Estimating the Agricultural Farm Soil Moisture Using Spectral Indices of Landsat 8, and Sentinel-1, and Artificial Neural Networks

Ghasemloo Nima; Matkan Ali Akbar; Alimohammadi AbbasAghighi HosseinMirbagheri Babak

首页> 外文期刊>Journal of geovisualization and spatial analysis >Estimating the Agricultural Farm Soil Moisture Using Spectral Indices of Landsat 8, and Sentinel-1, and Artificial Neural Networks

【24h】

Estimating the Agricultural Farm Soil Moisture Using Spectral Indices of Landsat 8, and Sentinel-1, and Artificial Neural Networks

机译：使用 Landsat 8 和 Sentinel-1 的光谱指数以及人工神经网络估算农业农场土壤水分

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Knowledge of soil moisture at various stages of agricultural production plays a fundamental role in better managing water resources. Satellite data provide useful information regarding soil moisture and have been frequently used to estimate soil moisture in recent years. The main objective of this study has been to examine the capabilities of integration of the optical and radar images for soil moisture estimation. For this purpose, Landsat 8 and Sentinel-1 satellite imagery and artificial neural networks have been used to measure soil moisture in 30 hectares area of Rosa Damascena Mill farm located at Qom province of Iran. Soil moisture data were collected in the interval between two irrigations of agricultural land as target data. The findings of this study reveal that integration of the spectral indices of normalized difference vegetation index (NDVI) and land surface temperature data (LST) from Landsat 8 and vertical-horizontal polarization (VH) and vertical-vertical polarization (VV) data from Sentinel-1 leads to 10-cm depth soil moisture estimation with root mean square error (RMSE) of 4.9 percent. Positive relations were observed between the soil moisture estimation errors and the distance from the irrigation starting points. Therefore, distance data were utilized as the contextual input information and the spectral data leading to a reduction of the RMSE from 4.9 to 4.6 percent and an eleven percent reduction of the maximum error rate. On the other hand, RMSE of networks with one and two middle layers with 20 neutrons, respectively, were 4.6 and 5.0%. Therefore, in the conditions of this study, one middle layer with 20 neurons yielded better outcomes than those of using two middle layers.

机译：土壤水分在不同阶段的知识农业生产起着根本性的作用更好地管理水资源。关于土壤数据提供有用的信息水分和被频繁使用近年来估算土壤水分。本研究的目的是检查光学和集成的能力对土壤水分估计雷达图像。这个目的,地球资源观测卫星8和Sentinel-1卫星图像和人工神经网络用来测量30公顷地区土壤水分罗莎Damascena轧机农场位于库姆省的伊朗。收集两个治疗之间的时间间隔农业土地作为目标数据。本研究表明,集成的光谱指数归一化差异植被指数(NDVI)和地表从地球资源观测卫星8和温度数据(LST)-水平极化(VH)和vertical-vertical极化(VV)的数据Sentinel-1导致10厘米深度土壤水分估计与均方根误差(RMSE)4.9%。和土壤水分之间的估计错误从灌溉起始点的距离。因此,距离数据被利用语境输入信息和光谱数据导致减少的RMSE 4.9减少到4.6%和百分之一百一十一最大的错误率。1和2的网络中间层20个中子,分别是5.0%和4.6。因此,在本研究的条件下,一个中间层有20个神经元产生更好结果比使用两个中间层。

著录项

来源
《Journal of geovisualization and spatial analysis》 |2022年第2期|共12页
作者
Ghasemloo Nima; Matkan Ali Akbar; Alimohammadi AbbasAghighi HosseinMirbagheri Babak;
展开▼
作者单位

Shahid Beheshti Univ;

KN Toosi Univ Technol;

展开▼
收录信息
原文格式 PDF
正文语种英语
中图分类自然地理学;
关键词
Soil moisture; Precision agriculture; Landsat; Sentinel; Artificial neural network; TERRASAR-X;

机译：土壤墒情;精准农业;Landsat;哨兵;人工神经网络;TERRASAR-X型;

相似文献

外文文献
中文文献

1. Assessing artificial neural networks coupled with wavelet analysis for multi-layer soil moisture dynamics prediction [J] . JunJun Yang, ZhiBin He, WeiJun Zhao, 寒旱区科学（英文版） . 2016,第2期
2. Assessing artificial neural networks coupled with waveletanalysis for multi-layer soil moisture dynamics pr [J] . 寒旱区科学：英文版 . 2016,第002期
3. Optimization of Laser Ablation Technology for PDPhSM Matrix Nanocomposite Thin Film by Artificial Neural Networks-particle Swarm AlgorithmOptimization of Laser Ablation Technology for PDPhSM Matrix Nanocomposite Thin Film by Artificial Neural Networks-particle Swarm AlgorithmOptimization of Laser Ablation Technology for PDPhSM Matrix Nanocomposite Thin Film by Artificial Neural Networks-particle Swarm Algorithm [J] . TANG Puhong, SONG Renguo, CHAI Guozhong, 武汉理工大学学报：材料科学英文版 . 2010,第002期
4. Researchers at Adiyaman University Publish New Study Findings on Artificial Neural Networks (Comparison of Recent Remote Sensing Data Using an Artificial Neural Network to Predict Soil Moisture by Focusing on Radiometric Indices) [J] . Network Daily News . 2023,第16期

机译：Researchers at Adiyaman University Publish New Study Findings on Artificial Neural Networks (Comparison of Recent Remote Sensing Data Using an Artificial Neural Network to Predict Soil Moisture by Focusing on Radiometric Indices)
5. Findings in Artificial Neural Networks Reported from Karadeniz Technical University (Prediction of Soil Water Contents and Erodibility Indices Based On Artificial Neural Networks: Using Topography and Remote Sensing) [J] . Network Daily News . 2022,第17期

机译：Findings in Artificial Neural Networks Reported from Karadeniz Technical University (Prediction of Soil Water Contents and Erodibility Indices Based On Artificial Neural Networks: Using Topography and Remote Sensing)
6. New Findings from University of Toulouse in the Area of Artificial Neural Networks Published (Integrating process-related information into an artificial neural network for root-zone soil moisture prediction) [J] . Network Daily News . 2022,第8期

机译：New Findings from University of Toulouse in the Area of Artificial Neural Networks Published (Integrating process-related information into an artificial neural network for root-zone soil moisture prediction)
7. Monitoring winter wheat drought threat in Northern China using multiple climate-based drought indices and soil moisture during 2000-2013 [O] . Wang H. S., Vicente-Serrano, S. M., Tao, F. L., 2016

机译：monitoring winter wheat drought threat in Northern China using multiple climate-based drought indices and soil moisture during 2000-2013

Estimating the Agricultural Farm Soil Moisture Using Spectral Indices of Landsat 8, and Sentinel-1, and Artificial Neural Networks

摘要

著录项

相似文献

相关主题

期刊订阅