Supervised soil salinity estimation and mapping for potential crop cultivation based on multi-date SAR Sentinel-1A imagery: a case study in the wet coast of Jiangsu Province, China

Jianjun Wang ^1,2, Quan Yin ^3,4, Jiali Shang ⁵

¹Jiangsu Key Laboratory of Crop Genetics and Physiology/Jiangsu Key Laboratory of Crop Cultivation and Physiology, Agricultural College of Yangzhou University, Yangzhou, 225009, China. wangjianjun@yzu.edu.cn.
²Jiangsu Co-Innovation Center for Modern Production Technology of Grain Crops, Yangzhou University, Yangzhou, 225009, China. wangjianjun@yzu.edu.cn.
³Jiangsu Key Laboratory of Crop Genetics and Physiology/Jiangsu Key Laboratory of Crop Cultivation and Physiology, Agricultural College of Yangzhou University, Yangzhou, 225009, China.
⁴Jiangsu Co-Innovation Center for Modern Production Technology of Grain Crops, Yangzhou University, Yangzhou, 225009, China.
⁵Ottawa Research and Development Centre, Agriculture and Agri-Food Canada, Ottawa, ON, K1A OC6, Canada.
⁶School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu, 611731, China.
⁷Joint International Research Laboratory of Agriculture and Agricultural Product Safety, Yangzhou University, Yangzhou, 225009, Jiangsu, China.
⁸Institute of Marine Geology and Resources, Ocean College, Zhejiang University, Zhoushan, 316021, China.
⁹College of Life and Health Sciences, Anhui Science and Technology University, Fengyang, 233100, China.
¹⁰Jiangsu Key Laboratory of Crop Genetics and Physiology/Jiangsu Key Laboratory of Crop Cultivation and Physiology, Agricultural College of Yangzhou University, Yangzhou, 225009, China. qgdai@yzu.edu.cn.
¹¹Jiangsu Co-Innovation Center for Modern Production Technology of Grain Crops, Yangzhou University, Yangzhou, 225009, China. qgdai@yzu.edu.cn.

⁰Jiangsu Key Laboratory of Crop Genetics and Physiology/Jiangsu Key Laboratory of Crop Cultivation and Physiology, Agricultural College of Yangzhou University, Yangzhou, 225009, China. wangjianjun@yzu.edu.cn.

Environmental Geochemistry and Health +

|

May 6, 2025

View abstract on PubMed

Summary

Mapping soil salinity on wet coasts is now feasible using machine learning and multi-date Synthetic Aperture Radar (SAR) data. This approach accurately estimates salinity, aiding in crop selection and soil management in humid regions.

Area Of Science

Environmental Science
Remote Sensing
Agricultural Science

Background

Soil salinity remote sensing is crucial for agriculture, especially in coastal areas.
Previous studies primarily focused on arid regions, with limited success in humid zones due to moisture and vegetation interference.
Synthetic Aperture Radar (SAR) data offers potential for cloud-prone wet coasts.

Purpose Of The Study

To demonstrate the feasibility of mapping soil salinity on China's wet east coast using machine learning and multi-date SAR data.
To develop and compare Support Vector Regression (SVR) and Random Forest Regression (RFR) models for soil salinity estimation.
To create an image-based framework for accurate and accessible soil salinity assessment.

Main Methods

Utilized Sentinel-1A SAR imagery from 15 individual dates.
Employed recursive feature elimination to screen SAR variables.
Developed and validated SVR and RFR models using two field surveys (June 17 and July 21, 2017).
Implemented tenfold cross-validation to minimize overfitting and uncertainty.

Main Results

SVR models significantly outperformed RFR models.
High accuracy was achieved with SVR models: R²=0.98 and R²=0.92 for the two survey dates, respectively.
The models effectively mapped spatial soil salinity distribution and temporal changes.
The framework successfully estimated soil salinity without requiring on-site soil moisture or roughness data.

Conclusions

A novel, image-based framework combining machine learning and multi-date SAR data enables accurate soil salinity mapping on wet coasts.
The developed SVR models provide a robust and operation-friendly tool for soil salinity assessment.
This approach has potential for application in other humid saline regions, improving soil management and crop selection.

Keywords:

Coast Estimation Machine learning Multi-date Sentinel-1 data Soil salinity

Related Concept Videos

Responses to Salt Stress

Salt stress—which can be triggered by high salt concentrations in a plant’s environment—can significantly affect plant growth and crop production by influencing photosynthesis and the absorption of water and nutrients.

Plant cell cytoplasm has a high solute concentration, which causes water to flow from the soil into the plant due to osmosis. However, excess salt in the surrounding soil increases the soil solute concentration, reducing the plant’s ability to take up...