Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms

Almeida, Catherine Torres de; Galvão, Lênio Soares; Aragão, L. E.; Ometto, Jean Pierre; Jacon, Aline Daniele; Pereira, Francisca Rocha de Souza; Sato, Luciane Yumie; Pontes‐Lopes, Aline; Graça, Paulo Maurı́cio Lima de Alencastro; Silva, Camila V. J.; Ferreira-Ferreira, Jefferson; Longo, Marcos

doi:10.1016/j.rse.2019.111323

Cited by 96 publications

(47 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ANOVA results provided in Table 4 show that the data source is the cause of 69% of the variation in the prediction results, 28% for the regression method, and 3% for the interaction their interaction. These results are consistent with those of [33,69]. This indicates that the data source should also be considered to determine the regression method in the design of similar experiments.…”

Section: Discussionsupporting

confidence: 86%

“…Considering individual sensors, the features extracted from VNIR provided the most accurate predictions. However, adding the geometric based features extracted from the LiDAR data to the models improved the accuracy of the predictions significantly, which is consistent with previous studies for biomass prediction in forest environments [44,69]. We recommend acquiring data from both VNIR and LiDAR sensors, if possible, for the most reliable biomass prediction.…”

Section: Recommendations For Biomass Predictionsupporting

confidence: 86%

“…Also, the SVR models provided the maximum R 2 for all the data sources. Similar to the study by Almeida et al [69], an ANOVA test was performed on the prediction results to determine the impact of the method and data source (e.g. sensor-based features) on the prediction results.…”

Section: Discussionmentioning

confidence: 99%

“…This indicates that the data source should also be considered to determine the regression method in the design of similar experiments. A similar ANOVA test was performed on the R 2 values for six experiments, including Similar to the study by Almeida et al [69], an ANOVA test was performed on the prediction results to determine the impact of the method and data source (e.g., sensor-based features) on the prediction results. The ANOVA results provided in Table 4 show that the data source is the cause of 69% of the variation in the prediction results, 28% for the regression method, and 3% for the interaction their interaction.…”

Section: Discussionmentioning

confidence: 99%

See 3 more Smart Citations

Multi-Temporal Predictive Modelling of Sorghum Biomass Using UAV-Based Hyperspectral and LiDAR Data

et al. 2020

View full text Add to dashboard Cite

High-throughput phenotyping using high spatial, spectral, and temporal resolution remote sensing (RS) data has become a critical part of the plant breeding chain focused on reducing the time and cost of the selection process for the “best” genotypes with respect to the trait(s) of interest. In this paper, the potential of accurate and reliable sorghum biomass prediction using visible and near infrared (VNIR) and short-wave infrared (SWIR) hyperspectral data as well as light detection and ranging (LiDAR) data acquired by sensors mounted on UAV platforms is investigated. Predictive models are developed using classical regression-based machine learning methods for nine experiments conducted during the 2017 and 2018 growing seasons at the Agronomy Center for Research and Education (ACRE) at Purdue University, Indiana, USA. The impact of the regression method, data source, timing of RS and field-based biomass reference data acquisition, and the number of samples on the prediction results are investigated. R2 values for end-of-season biomass ranged from 0.64 to 0.89 for different experiments when features from all the data sources were included. Geometry-based features derived from the LiDAR point cloud to characterize plant structure and chemistry-based features extracted from hyperspectral data provided the most accurate predictions. Evaluation of the impact of the time of data acquisition during the growing season on the prediction results indicated that although the most accurate and reliable predictions of final biomass were achieved using remotely sensed data from mid-season to end-of-season, predictions in mid-season provided adequate results to differentiate between promising varieties for selection. The analysis of variance (ANOVA) of the accuracies of the predictive models showed that both the data source and regression method are important factors for a reliable prediction; however, the data source was more important with 69% significance, versus 28% significance for the regression method.

show abstract

Section: Discussionsupporting

confidence: 86%

Section: Recommendations For Biomass Predictionsupporting

confidence: 86%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-Temporal Predictive Modelling of Sorghum Biomass Using UAV-Based Hyperspectral and LiDAR Data

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In our study, the metrics selected to compose the models are corroborated by previous studies [59,61]. For instance, numerous AGB estimation studies [62][63][64] had indicated the metric 'mean canopy height' to be one of the most significant attributes, and this is reflected by our PCA results. Likewise, metrics such as Standard Deviation and Coefficient of Variation of Height were found to provide information on the vertical complexity and heterogeneity of canopy components [65].…”

Section: Discussionsupporting

confidence: 85%

Comparison of Statistical Modelling Approaches for Estimating Tropical Forest Aboveground Biomass Stock and Reporting Their Changes in Low-Intensity Logging Areas Using Multi-Temporal LiDAR Data

et al. 2020

View full text Add to dashboard Cite

Accurately quantifying forest aboveground biomass (AGB) is one of the most significant challenges in remote sensing, and is critical for understanding global carbon sequestration. Here, we evaluate the effectiveness of airborne LiDAR (Light Detection and Ranging) for monitoring AGB stocks and change (ΔAGB) in a selectively logged tropical forest in eastern Amazonia. Specifically, we compare results from a suite of different modelling methods with extensive field data. The calibration AGB values were derived from 85 square field plots sized 50 × 50 m field plots established in 2014 and which were estimated using airborne LiDAR data acquired in 2012, 2014, and 2017. LiDAR-derived metrics were selected based upon Principal Component Analysis (PCA) and used to estimate AGB stock and change. The statistical approaches were: ordinary least squares regression (OLS), and nine machine learning approaches: random forest (RF), several variations of k-nearest neighbour (k-NN), support vector machine (SVM), and artificial neural networks (ANN). Leave-one-out cross-validation (LOOCV) was used to compare performance based upon root mean square error (RMSE) and mean difference (MD). The results show that OLS had the best performance with an RMSE of 46.94 Mg/ha (19.7%) and R² = 0.70. RF, SVM, and ANN were adequate, and all approaches showed RMSE ≤54.48 Mg/ha (22.89%). Models derived from k-NN variations all showed RMSE ≥64.61 Mg/ha (27.09%). The OLS model was thus selected to map AGB across the time-series. The mean (±sd—standard deviation) predicted AGB stock at the landscape level was 229.10 (±232.13) Mg/ha in 2012, 258.18 (±106.53) in 2014, and 240.34 (sd ± 177.00) Mg/ha in 2017, showing the effect of forest growth in the first period and logging in the second period. In most cases, unlogged areas showed higher AGB stocks than logged areas. Our methods showed an increase in AGB in unlogged areas and detected small changes from reduced-impact logging (RIL) activities occurring after 2012. We also detected that the AGB increase in areas logged before 2012 was higher than in unlogged areas. Based on our findings, we expect our study could serve as a basis for programs such as REDD+ and assist in detecting and understanding AGB changes caused by selective logging activities in tropical forests.

show abstract

Natural vegetation biomass and the dimension of forest quality in tropical agricultural landscapes

de Toledo,

Pivello,

Perring

et al. 2024

Ecological Applications

View full text Add to dashboard Cite

Forest cover has been a pivotal indicator of biological conservation and carrying capacity for wildlife in forest ecoregions. Such a relationship underpins policies focused on the extension of protected lands. Here, we estimate aboveground biomass (AGB) as a proxy for habitat quality in seminatural rural patches and provide a comparison with approaches that only consider forest cover. We hypothesize that recommendations for biological conservation in agricultural landscapes are substantially improved if habitat quality is also taken into account, and thus consider the possibility of forest quality being modulated by land‐use amount, type, and age. We assessed AGB in a densely farmed Brazilian region using a straightforward approach designed to be affordable at large scales, focusing on two expanding and contrasting land uses: sugarcane, and eucalyptus plantations. At a detailed scale, we confirmed through field surveys and AGB estimation using 3D‐multispectral imagery (i.e., AGB = 0.842 × vegetation heightNDVI+1) that AGB variation could be predicted with forest degradation classes that are visually distinguishable with high‐resolution images: 9.33 t ha−1 (90% predictive intervals [PI] = [3.23, 26.97]) in regenerating fields (RF), 31.12 t ha−1 (90% PI = [10.77, 89.90]) in pioneer woods (PW), and 149.04 t ha−1 (90% PI = [51.59, 430.58]) in dense forests (DF). Applying these values to land units sampled across the study region, we found an average land use of 88.5%, together with 11.5% of land set aside for conservation, which reduced AGB to less than 4.2% of its potential (averages of 5.85 t ha−1 in sugarcane‐dominated areas and 6.56 t ha−1 in eucalyptus‐dominated areas, with secondary forests averaging 149.04 t ha−1). This imbalance between forest cover and AGB resulted from forest quality decay, which was similarly severe among land‐use types, ages, and extensions. Therefore, the shortage of trophic resources is likely more critical to wildlife than spatial limitations in vastly deforested tropical ecoregions, where AGB and carbon sinks can be more than doubled just by restoring forests in lands currently spared by agriculture.

show abstract

Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms

Cited by 96 publications

References 87 publications

Multi-Temporal Predictive Modelling of Sorghum Biomass Using UAV-Based Hyperspectral and LiDAR Data

Multi-Temporal Predictive Modelling of Sorghum Biomass Using UAV-Based Hyperspectral and LiDAR Data

Comparison of Statistical Modelling Approaches for Estimating Tropical Forest Aboveground Biomass Stock and Reporting Their Changes in Low-Intensity Logging Areas Using Multi-Temporal LiDAR Data

Natural vegetation biomass and the dimension of forest quality in tropical agricultural landscapes

Contact Info

Product

Resources

About