Effects of Water Management Strategies on Water Balance in a Water Scarce Region: A Case Study in Beijing by a Holistic Model

A comparative study among machine learning and numerical models for simulating groundwater dynamics in the Heihe River Basin, northwestern China

Groundwater is unique resource for agriculture, domestic use, industry and environment in the Heihe River Basin, northwestern China. Numerical models are effective approaches to simulate and analyze the groundwater dynamics under changeable conditions and have been widely used all over the world. In this paper, the groundwater dynamics of the middle reaches of the Heihe River Basin was simulated using one numerical model and three machine learning algorithms (multi-layer perceptron (MLP); radial basis function network (RBF); support vector machine (SVM)). Historical groundwater levels and streamflow rates were used to calibrate/train and verify the different methods. The root mean square error and R² were used to evaluate the accuracy of the simulation/training and verification results. The results showed that the accuracy of machine learning models was significantly better than that of numerical model in both stages. The SVM and RBF performed the best in training and verification stages, respectively. However, it should be noted that the generalization ability of numerical model is superior to the machine learning models because of the inclusion of physical mechanism. This study provides a feasible and accurate approach for simulating groundwater dynamics and a reference for model selection.

Variation in actual evapotranspiration following changes in climate and vegetation cover during an ecological restoration period (2000-2015) in the Loess Plateau, China

The spatial distribution of water resources largely influences Earth ecosystems and human civilization. Being a major component of the global water cycle, evapotranspiration (ET) serves as an indicator of the availability of water resources. Understanding the actual ET (ET_a) variation mechanism at different spatial and temporal scales can improve management of water use within the sustainable development limits. In this study, remote sensing derived ET_a data were used to study water resource fluctuations in the Loess Plateau, China. This region covers diverse climate types from humid to arid and experienced large changes in vegetation cover during a revegetation project between 2000 and 2015. The relations between spatiotemporal variation of ET_a, climate factors and vegetation change were explored using statistical methods. The results show that cropland, forestland and grassland take the largest percentage of total ET_a. Total ET_a exhibited a marginally increasing trend (p < 0.1) during 2000-2010 and no trend during 2011-2015. Windspeed and vegetation cover index highly influenced ET_a, followed by atmospheric pressure, air humidity, precipitation, bright sunshine duration and temperature. Temperature has little effect on ET_a throughout the Loess Plateau. The monitoring of water resources based upon water balance between precipitation, ET_a and river flow changes shows that water consumption deficit is consistent with vegetation changes: it was large during 2000-2010 when vegetation increased rapidly and decreased after 2010. These results could help to develop different water saving strategies across the Loess Plateau and build a better monitoring system of water resources.