A unique and intensive flux observation matrix was established during May to September of 2012 in an oasis–desert area located in the middle reaches of the Heihe River basin, China. The flux observation matrix included 22 eddy covariance systems belonging to the first thematic experiment of the Heihe Watershed Allied Telemetry Experimental Research (HiWATER) project. The energy balance closure ratio (EBR) was assessed and possible mechanisms were investigated using remote sensing data. The results showed that 1) the EBR was in the range of 0.78–1.04 at all sites with an average EBR of 0.92, and 2) the calculated daily EBR exhibited better performance than the 30-min averages. 3) The heat storage cannot be ignored during the crop growing season. An improvement of approximately 6% in the total closure was found after considering the heat storage terms (canopy and photosynthesis storage) in the energy budget at the maize surface, and the canopy and photosynthesis showed approximately equal contributions of 3% for each storage term. The results also showed that 4) the land heterogeneous surface had a significant effect on the EBR. The EBR decreased with land surface heterogeneity increasing (taking the standard deviation of the surface temperature in the eddy covariance system source area as an index). The EBR also decreased when irrigation occurred and increased after irrigation was completed. The advection or secondary circulation broke the closed system of the energy balance given the phenomenon of EBR increasing when the advection or secondary circulation occurred.

Soil texture and soil particle size fractions (PSFs) play an increasing role in physical, chemical, and hydrological processes. Many previous studies have used machine-learning and log-ratio transformation methods for soil texture classification and soil PSF interpolation to improve the prediction accuracy. However, few reports have systematically compared their performance with respect to both classification and interpolation. Here, five machine-learning models – K-nearest neighbour (KNN), multilayer perceptron neural network (MLP), random forest (RF), support vector machines (SVM), and extreme gradient boosting (XGB) – combined with the original data and three log-ratio transformation methods – additive log ratio (ALR), centred log ratio (CLR), and isometric log ratio (ILR) – were applied to evaluate soil texture and PSFs using both raw and log-ratio-transformed data from 640 soil samples in the Heihe River basin (HRB) in China. The results demonstrated that the log-ratio transformations decreased the skewness of soil PSF data. For soil texture classification, RF and XGB showed better performance with a higher overall accuracy and kappa coefficient. They were also recommended to evaluate the classification capacity of imbalanced data according to the area under the precision–recall curve (AUPRC). For soil PSF interpolation, RF delivered the best performance among five machine-learning models with the lowest root-mean-square error (RMSE; sand had a RMSE of 15.09 %, silt was 13.86 %, and clay was 6.31 %), mean absolute error (MAE; sand had a MAD of 10.65 %, silt was 9.99 %, and clay was 5.00 %), Aitchison distance (AD; 0.84), and standardized residual sum of squares (STRESS; 0.61), and the highest Spearman rank correlation coefficient (RCC; sand was 0.69, silt was 0.67, and clay was 0.69). STRESS was improved by using log-ratio methods, especially for CLR and ILR. Prediction maps from both direct and indirect classification were similar in the middle and upper reaches of the HRB. However, indirect classification maps using log-ratio-transformed data provided more detailed information in the lower reaches of the HRB. There was a pronounced improvement of 21.3 % in the kappa coefficient when using indirect methods for soil texture classification compared with direct methods. RF was recommended as the best strategy among the five machine-learning models, based on the accuracy evaluation of the soil PSF interpolation and soil texture classification, and ILR was recommended for component-wise machine-learning models without multivariate treatment, considering the constrained nature of compositional data. In addition, XGB was preferred over other models when the trade-off between the accuracy and runtime was considered. Our findings provide a reference for future works with respect to the spatial prediction of soil PSFs and texture using machine-learning models with skewed distributions of soil PSF data over a large area.