• Korean Journal of Agricultural and Forest Meteorology
• /
• v.21 no.1
• /
• pp.29-41
• /
• 2019

Terrestrial Gross Primary Production (GPP) is the largest global carbon flux, and forest ecosystems are important because of the ability to store much more significant amounts of carbon than other terrestrial ecosystems. There have been several attempts to estimate GPP using mechanism-based models. However, mechanism-based models including biological, chemical, and physical processes are limited due to a lack of flexibility in predicting non-stationary ecological processes, which are caused by a local and global change. Instead mechanism-free methods are strongly recommended to estimate nonlinear dynamics that occur in nature like GPP. Therefore, we used the mechanism-free machine learning techniques to estimate the daily GPP. In this study, support vector machine (SVM), random forest (RF) and artificial neural network (ANN) were used and compared with the traditional multiple linear regression model (LM). MODIS products and meteorological parameters from eddy covariance data were employed to train the machine learning and LM models from 2006 to 2013. GPP prediction models were compared with daily GPP from eddy covariance measurement in a deciduous forest in South Korea in 2014 and 2015. Statistical analysis including correlation coefficient (R), root mean square error (RMSE) and mean squared error (MSE) were used to evaluate the performance of models. In general, the models from machine-learning algorithms (R = 0.85 - 0.93, MSE = 1.00 - 2.05, p < 0.001) showed better performance than linear regression model (R = 0.82 - 0.92, MSE = 1.24 - 2.45, p < 0.001). These results provide insight into high predictability and the possibility of expansion through the use of the mechanism-free machine-learning models and remote sensing for predicting non-stationary ecological processes such as seasonal GPP.

• Economic and Environmental Geology
• /
• v.44 no.3
• /
• pp.229-238
• /
• 2011

S-wave, which provides lithology and pore fluid information, plays a key role in estimating gas-hydrate saturation. In general, P- and S-wave velocities increase in the presence of gas-hydrate and the P-wave velocity decreases in the presence of free gas under the gas-hydrate layer. Whereas there are very small changes, even slightly increases, in the S-wave velocity in the free gas layer because S-wave is not affected by the pore fluid when propagating in the free gas layer. To verify those velocity properties of the BSR (bottom-simulating reflector) depth in the gas-hydrate prospect area in the Ulleung Basin, P- and S-wave velocity profiles were derived from multi-component ocean-bottom seismic data which were acquired by Korea Institute of Geoscience and Mineral Resources (KIGAM) in May 2009. OBS (ocean-bottom seismometer) hydrophone component data were modeled and inverted first through the traveltime inversion method to derive P-wave velocity and depth model of survey area. 2-D multichannel stacked data were incorporated as an initial model. Two horizontal geophone component data, then, were polarization filtered and rotated to make radial component section. Traveltimes of main S-wave events were picked and used for forward modeling incorporating Poisson's ratio. This modeling provides S-wave profiles and Poisson's ratio profiles at every OBS site. The results shows that P-wave velocities in most OBS sites decrease beneath the BSR, whereas S-wave velocities slightly increase. Consequently, Poisson's ratio decreased strongly beneath the BSR indicating the presence of a free gas layer under the BSR.