Dawei Han

Machine Learning Techniques for Downscaling SMOS Satellite Soil Moisture Using MODIS Land Surface Temperature for Hydrological Application

AbstractMany hydrologic phenomena and applications such as drought, flood, irrigation management and scheduling needs high resolution satellite soil moisture data at a local/regional scale. Downscaling is a very important process to convert a coarse domain satellite data to a finer spatial resolution. Three artificial intelligence techniques along with the generalized linear model (GLM) are used to improve the spatial resolution of Soil Moisture and Ocean Salinity (SMOS) derived soil moisture, which is currently available at a very coarse scale of ~40 Km. Artificial neural network (ANN), support vector machine, relevance vector machine and generalized linear models are chosen for this study to integrate the Moderate Resolution Imaging Spectroradiometer (MODIS) Land Surface Temperature (LST) with the SMOS derived soil moisture. Soil moisture deficit (SMD) derived from a hydrological model called PDM (Probability Distribution Model) is used for the downscaling performance evaluation. The statistical evaluation has also been made with the day-time and night-time MODIS LST differences with the mean day and night-time PDM SMD data for the selection of effective MODIS products. The accuracy and robustness of all the downscaling algorithms are discussed in terms of their assumptions and applicability. The statistical performance indices such as R2, %Bias and RMSE indicates that the ANN (R2  = 0.751, %Bias = −0.628 and RMSE = 0.011), RVM (R2  = 0.691, %Bias = 1.009 and RMSE = 0.013), SVM (R2  = 0.698, %Bias = 2.370 and RMSE = 0.013) and GLM (R2  = 0.698, %Bias = 1.009 and RMSE = 0.013) algorithms on the whole are relatively more skillful to downscale the variability of the soil moisture in comparison to the non-downscaled data (R2  = 0.418 and RMSE = 0.017) with the outperformance of ANN algorithm. The other attempts related to growing and non-growing seasons have been used in this study to reveal that season based downscaling is even better than continuous time series with fairly high performance statistics.

Automated Thiessen polygon generation

Data uncertainty research of rain gauge network requires generation of large numbers of Thiessen polygons. Despite its importance in hydrology, few studies on computational Thiessen polygons have been carried out, and there is little published information in the hydrological literature. This paper describes two automated approaches and the ways for their implementation in hydrological applications: triangulation method and grid method. Triangulation is a lossless method but suffers from complications in coding and slow computational speed with small numbers of gauges. Grid method is easy to implement, but a compromise must be made between the computational grid size, accuracy, and speed. This paper describes a procedure to derive the relationship between the catchment area, grid size, and accuracy indicator based on weighted mean error. The computational speed comparison between the two methods has been found to follow a logarithm curve, and the critical number of gauges could be found from this curve for deciding the method choice if the computational speed is the limiting factor in a project.

Daily Pan Evaporation Modeling in a Hot and Dry Climate

Evaporation plays a key role in water resources management in arid and semiarid climatic regions. This is the first time that an artificial neural network (ANN) model is applied to estimate evaporation in a hot and dry region (BWh climate by the Koppen classification). It has been found that ANN works very well at the study site and, further, an integrated ANN and autoregressive with exogeneous inputs can have an improved performance over the traditional ANN. Both models significantly outperformed the two empirical methods. It has been demonstrated that the important weather factors to be included in the model inputs are wind speed, saturation vapor pressure deficit, and relative humidity. This result is different from all those reported in the literature and is interestingly linked with a 1936 study by Anderson, who emphasized the importance of saturation vapor pressure deficit. As evaporation is a nonlinear dynamic process, the selection of suitable input weather variables has been a complicated and tim...

Data fusion techniques for improving soil moisture deficit using SMOS satellite and WRF-NOAH Land surface model

Microwave remote sensing and mesoscale weather models have high potential to monitor global hydrological processes. The latest satellite soil moisture dedicated mission SMOS and WRF-NOAH Land Surface Model (WRF-NOAH LSM) provide a flow of coarse resolution soil moisture data, which may be useful data sources for hydrological applications. In this study, four data fusion techniques: Linear Weighted Algorithm (LWA), Multiple Linear Regression (MLR), Kalman Filter (KF) and Artificial Neural Network (ANN) are evaluated for Soil Moisture Deficit (SMD) estimation using the SMOS and WRF-NOAH LSM derived soil moisture. The first method (and most simplest) utilizes a series of simple combinations between SMOS and WRF-NOAH LSM soil moisture products, while the second uses a predictor equation generally formed by dependent variables (Probability Distributed Model based SMD) and independent predictors (SMOS and WRF-NOAH LSM). The third and fourth techniques are based on rigorous calibration and validation and need proper optimisation for the final outputs backboned by strong non-linear statistical analysis. The performances of all the techniques are validated against the probability distributed model based soil moisture deficit as benchmark; estimated using the ground based observed datasets. The observed high Nash Sutcliffe Efficiencies between the fused datasets with Probability Distribution Model clearly demonstrate an improved performance from the individual products. However, the overall analysis indicates a higher capability of ANN and KF for data fusion than the LWA or MLR approach. These techniques serve as one of the first demonstrations that there is hydrological relevant information in the coarse resolution SMOS satellite and WRF-NOAH LSM data, which could be used for hydrological applications.

Error Correction Modelling of Wind Speed Through Hydro-Meteorological Parameters and Mesoscale Model: A Hybrid Approach

Accurate estimation of wind speed is essential for many hydrological applications. One way to generate wind velocity is from the fifth generation PENN/NCAR MM5 mesoscale model. However, there is a problem in using wind speed data in hydrological processes due to large errors obtained from the mesoscale model MM5. The theme of this article has been focused on hybridization of MM5 with four mathematical models (two regression models- the multiple linear regression (MLR) and the nonlinear regression (NLR), and two artificial intelligence models – the artificial neural network (ANN) and the support vector machines (SVMs)) in such a way so that the properly modelled schemes reduce the wind speed errors with the information from other MM5 derived hydro-meteorological parameters. The forward selection method was employed as an input variable selection procedure to examine the model generalization errors. The input variables of this statistical analysis include wind speed, temperature, relative humidity, pressure, solar radiation and rainfall from the MM5. The proposed conjunction structure was calibrated and validated at the Brue catchment, Southwest of England. The study results show that relatively simple models like MLR are useful tools for positively altering the wind speed time series obtaining from the MM5 model. The SVM based hybrid scheme could make a better robust modelling framework capable of capturing the non-linear nature than that of the ANN based scheme. Although the proposed hybrid schemes are applied on error correction modelling in this study, there are further scopes for application in a wide range of areas in conjunction with any higher end models.

River Flow Modelling Using Fuzzy Decision Trees

A modern real time flood forecasting system requires itsmathematical model(s) to handle highly complex rainfall runoffprocesses. Uncertainty in real time flood forecasting willinvolve a variety of components such as measurement noise fromtelemetry systems, inadequacy of the models, insufficiency ofcatchment conditions, etc. Probabilistic forecasting is becomingmore and more important in this field. This article describes a novel attempt to use a Fuzzy Logic approach for river flow modelling based on fuzzy decision trees. These trees are learntfrom data using the MA-ID3 algorithm. This is an extension of Quinlans ID3 and is based on mass assignments. MA-ID3 allows for the incorporation of fuzzy attribute and class values intodecision trees aiding generalisation and providing a framework for representing linguistic rules. The article showed that with only five fuzzy labels, the FDT model performed reasonably welland a comparison with a Neural Network model (Back Propagation)was carried out. Furthermore, the FDT model indicated that therainfall values of four or five days before the prediction time are regarded as more informative to the prediction than the morerecent ones. Although its performance is not as good as the neural network model in the test case, its glass box nature couldprovide some useful insight about the hydrological processes.

Integrated framework for monitoring groundwater pollution using a geographical information system and multivariate analysis

Abstract Appropriate assessment of groundwater is important to ensure sustainable and safe use of this natural resource. However, evaluating overall groundwater quality is difficult due to the spatial variability of multiple contaminants. This research proposes a geographical information system (GIS)-based groundwater quality pollution mapping technique, which synthesizes different available water quality data, normalized with the World Health Organization (WHO) standards. The normalized difference index (NDI) is used to perform the normalization process. This study utilizes a multi-criteria evaluation (MCE) script (MATLAB 10.0), developed to assign weights to each of the analysed water quality parameters. The consistency of judgments of weight assignment is further analysed using the consistency ratio (CR) and consistency index (CI) techniques. The Shuttle Radar Topography Mission (SRTM) C-band radar and Landsat TM satellite image data are used to derive a digital elevation model (DEM) and land-use/land-cover map of the area. A new sensitivity analysis method is introduced to estimate the responsible factors associated with the proposed groundwater pollution zone model (GPZM). Multivariate analysis methods, such as factor analysis (FA), cluster analysis (CA) and principal component analysis (PCA), are used to uncover the latent structure of the data, to understand the correlations across hierarchical levels, and for dimensionality reduction, respectively. Editor D. Koutsoyiannis; Associate editor Chong-yu Xu Citation Srivastava, P. K., Han, D., Gupta, M., and Mukherjee, S., 2012. Integrated framework for monitoring groundwater pollution using a geographical information system and multivariate analysis. Hydrological Sciences Journal, 57 (7), 1453–1472.

Most computational hydrology is not reproducible, so is it really science?

Reproducibility is a foundational principle in scientific research. Yet in computational hydrology the code and data that actually produces published results are not regularly made available, inhibiting the ability of the community to reproduce and verify previous findings. In order to overcome this problem we recommend that reuseable code and formal workflows, which unambiguously reproduce published scientific results, are made available for the community alongside data, so that we can verify previous findings, and build directly from previous work. In cases where reproducing large-scale hydrologic studies is computationally very expensive and time-consuming, new processes are required to ensure scientific rigor. Such changes will strongly improve the transparency of hydrological research, and thus provide a more credible foundation for scientific advancement and policy support.

Integrated Planning of Land Use and Water Allocation on a Watershed Scale Considering Social and Water Quality Issues

AbstractSustainable development in river basins depends on sound management of land use and water allocation policies. Integrated water resources management (IWRM) is considered a path to bring many elements within the development schemes together toward a unified land-water planning and management process. In this study, an integrated water resources management model is developed to connect three groups of decision makers in pollution control, agricultural planning, and water resources allocation with economic, environmental, and social objectives. A genetic algorithm–based optimization model is developed for providing desirable water quality and quantity while maximizing agricultural production in the upstream region, mitigating the unemployment (social) impacts of land use changes, and providing reliable water supply to the downstream region. The upstream region is divided into subbasins, and a fuzzy-based multiobjective optimization model is used to determine the optimal land uses in each subbasin and...

Appraisal of NLDAS-2 Multi-Model Simulated Soil Moistures for Hydrological Modelling

Soil moisture is a key variable in hydrological modelling, which could be estimated by land surface modelling. However the previous studies have focused on evaluating these soil moisture estimates by using point-based measurements, and there is a lack of attention for their appraisal over basin scales particularly for hydrological applications. In this study, we carry out for the first time, a detailed evaluation of five sources of soil moisture products (NLDAS-2 multi-model simulated soil moistures: Noah, VIC, Mosaic and SAC; and a ground observation), against a widely used hydrological model Xinanjiang (XAJ) as a benchmark at a U.S. basin. Generally speaking, all products have good agreements with the hydrological soil moisture simulation, with superior performance obtained from the SAC model and the VIC model. Furthermore, the results indicate that the in-situ measurements in deeper soil layer are still usable for hydrological applications. Nevertheless further improvement is still required on the definition of land surface model layer thicknesses and the related data fusion with the remotely sensed soil moisture. The potential usage of the NLDAS-2 soil moisture datasets in real-time flood forecasting is discussed.