Forecasting performance of support vector machine for the Poyang Lake's water level

Abstract

The growth of forecasting models has resulted in the development of an excellent model known as the support vector machine (SVM). SVMs can find a global optimal solution equipped with kernel functions. This research trains and tests the SVM network and constructs the support vector regression prediction model by using hydrologic data. Six hydrologic time series were calculated by different kernel functions (namely, linear, polynomial, radial basis function (RBF)), to determine which kernel is the more suitable hydrologic time series in practice. A new solution is presented to identify the good parameter (C; g) by using grid-search and cross-validation. Results prove that linear SVM is a superior model to polynomial and RBF and produced the most accurate results for modeling hydrologic time series behavior as complex hydrologic phenomena. The case study also shows that the calculation errors were correlated with data characteristics. More stable raw data will result in a more accurate result, whereas more random data will result in a more inaccurate result. Model performance could also be dependent on base data nonlinearity.

Relationships Between Temporal and Spatial Variations of Water Quality and Water Level Changes in Poyang Lake Based on 5 Consecutive Years’ Monitoring

“…During the dry season, the water level drops, and the beach is exposed; it then rises during the wet season and the landscape is very different from that in the dry season (Yuan et al, 2015). The water level in the lake is generally highest between June and August, and lowest between December to February (Lan, 2014).…”

Phytoplankton responses to meteorological and hydrological forcing at decadal to seasonal time scales

“…For example, variance partitioning showed that only a small part of variability in water level was attributable to stochastic changes, which is fully comprehensible since it is a strongly autocorrelated variable (Lan, 2014). However, the correlations of phytoplankton with stochastic component of water level remained significant, which is not easy to interpret.…”

A systematic review on machine learning algorithms used for forecasting lake‐water level fluctuations

“…Herein, the training set is for fitting the model with its labels (training phase) that define the meaning of the supervised approach, the validation set is for adjusting or tuning the parameter constraints of the trained algorithms, and the testing set is for measuring or evaluating the performance of the algorithms previously trained and validated. 61 27 and Lan in 2014 32 have splitted their database inputs for evaluating the performance of the models used. As listed in Table 1, the splitting ratio employed is in the range of 0.05-0.50.…”