Mapping canopy nitrogen in European forests using remote sensing and environmental variables with the random forests method

Loozen, Yasmina; Rebel, Karin T.; Jong, S.M. de; Lü, Meng; Ollinger, Scott V.; Wassen, Martin J.; Karssenberg, Derek

doi:10.1016/j.rse.2020.111933

Cited by 68 publications

(40 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm of Random forests was developed by Breiman et al [43] and shows a promising capability to avoid overfitting by sampling the predictor space randomly. It can construct non-linear relationships without the limitations of the assumptions of variable distributions and dependency [12]. In addition, RF could effectively evaluate the importance of independent variables and partly deal with multicollinearity among variables while having great tolerance to noises and outliers.…”

Section: Random Forestsmentioning

confidence: 99%

“…VIs and biophysical variables derived from Sentinel-2 satellite images were examined for estimation of plant N status [11]. Loozen et al [12] used satellite-based VIs and environmental variables to map crop N in European forests. Yet today, the application of satellite-based VIs is still challenged for crop N status assessment because of the limited spatial resolution, the infrequency of satellite overpasses, and the risk of poor image data quality due to atmospheric conditions [13].…”

Section: Introductionmentioning

confidence: 99%

“…In this study, VIs and color moments were used to estimate rice PNC based on partial least square regression (PLSR) and random forest (RF) regression algorithms [12,26,28], in which the objectives are (i) to examine the performance of VIs and color moments from UAV-based RGB images for PNC estimation in rice using algorithms of PLSR and RF; (ii) to explore the potential of improving rice PNC estimation accuracy by fusing VIs and color moments based on the above two methods.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Estimating Plant Nitrogen Concentration of Rice through Fusing Vegetation Indices and Color Moments Derived from UAV-RGB Images

Xiang

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Estimating plant nitrogen concentration (PNC) has been conducted using vegetation indices (VIs) from UAV-based imagery, but color features have been rarely considered as additional variables. In this study, the VIs and color moments (color feature) were calculated from UAV-based RGB images, then partial least square regression (PLSR) and random forest regression (RF) models were established to estimate PNC through fusing VIs and color moments. The results demonstrated that the fusion of VIs and color moments as inputs yielded higher accuracies of PNC estimation compared to VIs or color moments as input; the RF models based on the combination of VIs and color moments (R2 ranging from 0.69 to 0.91 and NRMSE ranging from 0.07 to 0.13) showed similar performances to the PLSR models (R2 ranging from 0.68 to 0.87 and NRMSE ranging from 0.10 to 0.29); Among the top five important variables in the RF models, there was at least one variable which belonged to the color moments in different datasets, indicating the significant contribution of color moments in improving PNC estimation accuracy. This revealed the great potential of combination of RGB-VIs and color moments for the estimation of rice PNC.

show abstract

Section: Random Forestsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimating Plant Nitrogen Concentration of Rice through Fusing Vegetation Indices and Color Moments Derived from UAV-RGB Images

Xiang

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Most of the previous studies on crop physiological parameter estimation have demonstrated that the RF algorithm exhibits high accuracy and estimation ability, and confers the advantages of strong stability and high e ciency when compared with other modeling methods. Loozen et al [55] used RF technology estimate the N content of a European forest canopy, which exhibited superior accuracy (R 2 = 0.62, RMSE = 0.18). To establish an e cient method for estimating winter wheat biomass, Yue et al [56] used RF algorithm to develop a regression model of winter wheat biomass by combining spectrum, radar backscattering, vegetation index, and radar vegetation index, and the results revealed the potential application of stochastic forest algorithm in remote sensing to estimate winter wheat biomass.…”

Section: Comparison Between Wnn and Rfmentioning

confidence: 99%

Estimation of nitrate nitrogen content in cotton petioles under drip irrigation based on spectral indices and wavelet neural network

Dong¹,

Liu²,

Ci³

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: Estimating nitrate nitrogen (NO3--N) content in petioles is one of the key approaches for monitoring nitrogen (N) nutrition in crops. Rapid, non-destructive, and accurate monitoring of great NO3--N content in cotton petioles under drip irrigation is of great significance.Methods: NO3--N content in cotton petioles under drip irrigation and the corresponding canopy spectral reflectance of cotton plants grown in experimental plots under various N application levels were analyzed. The correlations among ‘trilateral parameters’ and six vegetation indices, and NO3--N content in petioles were determined. A traditional regression model of NO3--N content in cotton petioles under drip irrigation was established, and a wavelet neural network (WNN) model with different index numbers was developed. The WNN model was verified using independent data, and compared with the random forest algorithm , radial basis function neural network and back propagation neural network.Results: Based on the analyses of ‘trilateral parameters’ and petiole NO3--N content, blue edge amplitude (Db) and blue edge area (SDb) of the blue edge parameters exhibited a strong positive correlation with petiole NO3--N content, and the correlation coefficients was 0.90. Among the blue edge parameters, the coefficient of determination (R2) of the Db polynomial regression equation and petiole NO3--N content was the highest (R2 = 0.89), while the root mean square error (RMSE) of the linear regression model was the lowest (RMSE = 1.04). R2 value of the traditional regression model developed using blue edge parameters and petiole NO3--N content significantly increased, while RMSE value decreased when compared with those of the red edge and yellow edge parameters. Analyses results of the vegetation index developed using original spectral reflectance data and the vegetation index developed using the first set of derivative spectral reflectance data and petiole NO3--N content, revealed that the first derivative vegetation index, normalized difference spectral index (ND705) exhibited a strong negative correlation, with a correlation coefficient of -0.90. The first derivative vegetation index, ND705 and petiole NO3--N content index regression equation had the highest coefficient of determination (R2 = 0.83), while the first derivative vegetation index, red edge model index (CIred-edge) and petiole NO3--N content linear regression equation had the lowest RMSE = 0.92. R2 value of the traditional regression equation for the first derivative vegetation index and petiole NO3--N content significantly increased, while the RMSE value decreased when compared with the original spectral vegetation index. After conducting correlation analyses and developing traditional regression models, Db and SDb of the blue edge parameters, and the first derivative vegetation index, ND705 and CIred-edge were used to develop a WNN model. The model based on blue edge parameters had R2 of 0.88, RMSE of 0.74g/L and mean absolute error (MAE) of 0.58 g/L, the R2 value was 8.6% higher than the R2 the first derivative vegetation index model, in which RMSE and MAE reduced by 18.7% and 20.5%, respectively. The model was tested using independent verification data, and which revealed that the R2 value of the model was 0.88, RMSE was 0.65g/L, and MAE was 0.47g/L based on the blue edge parameters, predicted value of WNN, and true value of the verification model, which was superior other models. The performance of the WNN model based on the blue edge parameters improved by 7.3%, and RMSE and MAE reduced by 25.2% and 30.9%, respectively when compared with those of the vegetation index model.Conclusion: The present study demonstrated that an inexpensive approach consisting of WNN algorithm and spectrum can be used to enhance the accuracy of NO3--N content estimation in cotton petioles under drip irrigation, which reflects their practical application potential.

show abstract

“…This algorithm classifies the data by integrating votes from a mass of decision trees, which are built by fitting the features of training samples subsets generated randomly. There are three parameters governing the Random Forest algorithm: the number of trees (ntree), the minimum number of terminal seeds (nodesize), and the number of features (mtry) [47]. In our study, ntree was set to 200, since previous studies have found that if the number of decision trees is larger than 120, the accuracies of maps become more stable [27].…”

Section: Mapping Mangrove Forests With Random Forestmentioning

confidence: 99%

Advancing the Mapping of Mangrove Forests at National-Scale Using Sentinel-1 and Sentinel-2 Time-Series Data with Google Earth Engine: A Case Study in China

Liang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

A high resolution mangrove map (e.g., 10-m), including mangrove patches with small size, is urgently needed for mangrove protection and ecosystem function estimation, because more small mangrove patches have disappeared with influence of human disturbance and sea-level rise. However, recent national-scale mangrove forest maps are mainly derived from 30-m Landsat imagery, and their spatial resolution is relatively coarse to accurately characterize the extent of mangroves, especially those with small size. Now, Sentinel imagery with 10-m resolution provides an opportunity for generating high-resolution mangrove maps containing these small mangrove patches. Here, we used spectral/backscatter-temporal variability metrics (quantiles) derived from Sentinel-1 SAR (Synthetic Aperture Radar) and/or Sentinel-2 MSI (Multispectral Instrument) time-series imagery as input features of random forest to classify mangroves in China. We found that Sentinel-2 (F1-Score of 0.895) is more effective than Sentinel-1 (F1-score of 0.88) in mangrove extraction, and a combination of SAR and MSI imagery can get the best accuracy (F1-score of 0.94). The 10-m mangrove map was derived by combining SAR and MSI data, which identified 20003 ha mangroves in China, and the area of small mangrove patches (<1 ha) is 1741 ha, occupying 8.7% of the whole mangrove area. At the province level, Guangdong has the largest area (819 ha) of small mangrove patches, and in Fujian, the percentage of small mangrove patches is the highest (11.4%). A comparison with existing 30-m mangrove products showed noticeable disagreement, indicating the necessity for generating mangrove extent product with 10-m resolution. This study demonstrates the significant potential of using Sentinel-1 and Sentinel-2 images to produce an accurate and high-resolution mangrove forest map with Google Earth Engine (GEE). The mangrove forest map is expected to provide critical information to conservation managers, scientists, and other stakeholders in monitoring the dynamics of the mangrove forest.

show abstract

Mapping canopy nitrogen in European forests using remote sensing and environmental variables with the random forests method

Cited by 68 publications

References 51 publications

Estimating Plant Nitrogen Concentration of Rice through Fusing Vegetation Indices and Color Moments Derived from UAV-RGB Images

Estimating Plant Nitrogen Concentration of Rice through Fusing Vegetation Indices and Color Moments Derived from UAV-RGB Images

Estimation of nitrate nitrogen content in cotton petioles under drip irrigation based on spectral indices and wavelet neural network

Advancing the Mapping of Mangrove Forests at National-Scale Using Sentinel-1 and Sentinel-2 Time-Series Data with Google Earth Engine: A Case Study in China

Contact Info

Product

Resources

About