)和光谱波段比(B2和B5)等多种指标。这些指数提供了对土壤和植被特性的理解,允许准确的分类和盐度评估。土壤盐度分为极低(16.54%)、低(23.16%)、中等(21.97%)、高(19.95%)和极高(18.38%)5个等级。本研究采用的机器学习模型包括随机森林(RF)、人工神经网络(ANN)和支持向量机(SVM)。其中,射频预测准确率最高(92.1%),其次是人工神经网络(89.5%)和支持向量机(86.2%)。这些结果强调了RF作为分析空间复杂环境数据集的强大工具的潜力。整合遥感参数和机器学习算法证明了一种有效的方法来绘制和管理土壤盐分。研究结果通过确定需要紧急干预的关键盐度区域来支持可持续土地管理。此外,在这种学习中建立的方法对面临类似挑战的其他区域也可以实用。本研究强调了数据驱动方法在环境监测和资源管理中的重要性。
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 South American Earth Sciences
Journal of South American Earth Sciences 地学-地球科学综合
CiteScore
3.70
自引率
22.20%
发文量
364
审稿时长
6-12 weeks
期刊介绍: Papers must have a regional appeal and should present work of more than local significance. Research papers dealing with the regional geology of South American cratons and mobile belts, within the following research fields: -Economic geology, metallogenesis and hydrocarbon genesis and reservoirs. -Geophysics, geochemistry, volcanology, igneous and metamorphic petrology. -Tectonics, neo- and seismotectonics and geodynamic modeling. -Geomorphology, geological hazards, environmental geology, climate change in America and Antarctica, and soil research. -Stratigraphy, sedimentology, structure and basin evolution. -Paleontology, paleoecology, paleoclimatology and Quaternary geology. New developments in already established regional projects and new initiatives dealing with the geology of the continent will be summarized and presented on a regular basis. Short notes, discussions, book reviews and conference and workshop reports will also be included when relevant.
×
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