Automated Water Extraction Index: a new technique for surface water mapping using Landsat imagery.

Over the past 15 years, artificial neural networks (ANNs) have been used increasingly for prediction and forecasting in water resources and environmental engineering. However, despite this high level of research activity, methods for developing ANN models are not yet well established. In this paper, the steps in the development of ANN models are outlined and taxonomies of approaches are introduced for each of these steps. In order to obtain a snapshot of current practice, ANN development methods are assessed based on these taxonomies for 210 journal papers that were published from 1999 to 2007 and focus on the prediction of water resource variables in river systems. The results obtained indicate that the vast majority of studies focus on flow prediction, with very few applications to water quality. Methods used for determining model inputs, appropriate data subsets and the best model structure are generally obtained in an ad-hoc fashion and require further attention. Although multilayer perceptrons are still the most popular model architecture, other model architectures are also used extensively. In relation to model calibration, gradient based methods are used almost exclusively. In conclusion, despite a significant amount of research activity on the use of ANNs for prediction and forecasting of water resources variables in river systems, little of this is focused on methodological issues. Consequently, there is still a need for the development of robust ANN model development approaches.

Review: Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions

D. B. Owen: Handbook of Statistical Tables. London: Pergamon Press; Reading, Massachusetts: Addison‐Wesley, 1962. Pp. xii+580. 70s.

Handbook of Statistical Tables.

Neural networks

The normalized difference water index (NDWI) has been successfully used to delineate surface water features. However, two major problems have been often encountered: (a) NDWIs calculated from different band combinations [visible, nearinfrared, or shortwave-infrared (SWIR)] can generate different results, and (b) NDWI thresholds vary depending on the proportions of subpixel water/non-water components. We need to evaluate all the NDWIs for determining the best performing index and to establish appropriate thresholds for clearly identifying water features. We used the spectral data obtained from a spectral library to simulate the satellite sensors Landsat ETM, SPOT-5, ASTER, and MODIS, and calculated the simulated NDWI in different forms. We found that the NDWI calculated from (green ‐ SWIR)/(green SWIR), where SWIR is the shorter wavelength region (1.2 to 1.8 mm), has the most stable threshold. We recommend this NDWI be employed for mapping water, but adjustment of the threshold based on actual situations is necessary.

Analysis of Dynamic Thresholds for the Normalized Difference Water Index

Flood problems resulting due to heavy rainfall and drainage congestion are being regularly experienced in plain areas of Bihar, India. Due to this problem, power plant located in Koa catchment, Kahalgaon, Bihar, is faces huge loss at the time of flood. In this paper, the flood-affected areas in Koa catchment have been mapped using remote sensing satellite data (IRS LISS III, 1999 and Landsat TM, 1995). A range of image processing techniques has been used, including simple density slicing, Tasseled Cap Transformation and water-specific index. The results obtained using different approaches have been analysed. Result indicates that a Normalized Difference Water Index (NDWI) based approach produced best results.

Delineation of flood-prone areas using remote sensing techniques

Hydrological time series modeling: A comparison between adaptive neuro-fuzzy, neural network and autoregressive techniques

Considering the importance of climatic variability on availability of water, irrigation demand, crop yield and other areas of life, an assessment of change detection and trend on monthly, seasonal and annual historical series of different climatic variables of Raipur, a capital city of newly created Chhattisgarh state of India, have been carried out. The change detection analysis has been conceded using Pettitt’s test, von Neumann ratio test, Buishand’s range test and standard normal homogeneity (SNH) test, while non-parametric tests including linear regression, Mann-Kendall and Spearman rho tests have been applied for trend analysis. The annual series of minimum temperature, wind speed, sunshine hour showed significant change points, while evaporation indicated a doubtful case and maximum temperature confirmed the homogeneity at 95 % confidence level. The change point analysis results of meteorological variables indicated different change points from year 1990 to 2000, with maximum change points in and around 1995. This was due to the industrialization and urbanization in this period as this city was selected as capital of Chhattisgarh state. Based on the results of change point analysis and development scenarios in and around Raipur city, trend analysis was applied for three different time periods namely: P-1 from 1971 to 1995, P-2 from 1986 to 2012, and P-3 the whole series from 1971 to 2012. The significant rising trend in the summer and rainy months in case of minimum temperature, and the winter months in case of maximum temperature during the periods P-2 and P-3 may affect water availability and water demands in the region. The relative humidity showed a significant rising trend in few summer and rainy months series of all three periods under investigation, while sunshine hours and evaporation indicated random distribution prior to 1995 (P-1), but a significant falling trend in few winter months and annual series during period P-3. Although the annual minimum, maximum temperatures and relative humidity showed a rising trend, the falling trend of pan evaporation may be due to strong declining trends in wind speed and falling trend in sunshine hour series on a long term basis.

/pdf/statistical-analysis-for-change-detection-and-trend-oslphdk6rv.pdf

Anil Kumar Lohani

Papers

Delineation of flood-prone areas using remote sensing techniques

Hydrological time series modeling: A comparison between adaptive neuro-fuzzy, neural network and autoregressive techniques

Statistical Analysis for Change Detection and Trend Assessment in Climatological Parameters

Improving real time flood forecasting using fuzzy inference system

Takagi–Sugeno fuzzy inference system for modeling stage–discharge relationship