Regionalization of hydrological model parameters using gradient boosting machine

Regionalization of hydrological model parameters is key to hydrological predictions in ungauged basins. The commonly used multiple linear regression (MLR) method may not be applicable in complex and nonlinear relationships between model parameters and watershed properties. Moreover, most regionalization methods assume lumped parameters for each catchment without considering within-catchment heterogeneity. Here we incorporated the Penman-Monteith-Leuning (PML) equation into the Distributed Time-Variant Gain Model (DTVGM) to improve the mechanistic representation of the evapotranspiration process. We calibrated six key model parameters grid-by-grid across China using a multivariable calibration strategy, which incorporates spatiotemporal runoff and evapotranspiration (ET) datasets (0.25°, monthly) as reference. In addition, we used the gradient boosting machine (GBM), a machine learning technique, to portray the dependence of model parameters on soil and terrain attributes in four distinct climatic zones across China. We show that the modified DTVGM could reasonably estimate the runoff and ET over China using the calibrated parameters, but performed better in humid than arid regions for the validation period. The regionalized parameters by the GBM method exhibited better spatial coherence relative to the calibrated grid-by-grid parameters. In addition, GBM outperformed the stepwise MLR method in both parameter regionalization and gridded runoff simulations at national scale, though the improvement is not significant pertaining to watershed streamflow validation due to most of the watersheds being located in humid regions. We also revealed that the slope, saturated soil moisture content, and elevation are the most important explanatory variables to inform model parameters based on the GBM approach. The machine-learning-based regionalization approach provides an effective alternative to deriving hydrological model parameters by using watershed properties in ungauged regions.

QSAR investigation on benzimidazole derivatives in Trichomonosis’ disease

Globally trichomoniasis affects approximately 152 million people as of 2010 (2.2% of the population). It is more common in women (2.7%) than males (1.4%). The American Social Health Association estimates trichomoniasis affects 7.4 million previously unaffected Americans each year and is the most frequently presenting new infection of the common sexually transmitted diseases. On the pattern, QSAR study has been done on benzimidazole derivatives as potent inhibitors with trichomonicidal activity. Genetic algorithm (GA), artificial neural network (ANN), stepwise multiple linear regression (stepwise-MLR) were used to create then on non-linear and linear QSAR models. Geometry optimization of compounds was carried out by B3LYP method employing 6–31G (2d) basis set. HyperChem, Gaussian 03W, and Dragon (version 5.5) software programs were used for geometry optimization of the molecules and calculation of the quantum chemical descriptors. Finally, Unscrambler program was used for the analysis of data. The root-mean square errors of the training set and the test set for GA–ANN model using jack-knife method, were 0.1840, 0.5051 and R2 was 0.70. Also, the R and R2 values in the gas phase were obtained 0.78, 0.61 from GA-stepwise MLR model. According to the obtained results, we find out GA-ANN model is the most favorable method toward the other statistical methods. Also, we would suggest that compounds No. 20, 33, 58, 48 and 47 as the most appropriate structure for the design of drugs to pharmacists.

Quantitative Analysis of Alcohol, Real Extract, Original Gravity, Nitrogen and Polyphenols in Beers Using NIR Spectroscopy

This study was to develop a rapid and accurate NIR analysis method for determinations of alcohol, real extract, original gravity, total nitrogen and total polyphenols. Commercial European beers (110 samples) were used to create calibration models between EBC (European Brewing Committee) and NIR spectral data. The optimal correlation coefficients ( r) were 0.94 to 0.98 and the corresponding CV% (coefficients of validation variation) were 4.29, 6.53, 4.50, 6.06 and 4.74 for NIR predictions of alcohol, real extract, original gravity, nitrogen and polyphenols, respectively. The stepwise MLR calibration proved to be a good choice for measurements of alcohol and original gravity, while PLS regression models seem to be better for the predictions of the real extract, nitrogen and polyphenols. Comparisons of results from MLR and PLS, demonstrate that MLR methods (log 1/ R) are better than those of PLS (log 1/ R) in calibration and prediction sets. The reflection mode is better than those of transmission in all above cases.