Estimating the Aboveground Biomass of an Evergreen Broadleaf Forest in Xuan Lien Nature Reserve, Thanh Hoa, Vietnam, Using SPOT-6 Data and the Random Forest Algorithm

Kappas, Martin

doi:10.1155/2020/4216160

Cited by 11 publications

(9 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Studies that used satellite remote sensing data for AGB prediction highlighted a common drawback in terms of data saturation and low prediction precision [18], [26], [71]. Our study analyzed multiple models for different datasets and found two effective ways to reduce the bias and data saturation.…”

Section: Discussionmentioning

confidence: 91%

Generative Feature Extraction From Sentinel 1 and 2 Data for Prediction of Forest Aboveground Biomass in the Italian Alps

Naik¹,

Dalponte

Bruzzone

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Aboveground biomass (AGB) is an important forest attribute directly linked to the forest carbon pool. The use of satellite remote sensing (RS) data has increased for AGB prediction due to their large footprint and low-cost availability. However, they have been limited due to saturation effect that leads to low prediction precision. In this study, we propose an innovative and dynamic architecture based on generative neural network that extracts target oriented generative features for predicting forest AGB using satellite RS data. These features are more resilient to mixed forest types and geographical conditions as compared to the traditional features and models. The effectiveness of the proposed features was assessed by experiments performed using multispectral (MS), Synthetic aperture Radar (SAR) and combined dual-source (DS) datasets. The proposed model achieved best performance in terms of precision, model agreement and overfitting as compared to the other conventional models for all analyzed datasets. The t-distributed stochastic neighbor embedding (t-SNE) scatterplots of the generative features clearly show one dimension of the feature space associated with the target AGB. Feature importance analysis indicated that the produced generative features were more significant than the conventional analytical features. Also, the model provided a robust framework for homogeneous fusion of multi-sensor features from satellite RS data for predicting AGB.

show abstract

Section: Discussionmentioning

confidence: 91%

Generative Feature Extraction From Sentinel 1 and 2 Data for Prediction of Forest Aboveground Biomass in the Italian Alps

Naik¹,

Dalponte

Bruzzone

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The bagging approach is based on the premise that combining learning models improves the final result. Several studies have investigated the RF algorithm's potential for random agricultural forests [123,124]. The advantages of using this approach include resolving vector collinearity issues, often encountered while using traditional LR models.…”

Section: Support Vector Machine (Svm)mentioning

confidence: 99%

A Review of an Artificial Intelligence Framework for Identifying the Most Effective Palm Oil Prediction

et al. 2022

View full text Add to dashboard Cite

Machine Learning (ML) offers new precision technologies with intelligent algorithms and robust computation. This technology benefits various agricultural industries, such as the palm oil sector, which possesses one of the most sustainable industries worldwide. Hence, an in-depth analysis was conducted, which is derived from previous research on ML utilisation in the palm oil in-dustry. The study provided a brief overview of widely used features and prediction algorithms and critically analysed current the state of ML-based palm oil prediction. This analysis is extended to the ML application in the palm oil industry and a comparison of related studies. The analysis was predicated on thoroughly examining the advantages and disadvantages of ML-based palm oil prediction and the proper identification of current and future agricultural industry challenges. Potential solutions for palm oil prediction were added to this list. Artificial intelligence and ma-chine vision were used to develop intelligent systems, revolutionising the palm oil industry. Overall, this article provided a framework for future research in the palm oil agricultural industry by highlighting the importance of ML.

show abstract

“…Similarly, the relationship between forest attributes (e.g., forest structure, tree species diversity and functional traits) and AGC storage is less well studied (Con et al, 2013). Previous works in this ecoregion have only developed sets of allometric equations to improve estimations of tree aboveground biomass (AGB) (Huy et al, 2016a;2016b) and remote sensing technology to estimate AGC storage (Luong et al, 2015;Avitabile et al, 2016;Nguyen & Kappas, 2020).…”

Section: Introductionmentioning

confidence: 99%

Effects of tree diversity and stand structure on above-ground carbon storage in evergreen broad-leaved and deciduous forests in Southeast Vietnam

Nguyen¹,

Rodríguez-Hernández²,

Tuan³

et al. 2022

Dendrobiology

View full text Add to dashboard Cite

Understanding the relationship between tree species diversity and above-ground carbon (AGC) storage in tropical forests is essential for a sustainable flow of ecosystem goods and services. Although tropical forests of Vietnam are of particular interest due to their high biodiversity and carbon density, few studies have evaluated the relative importance of species composition, tree species diversity and forest structure on AGC storage by forest vegetation type. In this study, we tested for the influence of taxonomic diversity, forest structure and species composition on AGC storage in evergreen broad-leaved and deciduous forests of Southeast Vietnam. Data was collected within 137 rectangular plots (25 m × 20 m), randomly selected across a deciduous forest (DF) and four evergreen broad-leaved forest (EB) categories, with different standing volumes levels: very poor (EBG), poor (EBP), medium (EBM) and rich (EBR). In total, we identified 3687 individuals from 110 tree species belonging to 46 families in 6.85 hectares of sampled area. AGC storage significantly differed among forest categories, ranging from 14.81 Mg ha−1 in EBG to 146.74 Mg ha−1 in EBR. There was higher AGC in the medium diameter class (20-40 cm), except for EBR where there was higher AGC within individuals of 40-60 cm in diameter. Taxonomic diversity was weakly correlated with AGC while stand structure (stem density and maximum diameter) were strongly correlated. Our results suggest that maintaining the abundance distributions of remnant tree species, particularly that of large trees, is one important method to enhance AGC storage in the tropical ecosytems of southern Vietnam.

show abstract

Estimating the Aboveground Biomass of an Evergreen Broadleaf Forest in Xuan Lien Nature Reserve, Thanh Hoa, Vietnam, Using SPOT-6 Data and the Random Forest Algorithm

Cited by 11 publications

References 54 publications

Generative Feature Extraction From Sentinel 1 and 2 Data for Prediction of Forest Aboveground Biomass in the Italian Alps

Generative Feature Extraction From Sentinel 1 and 2 Data for Prediction of Forest Aboveground Biomass in the Italian Alps

A Review of an Artificial Intelligence Framework for Identifying the Most Effective Palm Oil Prediction

Effects of tree diversity and stand structure on above-ground carbon storage in evergreen broad-leaved and deciduous forests in Southeast Vietnam

Contact Info

Product

Resources

About