Applicability of remote sensing and machine learning for predicting bulk soil electrical conductivity under different forest types in central Japan
Soil electrical conductivity (EC) is a key indicator in forest ecosystems for assessing soil nutrient availability, moisture retention capacity, ion exchange processes, and overall soil health, which are critical for tree growth, carbon sequestration, and ecosystem stability. With the growing intere...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Soil Advances |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2950289625000132 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849694449647484928 |
|---|---|
| author | Kyaw Win Tamotsu Sato Takuya Hiroshima |
| author_facet | Kyaw Win Tamotsu Sato Takuya Hiroshima |
| author_sort | Kyaw Win |
| collection | DOAJ |
| description | Soil electrical conductivity (EC) is a key indicator in forest ecosystems for assessing soil nutrient availability, moisture retention capacity, ion exchange processes, and overall soil health, which are critical for tree growth, carbon sequestration, and ecosystem stability. With the growing interest in remote sensing applications, this study aimed to apply remote sensing and machine-learning (ML) models such as random forest (RF), classification and regression tree (CART), extreme gradient boosting (XGBoost), k-nearest neighbors (KNN), minimum distance (MD), and Naive Bayes (NB) for EC prediction. We aimed to propose the most suitable ML model for soil EC classification to enhance large-scale soil property assessment and improve our understanding of soil EC distribution under different forest types in central Japan. The RF model consistently outperformed others at 30 m resolution, with the image combinations of Sentinel-2 and surface soil moisture achieving the highest mean accuracy (MA) (MA = 0.926). The XGBoost model also performed strongly using the same image combinations with high mean accuracy (MA = 0.923). By demonstrating the potential of integrating remote sensing and ML, our study highlights the role of modern technologies in addressing complex ecological challenges in forestry and beyond. |
| format | Article |
| id | doaj-art-0c9cb500d8ec437a903dcbac6bd30e86 |
| institution | DOAJ |
| issn | 2950-2896 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Soil Advances |
| spelling | doaj-art-0c9cb500d8ec437a903dcbac6bd30e862025-08-20T03:20:03ZengElsevierSoil Advances2950-28962025-06-01310004510.1016/j.soilad.2025.100045Applicability of remote sensing and machine learning for predicting bulk soil electrical conductivity under different forest types in central JapanKyaw Win0Tamotsu Sato1Takuya Hiroshima2Department of Global Agricultural Sciences, Graduate School of Agricultural and Life Sciences, The University of Tokyo, Yayoi 1-1-1, Bunkyo-ku, Tokyo 113-8657, Japan; Corresponding author.Department of Global Agricultural Sciences, Graduate School of Agricultural and Life Sciences, The University of Tokyo, Yayoi 1-1-1, Bunkyo-ku, Tokyo 113-8657, Japan; Forestry and Forest Products Research Institute, Tsukuba, Ibaraki 305-8687, JapanDepartment of Global Agricultural Sciences, Graduate School of Agricultural and Life Sciences, The University of Tokyo, Yayoi 1-1-1, Bunkyo-ku, Tokyo 113-8657, JapanSoil electrical conductivity (EC) is a key indicator in forest ecosystems for assessing soil nutrient availability, moisture retention capacity, ion exchange processes, and overall soil health, which are critical for tree growth, carbon sequestration, and ecosystem stability. With the growing interest in remote sensing applications, this study aimed to apply remote sensing and machine-learning (ML) models such as random forest (RF), classification and regression tree (CART), extreme gradient boosting (XGBoost), k-nearest neighbors (KNN), minimum distance (MD), and Naive Bayes (NB) for EC prediction. We aimed to propose the most suitable ML model for soil EC classification to enhance large-scale soil property assessment and improve our understanding of soil EC distribution under different forest types in central Japan. The RF model consistently outperformed others at 30 m resolution, with the image combinations of Sentinel-2 and surface soil moisture achieving the highest mean accuracy (MA) (MA = 0.926). The XGBoost model also performed strongly using the same image combinations with high mean accuracy (MA = 0.923). By demonstrating the potential of integrating remote sensing and ML, our study highlights the role of modern technologies in addressing complex ecological challenges in forestry and beyond.http://www.sciencedirect.com/science/article/pii/S2950289625000132Bulk soil electrical conductivityExtreme gradient boostingRandom forestSurface soil moisture |
| spellingShingle | Kyaw Win Tamotsu Sato Takuya Hiroshima Applicability of remote sensing and machine learning for predicting bulk soil electrical conductivity under different forest types in central Japan Soil Advances Bulk soil electrical conductivity Extreme gradient boosting Random forest Surface soil moisture |
| title | Applicability of remote sensing and machine learning for predicting bulk soil electrical conductivity under different forest types in central Japan |
| title_full | Applicability of remote sensing and machine learning for predicting bulk soil electrical conductivity under different forest types in central Japan |
| title_fullStr | Applicability of remote sensing and machine learning for predicting bulk soil electrical conductivity under different forest types in central Japan |
| title_full_unstemmed | Applicability of remote sensing and machine learning for predicting bulk soil electrical conductivity under different forest types in central Japan |
| title_short | Applicability of remote sensing and machine learning for predicting bulk soil electrical conductivity under different forest types in central Japan |
| title_sort | applicability of remote sensing and machine learning for predicting bulk soil electrical conductivity under different forest types in central japan |
| topic | Bulk soil electrical conductivity Extreme gradient boosting Random forest Surface soil moisture |
| url | http://www.sciencedirect.com/science/article/pii/S2950289625000132 |
| work_keys_str_mv | AT kyawwin applicabilityofremotesensingandmachinelearningforpredictingbulksoilelectricalconductivityunderdifferentforesttypesincentraljapan AT tamotsusato applicabilityofremotesensingandmachinelearningforpredictingbulksoilelectricalconductivityunderdifferentforesttypesincentraljapan AT takuyahiroshima applicabilityofremotesensingandmachinelearningforpredictingbulksoilelectricalconductivityunderdifferentforesttypesincentraljapan |