Sustainable water resource management requires the assessment of hydrological changes in response to climate fluctuations and anthropogenic activities in any given area. A quantitative estimation of water balance entities is important to understand the variations within a basin. Water resources in remote areas with little infrastructure and technological knowhow suffer from poor documentation, rendering water management difficult and unreliable. This study analyzes the changes in the hydrological behavior of the Lake Chad basin with extreme climatic and environmental conditions that hinder the collection of field observations. Total water storage (TWS) from the Gravity Recovery and Climate Experiment (GRACE), lake level variations from satellite altimetry, and water fluxes and soil moisture from Global Land Data Assimilation System (GLDAS) were used to study the spatiotemporal variability of the hydrological parameters of the Lake Chad basin. The estimated TWS varies in a similar pattern as the lake water level. TWS in the basin area is governed by the lake's surface water. The subsurface water volume changes were derived by combining the altimetric lake volume with the TWS over the drainage basin. The results were compared with groundwater outputs from WaterGAP Global Hydrology Model (WGHM), with both showing a somewhat similar pattern. These results could provide an insight to the availability of water resources in the Lake Chad basin for current and future management purposes.

Consistent observations of lakes and reservoirs that comprise the majority of surface freshwater globally are limited, especially in Africa where water bodies are exposed to unfavorable climatic conditions and human interactions. Publicly available satellite imagery has increased the ability to monitor water bodies of various sizes without much financial hassle. Landsat 7 and 8 images were used in this study to estimate area changes around Lake Chad. The Automated Water Extraction Index (AWEI), Normalized Difference Water Index (NDWI), Modified Normalized Difference Water Index (MNDWI) and Normalized Difference Vegetation Index (NDVI) were compared for the remote sensing retrieval process of surface water. Otsu threshold method was used to separate water from non-water features. With an overall accuracy of ~96% and an inter-rater agreement (kappa coefficient) of 0.91, the MNDWI was a better indicator for mapping recent area changes in Lake Chad and was used to estimate the lake’s area changes from 2003–2016. Extracted monthly areas showed an increasing trend and ranged between ~1242 km2 and 2231 km2 indicating high variability within the 13-year period, 2003–2016. In addition, we combined Landsat measurements with Total Water Storage Anomaly (TWSA) data from the Gravity Recovery and Climate Experiment (GRACE) satellites. This combination is well matched with our estimated surface area trends. This work not only demonstrates the importance of remote sensing in sparsely gauged developing countries, it also suggests the use of freely available high-quality imagery data to address existing lake crisis.

Drought is a complex phenomenon caused by lack of precipitation that affects water resources and human society. Groundwater drought is difficult to assess due to its complexity and the lack of spatio-temporal groundwater observations. In this study, we present an approach to evaluate groundwater drought based on relatively high spatial resolution groundwater storage change data. We developed an artificial neural network (ANN) that employed satellite data (Gravity Recovery and Climate Experiment (GRACE) and Tropical Rainfall Measuring Mission (TRMM)) as well as Global Land Data Assimilation System (GLDAS) models. The Standardized Groundwater Level Index (SGI) was calculated by normalizing ANN-predicted groundwater storage changes from 2003 to 2015 across South Korea. The ANN-predicted 25 km groundwater storage changes correlated well with both the in situ and the water balance equation (WBE)-estimated groundwater storage changes, with mean correlation coefficients of 0.87 and 0.64, respectively. The Standardized Precipitation–Evapotranspiration Index (SPEI), having an accumulation time of 1–6 months, and the Palmer Drought Severity Index (PDSI) were used to validate the SGI. The results showed that the SGI had a pattern similar to that of SPEI-1 and SPEI-2 (1- and 2-month accumulation periods, respectively), and PDSI. However, the SGI performance fluctuated slightly due to its relatively short study period (13 years) as compared to SPEI and PDSI (more than 30 years). The SGI, which was developed using a new approach in this study, captured the characteristics of groundwater drought, thus presenting a framework for the assessment of these characteristics.

No abstract

Estimation of total discharge is necessary to understand the hydrological cycle and to manage water resources efficiently. However, the task is problematic in an area where ground observations are limited. The North Korea region is one example. Here, the total discharge was estimated based on the water balance using multiple satellite products. They are the terrestrial water storage changes (TWSC) derived from the Gravity Recovery and Climate Experiment (GRACE), precipitation from the Tropical Rainfall Measuring Mission (TRMM), and evapotranspiration from the Moderate Resolution Imaging Spectroradiometer (MODIS). The satellite-based discharge was compared with land surface model products of the Global Land Data Assimilation System (GLDAS), and a positive relationship between the results was obtained (r = 0.70-0.86; bias = −9.08-16.99 mm/month; RMSE = 36.90-62.56 mm/month; NSE = 0.01-0.62). Among the four land surface models of GLDAS (CLM, Mosaic, Noah, and VIC), CLM corresponded best with the satellite-based discharge, satellite-based discharge has a tendency to slightly overestimate compared to model-based discharge (CLM, Mosaic, Noah, and VIC) in the dry season. Also, the total discharge data based on the Precipitation-Runoff Modeling System (PRMS) and the in situ discharge for major five river basins in South Korea show comparable seasonality and high correlation with the satellite-based discharge. In spite of the relatively low spatial resolution of GRACE, and loss of information incurred during the process of integrating three different satellite products, the proposed methodology can be a practical tool to estimate the total discharge with reasonable accuracy, especially in a region with scarce hydrologic data.

No abstract

Abstract. In this study, we propose an improved version of the dynamic movement-based location update scheme that stores all cells visited by the MS, and their neighboring cells, to reduce the location update cost of the dynamic movement-based location update scheme. We show that a significant reduction in the location update cost is achieved in our scheme. We also show that our scheme has optimal total cost when the threshold is rather small. Additionally, the MS requires a minimal amount of memory to successfully implement our scheme.

Consumer Credit Risk Analysis is an important factor in financial institution as it would be possible to lend credit to only to consumers that have good credit. Besides using traditional methods such as credit scoring, machine learning can also be used as a tool to classify applications for credit. Many research papers had tested and concluded of the ability of machine learning methods to classify good and bad credit. From the previous papers it was concluded that Ensemble Method, Support Vector Machine and MLP (Neural Network) showed the best accuracy in credit risk. However those previous papers compared only a few algorithms so it is difficult to determine which algorithm has the best performance. Therefore, this paper will compare the algorithms from previous paper by applying the German dataset to the algorithms as it is the most common dataset used for credit risk analysis. The algorithms compared are Logistic Regression, Linear Discriminant Analysis, Support Vector Machine, Naïve Bayes, K-Nearest Neighbors, Decision Tree, Ensemble Methods (random forest, bagging, boosting) and MLP. The performance will be measured using accuracy, average accuracy from 10 fold cross validation, AUC, Sensitivity, Specificity, Precision rate, F1. This paper will focus to find the most accurate algorithm for credit risk analysis. From the result it was found out that Logistic Regression, Support Vector Machine and Bagging had a good result. However, since the scores were dispersed, it was difficult to conclude which algorithm had the best accuracy. At the end SVM was chosen as it was deemed to be the most accurate algorithm for credit risk analysis