Comparison of bagging, boosting and stacking algorithms for surface soil moisture mapping using optical-thermal-microwave remote sensing synergies

Das, Bappa; Rathore, Pooja; Roy, Debasish; Chakraborty, Debashis; Jatav, Raghuveer Singh; Sethi, Deepak; Kumar, Prabhat

doi:10.1016/j.catena.2022.106485

Cited by 49 publications

(16 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data cover 80% of the land area except Antarctica and the land near the North Pole, which is incomparable to the elevation data obtained using conventional ground measurement methods. The SRTM DEM has been widely used in the field of soil moisture [26,29,30].…”

Section: Topographic Datamentioning

confidence: 99%

“…In the past few decades, machine learning has been widely used in the field of soil moisture due to its excellent nonlinear fitting ability, especially ensemble learning, which reduces variance or bias through the integration of multiple machine learning models to improve the predictive ability of the model [29]. Wei et al [30] used the random forest algorithm to downscale the SMAP soil moisture data of the Iberian Peninsula based on MODIS optical thermal infrared data, and the results showed that RF could make a good improvement on SMAP.…”

Section: Introductionmentioning

confidence: 99%

“…The results showed that XGBoost was slightly better than RF. Das et al [29] used three ensemble learning methods of bagging, boosting, and stacking to invert surface soil moisture in semiarid areas. The stacking method improved the prediction of the model by reducing model overfitting and the deviation of each base learner.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Surface Soil Moisture Retrieval of China Using Multi-Source Data and Ensemble Learning

Yang

Miao

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Large-scale surface soil moisture (SSM) distribution is very necessary for agricultural drought monitoring, water resource management, and climate change research. However, the current large-scale SSM products have relatively coarse spatial resolution, which limits their application. In this study, we estimate the 1 km daily SSM in China based on ensemble learning using a multi-source data set including in situ soil moisture measurements from 2980 meteorological stations, MODIS Surface Reflectance products, SMAP (Soil Moisture Active Passive) soil moisture products, ERA5-Land dataset, SRTM DEM and soil texture. Among them, in situ measurements are used as independent variables, and other data are used as dependent variables. In order to improve the spatio-temporal completeness of SSM, the missing value in SMAP soil moisture products were reconstructed using the Discrete Cosine Transformation-penalized Partial Least Square (DCT-PLS) method to provide spatially complete background field information for soil moisture retrieval. The results show that the reconstructed soil moisture value has high quality, and the DCT-PLS method can fully utilize the three-dimensional spatiotemporal information to fill the data gaps. Subsequently, the performance of four ensemble learning models of random forest (RF), extremely randomized trees (ERT), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM) for soil moisture retrieval was evaluated. The LightGBM outperformed the other three machine learning models, with a correlation coefficient (R2) of 0.88, a bias of 0.0004 m³/m³, and an unbiased root mean square error (ubRMSE) of 0.0366 m³/m³. The high correlation between the in situ soil moisture and the predicted values at each meteorological station further indicate that LightGBM can well capture the temporal variation of soil moisture. Finally, the model was used to map the 1 km daily SSM in China on the first day of each month from May to October 2018. This study can provide some reference and help for future long-term daily 1 km surface soil moisture mapping in China.

show abstract

Section: Topographic Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Surface Soil Moisture Retrieval of China Using Multi-Source Data and Ensemble Learning

Yang

Miao

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Soil moisture monitoring based on remote sensing data not only saves time and effort, but also has irreplaceable superiority in spatial representativeness and sampling periodicity [4] , which is the most promising method for quantitative soil moisture monitoring. So scholars simulated the actual connection between surface cover type, surface temperature, soil thermal inertia and surface evapotranspiration and Soil moisture through the changes of reflective radiation characteristics of the ground features (vegetation index model [5] , temperature index model [6] , thermal inertia model [7] , evapotranspiration model [8] , etc. ), to initiate the inversion of soil moisture.…”

Section: Introductionmentioning

confidence: 99%

Accurate identification of soil moisture in Mu Us Sandy Land based on multi-source remote sensing data

Wang,

et al. 2024

International Conference on Remote Sensing Technology and Survey Mapping (RSTSM 2024)

View full text Add to dashboard Cite

“…Boosting and Bagging are the two main types of ensemble learning. 22 Bagging is a method of repeated sampling (with dropout) from a dataset based on the uniform probability distribution, where every sub dataset is sampled with equal probability. Boosting adaptively changes the distribution of training samples so that weak learners focus on those samples that are harder to learn.…”

Section: Introductionmentioning

confidence: 99%

Stacking ensemble learning fused with whale optimisation algorithm based method for crown prediction of hot-rolled strip

Meng,

Ding,

et al. 2024

Ironmaking & Steelmaking: Processes, Products and Applicati

View full text Add to dashboard Cite

Precision of strip shape is one of the important indexes to measure the quality of strip steel in hot rolling. Accurate prediction of strip shape can realise the timely adjustment of the production system, which is the important foundation for ensuring the quality and stable production of hot-rolled strip steel products. Given the poor accuracy of the traditional mechanism model, this paper proposes a stacking ensemble learning for crown prediction that consist of the random forest (RF), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), categorical boosting (CatBoost) and linear regression, whose hyperparameters are optimised by whale optimisation algorithm (WOA) Firstly, the key features are selected by analysing the feature importance and the Pearson correlation coefficient between rolling parameters. Then, the hyperparameters of the stacking ensemble learning are optimised by four meta-heuristic algorithms during modeling process, among which WOA has the best optimisation effect. Compared to RF, XGBoost, LightGBM, CatBoost and the stacking, proposed method has the highest prediction accuracy that the hit rate reaches 98.58% in the range of 5.0 μm of crown deviation. In addition, the effect of strip width, bending force, rolling force and roll shifting on crown are analysed based on Shapley additive explanations (SHAP).

show abstract

Comparison of bagging, boosting and stacking algorithms for surface soil moisture mapping using optical-thermal-microwave remote sensing synergies

Cited by 49 publications

References 51 publications

Surface Soil Moisture Retrieval of China Using Multi-Source Data and Ensemble Learning

Surface Soil Moisture Retrieval of China Using Multi-Source Data and Ensemble Learning

Accurate identification of soil moisture in Mu Us Sandy Land based on multi-source remote sensing data

Stacking ensemble learning fused with whale optimisation algorithm based method for crown prediction of hot-rolled strip

Contact Info

Product

Resources

About