Estimating Forest Carbon Stocks in Danyang Using Kriging Methods for Aboveground Biomass

Park, Hyun-Ju; Shin, Hyuseok; Roh, Young-Hee; Kim, Kyoung-Min; Park, Key-Ho

doi:10.11108/kagis.2012.15.1.016

Cited by 19 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The subjects covered were more diverse than journal articles: including timber stocks, forest growth, forest biomass, forest carbon, forest vegetation, statistic methodology in small forest area, methodology for estimating forest statistics, thematic maps, stand density, dead trees, site index, survey methodology, forest health, and forest changes. Lee et al, 2013bNamgung et al, 2014Nor et al, 2011Seo et al, 2009aSeo et al, 2010Shin et al, 2007Shin et al, 2008cShin et al, 2011Byun, 2011Choi, 2014 KFS, 2012b 34 Forest carbon Jeong et al, 2013Jung et al, 2010bJung et al, 2013bKim et al, 2014aKim et al, 2015Lee et al, 2015aLee et al, 2015bLee et al, 2015cPark et al, 2012aLee et al, 2010Nam et al, 2012Yim et al, 2010cYim et al, 2011aYim et al, 2011bYim et al, 2011cJeong, 2013Lee, 2012Pyo, 2013Seo, 2013aShin, 2012a KFS, 2012a 27 …”

Section: Conference Papersmentioning

confidence: 99%

Brief history of Korean national forest inventory and academic usage

Park¹,

Han²,

Rahman³

et al. 2016

Korean Journal of Agricultural Science

View full text Add to dashboard Cite

The National Forest Inventory (NFI) is important for providing fundamental data for basic forest planning and the establishment of forest policies for the purpose of implementing sustainable forest management. The purpose of this study is to present the development of Korea's NFI including legal basis, sampling design, and measured variables and to review the usage of NFI data. The survey methods and forestry statistics among the Unites States, Canada, Japan, China, and European countries were briefly compared. Total 140 publications utilizing NFI data between 2008 and 2015 were categorized with 15 subjects. Korea has conducted the NFI 6 times since 1971, but only the 6 th NFI is comparable with the fifth, the previous NFI, because the permanent sampling plots have been shared between the periods. The Korean Forestry Statistics contains only half as many variables as that of advanced countries in Forestry. More researches were needed to improve consistent measurement of diverse variables through implementation of advanced technologies. Additional data for Forest Health Monitoring since the NFI 6 th must be under quality control which will be an essential part of the inventories for providing the chronological change of forest health.

show abstract

Section: Conference Papersmentioning

confidence: 99%

Brief history of Korean national forest inventory and academic usage

Park¹,

Han²,

Rahman³

et al. 2016

Korean Journal of Agricultural Science

View full text Add to dashboard Cite

show abstract

“…Numerous studies have reported the use of geostatistical techniques [2][3][4] to interpolate values at unsampled points from sampling data. Many studies have been conducted in geographic information system (GIS) environments to create predictive maps by applying geostatistics, and many of these studies have employed Ordinary Kriging (OK) [5][6][7]. Crossvalidation is frequently used to verify Kriging-based estimated values [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Spatial Prediction of Soil Contaminants Using a Hybrid Random Forest–Ordinary Kriging Model

Han,

Suh

2024

Applied Sciences

View full text Add to dashboard Cite

The accurate prediction of soil contamination in abandoned mining areas is necessary to address their environmental risks. This study employed a combined model of machine learning and geostatistics to predict the spatial distribution of soil contamination using heavy metal data collected in an abandoned metal mine. An exploratory data analysis was used to identify patterns in the collected data, the root mean squared error (RMSE) and coefficient of determination (R2) were used to verify the predicted values, and the model was validated using K-fold cross-validation. The prediction results were produced as a map by applying hyperparameter tuning to Random Forest (RF) and Ordinary Kriging (OK) through GridSearchCV using optimal parameter selections. Furthermore, the prediction residuals of the RF model were calculated, and the RF prediction map and OK interpolation results of the RF prediction residuals were summarized to construct an RF–OK prediction map. The RMSE and R2 values for the RF, OK, and RF–OK interpolation models were 66.214, 65.101, and 52.884 mg/kg and 0.867, 0.871, and 0.915, respectively. In addition, the optimization results with the minimum RMSE and maximum R2 were obtained through hyperparameter tuning. The proposed RF–OK hybrid model demonstrated superior prediction performance compared to the individual models.

show abstract

“…특히 지리정보시스템(geographic information systems, GIS) 환경에서 지구통계 분석을 이용하여 보간하는 방법들이 주를 이루며, 그중에서도 정규 크리깅(ordinary kriging)을 활용해 추정 (Jeong and Jang, 2011)하거나 보완 (Chung et al, 2001)하는 연구들이 다수 존재하였다. 또한 크리깅을 통해 예측된 값을 검정하기 위해 교차 타당성 검정 기법 중 Leave-one-out을 적용한 연구사례 (Park et al, 2006, Park and Jang, 2008, Park et al, 2012도 사례도 발표되 었다. 추가로 정규 크리깅을 이용하여 보간 지도를 작성 하는 사례 (Chung et al, 2000, Kim and Jo, 2012도 다수 발표된 바 있다.…”

unclassified

Optimization of Soil Contamination Distribution Prediction Error using Geostatistical Technique and Interpretation of Contributory Factor Based on Machine Learning Algorithm

Han

Suh

Choi

2023

Econ. Environ. Geol.

View full text Add to dashboard Cite

When creating a soil contamination map using geostatistical techniques, there are various sources that can affect prediction errors. In this study, a grid-based soil contamination map was created from the sampling data of heavy metal concentrations in soil in abandoned mine areas using Ordinary Kriging. Five factors that were judged to affect the prediction error of the soil contamination map were selected, and the variation of the root mean squared error (RMSE) between the predicted value and the actual value was analyzed based on the Leave-one-out technique. Then, using a machine learning algorithm, derived the top three factors affecting the RMSE. As a result, it was analyzed that Variogram Model, Minimum Neighbors, and Anisotropy factors have the largest impact on RMSE in the Standard interpolation. For the variogram models, the Spherical model showed the lowest RMSE, while the Minimum Neighbors had the lowest value at 3 and then increased as the value increased. In the case of Anisotropy, it was found to be more appropriate not to consider anisotropy. In this study, through the combined use of geostatistics and machine learning, it was possible to create a highly reliable soil contamination map at the local scale, and to identify which factors have a significant impact when interpolating a small amount of soil heavy metal data.

show abstract

Estimating Forest Carbon Stocks in Danyang Using Kriging Methods for Aboveground Biomass

Cited by 19 publications

References 10 publications

Brief history of Korean national forest inventory and academic usage

Brief history of Korean national forest inventory and academic usage

Spatial Prediction of Soil Contaminants Using a Hybrid Random Forest–Ordinary Kriging Model

Optimization of Soil Contamination Distribution Prediction Error using Geostatistical Technique and Interpretation of Contributory Factor Based on Machine Learning Algorithm

Contact Info

Product

Resources

About