Extraction of Saline Soil Distributions Using Different Salinity Indices and Deep Neural Networks
Soil salinization has become one of the major environmental problems threatening food security. The identification and knowledge of the spatial distributions of soil salinization are key in addressing this problem. This study assumes that a good saline land identification effect can be obtained with...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-09-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/14/18/4647 |
_version_ | 1797482747923529728 |
---|---|
author | Qianyi Gu Yang Han Yaping Xu Huitian Ge Xiaojie Li |
author_facet | Qianyi Gu Yang Han Yaping Xu Huitian Ge Xiaojie Li |
author_sort | Qianyi Gu |
collection | DOAJ |
description | Soil salinization has become one of the major environmental problems threatening food security. The identification and knowledge of the spatial distributions of soil salinization are key in addressing this problem. This study assumes that a good saline land identification effect can be obtained with the help of deep learning methods. Therefore, this study used the OLI sensor data from the Landsat-8, based on the U<sup>2</sup>-Network, and proposes a method to extract saline land from remote sensing images. The study also adds different salinity indices (SI, SI1, and SI2) to explore its impact on classification accuracy. Through our method, accurate saline soil distribution information were obtained, and several verification indicators (the Intersection-over-Union (IoU), recall, precision, and F1-score) were all measured above 0.8. In addition, compared with the multi-spectral training results, the classification accuracy increased after adding a specific salinity index, and most of the accuracy indices increased by about 2% (the IoU increased by 3.70%, recall increased by 1.50%, precision increased by 2.81%, and F1-score increased by 2.13%). In addition, we also included a case study based on our methodology to analyze the distribution characteristics and changes of saline soil in the Zhenlai area of Northeast China from 2016 to 2020. We found that the area of saline land in the Zhenlai area has reduced, which shows that the extraction method proposed in this study is feasible. Overall, this paper indicates that deep learning-based methods can efficiently extract the salinity of soil and enhance the mapping of its spatial distribution. The study has the broad impact of supplementing satellite imagery for salinity modeling and helping to guide agricultural land management practices for northeastern China and other salinized regions. |
first_indexed | 2024-03-09T22:37:55Z |
format | Article |
id | doaj.art-98f586464b9a41edb13e761d89ad3367 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-09T22:37:55Z |
publishDate | 2022-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-98f586464b9a41edb13e761d89ad33672023-11-23T18:46:13ZengMDPI AGRemote Sensing2072-42922022-09-011418464710.3390/rs14184647Extraction of Saline Soil Distributions Using Different Salinity Indices and Deep Neural NetworksQianyi Gu0Yang Han1Yaping Xu2Huitian Ge3Xiaojie Li4Key Laboratory of Geographical Processes and Ecological Security in Changbai Mountains, Ministry of Education, School of Geographical Sciences, Northeast Normal University, Changchun 130024, ChinaKey Laboratory of Geographical Processes and Ecological Security in Changbai Mountains, Ministry of Education, School of Geographical Sciences, Northeast Normal University, Changchun 130024, ChinaDepartment of Plant Sciences, University of Tennessee, Knoxville, TN 37996, USAKey Laboratory of Geographical Processes and Ecological Security in Changbai Mountains, Ministry of Education, School of Geographical Sciences, Northeast Normal University, Changchun 130024, ChinaNortheast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130102, ChinaSoil salinization has become one of the major environmental problems threatening food security. The identification and knowledge of the spatial distributions of soil salinization are key in addressing this problem. This study assumes that a good saline land identification effect can be obtained with the help of deep learning methods. Therefore, this study used the OLI sensor data from the Landsat-8, based on the U<sup>2</sup>-Network, and proposes a method to extract saline land from remote sensing images. The study also adds different salinity indices (SI, SI1, and SI2) to explore its impact on classification accuracy. Through our method, accurate saline soil distribution information were obtained, and several verification indicators (the Intersection-over-Union (IoU), recall, precision, and F1-score) were all measured above 0.8. In addition, compared with the multi-spectral training results, the classification accuracy increased after adding a specific salinity index, and most of the accuracy indices increased by about 2% (the IoU increased by 3.70%, recall increased by 1.50%, precision increased by 2.81%, and F1-score increased by 2.13%). In addition, we also included a case study based on our methodology to analyze the distribution characteristics and changes of saline soil in the Zhenlai area of Northeast China from 2016 to 2020. We found that the area of saline land in the Zhenlai area has reduced, which shows that the extraction method proposed in this study is feasible. Overall, this paper indicates that deep learning-based methods can efficiently extract the salinity of soil and enhance the mapping of its spatial distribution. The study has the broad impact of supplementing satellite imagery for salinity modeling and helping to guide agricultural land management practices for northeastern China and other salinized regions.https://www.mdpi.com/2072-4292/14/18/4647Landsat-8land degradationdeep learningsalinity index |
spellingShingle | Qianyi Gu Yang Han Yaping Xu Huitian Ge Xiaojie Li Extraction of Saline Soil Distributions Using Different Salinity Indices and Deep Neural Networks Remote Sensing Landsat-8 land degradation deep learning salinity index |
title | Extraction of Saline Soil Distributions Using Different Salinity Indices and Deep Neural Networks |
title_full | Extraction of Saline Soil Distributions Using Different Salinity Indices and Deep Neural Networks |
title_fullStr | Extraction of Saline Soil Distributions Using Different Salinity Indices and Deep Neural Networks |
title_full_unstemmed | Extraction of Saline Soil Distributions Using Different Salinity Indices and Deep Neural Networks |
title_short | Extraction of Saline Soil Distributions Using Different Salinity Indices and Deep Neural Networks |
title_sort | extraction of saline soil distributions using different salinity indices and deep neural networks |
topic | Landsat-8 land degradation deep learning salinity index |
url | https://www.mdpi.com/2072-4292/14/18/4647 |
work_keys_str_mv | AT qianyigu extractionofsalinesoildistributionsusingdifferentsalinityindicesanddeepneuralnetworks AT yanghan extractionofsalinesoildistributionsusingdifferentsalinityindicesanddeepneuralnetworks AT yapingxu extractionofsalinesoildistributionsusingdifferentsalinityindicesanddeepneuralnetworks AT huitiange extractionofsalinesoildistributionsusingdifferentsalinityindicesanddeepneuralnetworks AT xiaojieli extractionofsalinesoildistributionsusingdifferentsalinityindicesanddeepneuralnetworks |