Mapping Soil Organic Matter in Cultivated Land Using Landsat 8 Image and GA-AdaBoost Algorithm

Soil organic matter (SOM) is essential for maintaining soil structure, nutrient supply, and water regulation in cultivated land, significantly impacting agricultural productivity and the health of agricultural systems. However, developing robust inversion methods for SOM using satellite remote-sensi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE journal of selected topics in applied earth observations and remote sensing Jg. 18; S. 25427 - 25438
Hauptverfasser: Qu, Xuzhou, Jiang, Shuwen, Gu, Xiaohe, Zhou, Jingping, Tian, Yanan, Liu, Xingyu, Zong, Fajian, Li, Mengjie, Ji, Yalin
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Accuracy
Adaptive boosting (AdaBoost)
Agricultural production
Algorithms
Cultivated lands
Cultivation
Data models
Environmental regulations
Estimation
Farming systems
Feature extraction
genetic algorithm (GA)
Genetic algorithms
Heterogeneity
Image acquisition
Land use
Landsat
Landsat 8
Machine learning
Monitoring
Nutrient cycles
Organic matter
Particle swarm optimization
Patchiness
Predictive models
Remote sensing
Satellite imagery
Satellite technology
Satellites
Soil
Soil mapping
Soil organic matter
soil organic matter (SOM)
Soil structure
Soils
Spatial heterogeneity
Spatial resolution
spectral features
ISSN:1939-1404, 2151-1535
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Soil organic matter (SOM) is essential for maintaining soil structure, nutrient supply, and water regulation in cultivated land, significantly impacting agricultural productivity and the health of agricultural systems. However, developing robust inversion methods for SOM using satellite remote-sensing technology faces challenges due to the spatial heterogeneity of different land use patterns. This study aimed to improve the accuracy of estimating cultivated land SOM from remote-sensing images during the bare-soil period. A total of 15 spectral features were extracted from Landsat 8 image and the recursive feature elimination based on cross validation (RFECV) was applied to identify the optimal feature combination. Multiple machine-learning methods optimized by genetic algorithms (GAs) and particle swarm optimization were compared to identify the best method for estimating SOM. The results revealed that the features screened by RFECV showed improved modeling accuracy over unscreened features and that the highest accuracy of estimating SOM, with R 2 of 0.66, root-mean-square error of 5.93 g/kg, and mean absolute error of 4.70 g/kg, was achieved by the GA-optimized adaptive boosting (GA-AdaBoost) method. Therefore, Landsat 8 remote-sensing images acquired during the bare-soil period, the combination of RFECV and the GA-AdaBoost method can achieve the accurate estimation of cultivated land SOM at the regional scale.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1939-1404
2151-1535
DOI:10.1109/JSTARS.2025.3614884