Downscaling SMAP soil moisture estimation with gradient boosting decision tree regression over the Tibetan Plateau

Wei, Zhaoyu; Meng, Yizhuo; Zhang, Wen; Peng, Jian; Meng, Lingkui

doi:10.1016/j.rse.2019.02.022

Cited by 137 publications

(71 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The comparison between RF4 and RF5 indicates that the RF model with more VIs and topographic information can increase the accuracy further to obtain a more robust RF model. In addition, the slopes were all less than 1, which is similar to [84]. Second, the performances of RF1-RF5 generally agreed with the variable importance ( Figure 4).…”

Section: Evaluation Of the Random Forest (Rf) Models At 9 Km Resolutionsupporting

confidence: 67%

An Approach for Downscaling SMAP Soil Moisture by Combining Sentinel-1 SAR and MODIS Data

et al. 2019

Self Cite

View full text Add to dashboard Cite

A method is proposed for the production of downscaled soil moisture active passive (SMAP) soil moisture (SM) data by combining optical/infrared data with synthetic aperture radar (SAR) data based on the random forest (RF) model. The method leverages the sensitivity of active microwaves to surface SM and the triangle/trapezium feature space among vegetation indexes (VIs), land surface temperature (LST), and SM. First, five RF architectures (RF1-RF5) were trained and tested at 9 km. Second, a comparison was performed for RF1-RF5, and were evaluated against in situ SM measurements. Third, two SMAP-Sentinel active-passive SM products were compared at 3 km and 1 km using in situ SM measurements. Fourth, the RF5 model simulations were compared with the SMAP L2_SM_SP product based on the optional algorithm at 3 km and 1 km resolutions. The results showed that the downscaled SM based on the synergistic use of optical/infrared data and the backscatter at vertical-vertical (VV) polarization was feasible in semi-arid areas with relatively low vegetation cover. The RF5 model with backscatter and more parameters from optical/infrared data performed best among the five RF models and was satisfactory at both 3 km and 1 km. Compared with L2_SM_SP, RF5 was more superior at 1 km. The input variables in decreasing order of importance were backscatter, LST, VIs, and topographic factors over the entire study area. The low vegetation cover conditions probably amplified the importance of the backscatter and LST. A sufficient number of VIs can enhance the adaptability of RF models to different vegetation conditions. 2 of 20 salinity (SMOS) satellites [10] based on L-band passive microwaves can provide high-accuracy global daily SM products [16]. However, coarse-resolution passive microwave SM data cannot reflect the detailed distribution of surface SM; therefore, many researchers have downscaled coarse-resolution passive microwave SM data based on fine-resolution auxiliary data [17][18][19][20][21][22][23].Some downscaling methods are based on active or passive microwave data including downscaling coarse-resolution microwave brightness temperature (TB) data or coarse-resolution SM data based on microwave backscatter data [22,[24][25][26][27][28][29][30], and downscaling low-frequency passive microwave data based on high-frequency passive microwave data [31][32][33]. Active microwave techniques offer higher spatial resolutions than passive microwave techniques. Downscaling methods based on active microwaves usually leverage the linear or near-linear relationship between microwave TB or SM data and microwave backscatter data in a time series. Vegetation and surface roughness are generally considered time-invariant during long-time series [26]. However, active microwaves are greatly affected by vegetation and surface roughness [34]; therefore, their applications in most areas are limited [35]. Another assumption is that invariance of vegetation and surface roughness occurs in adjacent observations (several days); thus, these techniques req...

show abstract

Section: Evaluation Of the Random Forest (Rf) Models At 9 Km Resolutionsupporting

confidence: 67%

An Approach for Downscaling SMAP Soil Moisture by Combining Sentinel-1 SAR and MODIS Data

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…The results of all regression trees are integrated to give the final result [52,53]. The GBR model can handle mixed data types and is robust to outliers [54]. As GBR has not been widely applied to mangrove biomass estimation, it was considered for testing in the present study.…”

Section: Selection Of Machine Learning Modelmentioning

confidence: 99%

Estimating Mangrove Above-Ground Biomass Using Extreme Gradient Boosting Decision Trees Algorithm with Fused Sentinel-2 and ALOS-2 PALSAR-2 Data in Can Gio Biosphere Reserve, Vietnam

Pham

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

This study investigates the effectiveness of gradient boosting decision trees techniques in estimating mangrove above-ground biomass (AGB) at the Can Gio biosphere reserve (Vietnam). For this purpose, we employed a novel gradient-boosting regression technique called the extreme gradient boosting regression (XGBR) algorithm implemented and verified a mangrove AGB model using data from a field survey of 121 sampling plots conducted during the dry season. The dataset fuses the data of the Sentinel-2 multispectral instrument (MSI) and the dual polarimetric (HH, HV) data of ALOS-2 PALSAR-2. The performance standards of the proposed model (root-mean-square error (RMSE) and coefficient of determination (R 2 )) were compared with those of other machine learning techniques, namely gradient boosting regression (GBR), support vector regression (SVR), Gaussian process regression (GPR), and random forests regression (RFR). The XGBR model obtained a promising result with R 2 = 0.805, RMSE = 28.13 Mg ha −1 , and the model yielded the highest predictive performance among the five machine learning models. In the XGBR model, the estimated mangrove AGB ranged from 11 to 293 Mg ha −1 (average = 106.93 Mg ha −1 ). This work demonstrates that XGBR with the combined Sentinel-2 and ALOS-2 PALSAR-2 data can accurately estimate the mangrove AGB in the Can Gio biosphere reserve. The general applicability of the XGBR model combined with multiple sourced optical and SAR data should be further tested and compared in a large-scale study of forest AGBs in different geographical and climatic ecosystems.Mangrove forests are among the most important components of natural ecosystems. They perform a wide range of crucial functions, such as mitigating the effects of tropical typhoons and tsunami, reducing coastal erosion, and storing huge amounts of blue carbon [1,2]. Despite their functions and benefits, mangrove forests have been reduced and degraded worldwide, more seriously in South East Asia, where the decimation rate reached its highest level in the last 50 years [3,4]. The driving factors of mangrove deforestation and degradation are conversion to shrimp aquaculture, agriculture (particularly rice and oil palm in West Africa and Southeast Asia), urban development, poor governance, and overexploitation [3,5]. Unfortunately, the loss of mangrove carbon on large spatial scales is little understood. Without this knowledge, we cannot mitigate the global loss of mangrove habitats [6].Land-cover change is thought to alter the above-ground biomass (AGB) in the tropical areas [7-9]. By mapping the spatial distribution of mangrove AGB and the carbon stocks associated with external factors, we could detect the changes in mangrove ecosystems, better understand the drivers of these changes, and reduce the uncertainty in estimating the loss of mangrove ecosystem services. A precise estimation of mangrove AGB is required for sustainably preserving and protecting mangrove ecosystems from loss and degradation under climate change and accelerated global warming...

show abstract

“…2020, 12,1334 3 of 24 and support vector machine (SVM) techniques [27], have increasingly been used for mangrove AGB retrievals with different EO datasets due to their ability to produce better prediction accuracies than parametric models. Recently, gradient boosting decision tree (GBDT) techniques have been shown to be powerful not only for classification but also for regression tasks, such as soil moisture estimation [28] and forest AGB estimation [29,30]. In particular, a novel GBDT technique, extreme gradient boosting regression (XGBR), which was proposed by Chen and Guestrin [31], outperforms other available boosting implementations when handling various environmental issues such as the mobility of disease [32], energy supply security [33], and lithology classification [34].…”

Section: Introductionmentioning

confidence: 99%

Comparison of Machine Learning Methods for Estimating Mangrove Above-Ground Biomass Using Multiple Source Remote Sensing Data in the Red River Delta Biosphere Reserve, Vietnam

et al. 2020

View full text Add to dashboard Cite

This study proposes a hybrid intelligence approach based on an extreme gradient boosting regression and genetic algorithm, namely, the XGBR-GA model, incorporating Sentinel-2, Sentinel-1, and ALOS-2 PALSAR-2 data to estimate the mangrove above-ground biomass (AGB), including small and shrub mangrove patches in the Red River Delta biosphere reserve across the northern coast of Vietnam. We used the novel extreme gradient boosting decision tree (XGBR) technique together with genetic algorithm (GA) optimization for feature selection to construct and verify a mangrove AGB model using data from a field survey of 105 sampling plots conducted in November and December of 2018 and incorporated the dual polarimetric (HH and HV) data of the ALOS-2 PALSAR-2 L-band and the Sentinel-2 multispectral data combined with Sentinel-1 (C-band VV and VH) data. We employed the root-mean-square error (RMSE) and coefficient of determination (R 2 ) to evaluate the performance of the proposed model. The capability of the XGBR-GA model was assessed via a comparison with other machine-learning (ML) techniques, i.e., the CatBoost regression (CBR), gradient boosted regression tree (GBRT), support vector regression (SVR), and random forest regression (RFR) models. The XGBR-GA model yielded a promising result (R 2 = 0.683, RMSE = 25.08 Mg·ha −1 ) and outperformed the four other ML models. The XGBR-GA model retrieved a mangrove AGB ranging from 17 Mg·ha −1 to 142 Mg·ha −1 (with an average of 72.47 Mg·ha −1 ). Therefore, multisource optical and synthetic aperture radar (SAR) combined with the XGBR-GA model can be used to estimate the mangrove AGB in North Vietnam. The effectiveness of the proposed method needs to be further tested and compared to other mangrove ecosystems in the tropics.

show abstract

Downscaling SMAP soil moisture estimation with gradient boosting decision tree regression over the Tibetan Plateau

Cited by 137 publications

References 74 publications

An Approach for Downscaling SMAP Soil Moisture by Combining Sentinel-1 SAR and MODIS Data

An Approach for Downscaling SMAP Soil Moisture by Combining Sentinel-1 SAR and MODIS Data

Estimating Mangrove Above-Ground Biomass Using Extreme Gradient Boosting Decision Trees Algorithm with Fused Sentinel-2 and ALOS-2 PALSAR-2 Data in Can Gio Biosphere Reserve, Vietnam

Comparison of Machine Learning Methods for Estimating Mangrove Above-Ground Biomass Using Multiple Source Remote Sensing Data in the Red River Delta Biosphere Reserve, Vietnam

Contact Info

Product

Resources

About