scholarly journals Filling and validating rainfall data based on statistical techniques and artificial intelligence

2021 ◽  
Vol 16 (6) ◽  
pp. 1-14
Author(s):  
Camila Bermond Ruezzene ◽  
Renato Billia de Miranda ◽  
Talyson de Melo Bolleli ◽  
Frederico Fábio Mauad
Keyword(s):  
Neural Networks ◽  
Multiple Regression ◽  
Coefficient Of Determination ◽  
Ratio Method ◽  
Statistical Techniques ◽  
Precipitation Data ◽  
Gap Filling ◽  
Distance Weighting ◽  
Normal Ratio ◽  
Inverse Distance

The study of the hydric regime of rainfall helps in management analysis and decision-making in hydrographic basins, but a fundamental condition is the need for continuous time series of data. Therefore, this study compared gap filling methods in precipitation data and validated them using robust statistical techniques. Precipitation data from the municipality of Itirapina, which has four monitoring stations, were used. Four gap filling techniques were used, namely: normal ratio method, inverse distance weighting, multiple regression and artificial neural networks, in the period from 1979 to 1989. For validation and performance evaluation, the coefficient of determination (R²), mean absolute error (MAE), mean squared error (RMSE), Nash-Sutcliffe coefficient (Nash), agreement index (D), confidence index were used (C) and through non-parametric techniques with Mann-Witney and Kruskal-Wallis test. Excellent performances of real data were verified in comparison with estimated data, with values above 0.8 of the coefficient of determination (R²) and of Nash. Kruskal-Wallis and Mann-Whitney tests were not significant in Stations C1 and C2, demonstrating that there is a difference between real and estimated data and between the proposed methods. It was concluded that the multiple regression and neural network methods showed the best performance. From this study, efficient tools were found to fill the gap, thus promoting better management and operation of water resources. Keywords: artificial neural networks, inverse distance weighting, multiple regression, normal ratio method.

scholarly journals A Multimethod Analysis for Average Annual Precipitation Mapping in the Khorasan Razavi Province (Northeastern Iran)

Atmosphere ◽  
2021 ◽  
Vol 12 (5) ◽  
pp. 592
Author(s):  
Mehdi Aalijahan ◽  
Azra Khosravichenar
Keyword(s):  
Regional Planning ◽  
Interpolation Method ◽  
Absolute Error ◽  
Rain Gauge ◽  
Annual Precipitation ◽  
Coefficient Of Determination ◽  
Distance Weighting ◽  
Average Annual Precipitation ◽  
Inverse Distance

The spatial distribution of precipitation is one of the most important climatic variables used in geographic and environmental studies. However, when there is a lack of full coverage of meteorological stations, precipitation estimations are necessary to interpolate precipitation for larger areas. The purpose of this research was to find the best interpolation method for precipitation mapping in the partly densely populated Khorasan Razavi province of northeastern Iran. To achieve this, we compared five methods by applying average precipitation data from 97 rain gauge stations in that province for a period of 20 years (1994–2014): Inverse Distance Weighting, Radial Basis Functions (Completely Regularized Spline, Spline with Tension, Multiquadric, Inverse Multiquadric, Thin Plate Spline), Kriging (Simple, Ordinary, Universal), Co-Kriging (Simple, Ordinary, Universal) with an auxiliary elevation parameter, and non-linear Regression. Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and the Coefficient of Determination (R2) were used to determine the best-performing method of precipitation interpolation. Our study shows that Ordinary Co-Kriging with an auxiliary elevation parameter was the best method for determining the distribution of annual precipitation for this region, showing the highest coefficient of determination of 0.46% between estimated and observed values. Therefore, the application of this method of precipitation mapping would form a mandatory base for regional planning and policy making in the arid to semi-arid Khorasan Razavi province during the future.

scholarly journals Development and evaluation of an extended inverse distance weighting method for streamflow estimation at an ungauged site

2015 ◽  
Vol 47 (2) ◽  
pp. 333-343 ◽  
Author(s):  
Muhammad Waseem ◽  
Muhammad Ajmal ◽  
Ungtae Kim ◽  
Tae-Woong Kim
Keyword(s):  
Weighted Average ◽  
Inverse Distance Weighting ◽  
General Idea ◽  
Coefficient Of Determination ◽  
Weighting Method ◽  
Ungauged Sites ◽  
Distance Weighting ◽  
Leave One Out ◽  
Mean Square Errors ◽  
Inverse Distance

In spatial interpolation, one of the most widely used deterministic methods is the inverse distance weighting (IDW) technique. The general idea of IDW is primarily based on the hypothesis that the attribute value of an ungauged site is the weighted average of the known attribute values within the neighborhood, and the ‘weights’ are merely associated with the horizontal distances between the gauged and ungauged sites. However, here we propose an extended version of IDW (hereafter, called the EIDW method) to provide ‘alternative weights’ based on the blended geographical and physiographical spaces for estimation of streamflow percentiles at ungauged sites. Based on the leave-one-out cross-validation procedure, the coefficient of determination had a value of 0.77 and 0.82 for the proposed EIDW models, M1 and M2, respectively, with low root mean square errors. Moreover, after investigating the relationship between the prediction efficiency and the distance decay parameter (C), the better performance of the M1 and M2 resulted at C = 2. Furthermore, the results of this study show that the EIDW could be considered as a constructive way forward to provide more accurate and consistent results in comparison to the traditional IDW or the dimension reduction technique-based IDW.

scholarly journals Evaluation of Satellite and Reanalysis Precipitation Products Using GIS for All Basins in Turkey

2019 ◽  
Vol 2019 ◽  
pp. 1-11 ◽  
Author(s):  
Ahmet Irvem ◽  
Mustafa Ozbuldu
Keyword(s):  
Rain Gauge ◽  
Coefficient Of Determination ◽  
Data Sets ◽  
The West ◽  
Data Set ◽  
Precipitation Product ◽  
Distance Weighting ◽  
Areal Precipitation ◽  
Average Annual Precipitation ◽  
Inverse Distance

Use of the satellite and reanalysis precipitation products, as supplementary data sources, are steadily rising for hydrometeorological applications, especially in data-sparse areas. However, the accuracy of these data sets is often lacking, especially in Turkey. This study evaluates the accuracy of satellite precipitation product (TRMM 3B42V7) and reanalysis precipitation product (NCEP-CFSR) against rain gauge observations for the 1998–2010 periods. Average annual precipitation for the 25 basins in Turkey was calculated using rain gauge precipitation data from 225 stations. The inverse distance weighting (IDW) method was used to calculate areal precipitation for each basin using GIS. According to the results of statistical analysis, the coefficient of determination for the TRMM product gave satisfactory results (R2 > 0.88). However, R2 for the CFSR data set ranges from 0.35 for the Eastern Black Sea basin to 0.93 for the West Mediterranean basin. RMSE was calculated to be 95.679 mm and 128.097 mm for the TRMM and CFSR data, respectively. The NSE results of TRMM data showed very good performance for 6 basins, while the PBias value showed very good performance for 7 basins. The NSE results of CFSR data showed very good performance for 3 basins, while the PBias value showed very good performance for 6 basins.

Precipitation Estimation at the Site of Transmission Tower Using Geographic Information System

2014 ◽  
Vol 955-959 ◽  
pp. 3869-3874
Author(s):  
Leehter Yao ◽  
Teng Shih Tsai ◽  
Rong Chi Chang
Keyword(s):  
Information System ◽  
Spatial Interpolation ◽  
Precipitation Data ◽  
Transmission Tower ◽  
Transmission Towers ◽  
Computational Speed ◽  
Distance Weighting ◽  
Precipitation Estimation ◽  
Central Weather Bureau ◽  
Inverse Distance

A method calculating the precipitation at the site of every transmission tower based on the precipitation estimation data is proposed. An inverse-distance weighting (IDW) method is modified for spatial interpolation of the precipitation data received from Central Weather Bureau. Accuracy and computational speed are both put into consideration in the design of the proposed approach because vast amount of transmission towers is required to process at a time.

scholarly journals Evaluation of Infilling Methods for Time Series of Daily Temperature Data: Case Study of Limpopo Province, South Africa

Climate ◽  
2019 ◽  
Vol 7 (7) ◽  
pp. 86 ◽  
Author(s):  
Zakhele Phumlani Shabalala ◽  
Mokhele Edmond Moeletsi ◽  
Mphethe Isaac Tongwane ◽  
Sabelo Marvin Mazibuko
Keyword(s):  
South Africa ◽  
Multiple Regression ◽  
Limpopo Province ◽  
Maximum Temperature ◽  
Mean Bias Error ◽  
Climate Data ◽  
Daily Minimum ◽  
Normal Ratio ◽  
Maximum Temperatures ◽  
Inverse Distance

Incomplete climate records pose a major challenge to decision makers that utilize climate data as one of their main inputs. In this study, different climate data infilling methods (arithmetic averaging, inverse distance weighting, UK traditional, normal ratio and multiple regression) were evaluated against measured daily minimum and maximum temperatures. Eight target stations that are evenly distributed in Limpopo province, South Africa, were used. The objective was to recommend the best approach that results in lowest errors. The optimum number of buddy/neighboring weather stations required for best estimate for each of the approaches was determined. The evaluation indices employed in this study were the correlation coefficient (r), mean absolute error (MAE), root mean square error (RMSE), accuracy rate (AR) and mean bias error (MBE). The results showed high correlation (r > 0.92) for all the stations, different methods and varying number of neighboring stations utilised. The MAE [RMSE] for the best performing methods (multiple regression and UK traditional) of estimating daily minimum temperature and maximum temperature was less than 1.8 °C [2.3 °C] and 1.0 °C [1.6 °C], respectively. The AR technique showed the MR method as the best approach of estimating daily minimum and maximum temperatures. The other recommended methods are the UK traditional and normal ratio. The MBEs for the arithmetic averaging and inverse-distance weighing techniques are large, indicating either over- or underestimating of the air temperature in the province. Based on the low values for the error estimating statistics, these data infilling methods for daily minimum and maximum air temperatures using neighboring stations data can be utilised to complete the datasets that are used in various applications.

Application of the "genRE" approach to spatial interpolation of precipitation gauge data for the Suir River Basin

2021 ◽  
Author(s):  
Georgios Boumis ◽  
Bart van Osnabrugge ◽  
Jan Verkade
Keyword(s):  
Real Time ◽  
River Basin ◽  
Spatial Interpolation ◽  
Cross Validation ◽  
Inverse Distance Weighting ◽  
Data Sets ◽  
Precipitation Data ◽  
Data Set ◽  
Distance Weighting ◽  
Inverse Distance

<p>Operational near real-time flood forecasting relies heavily on adequate spatial interpolation of precipitation forcing which bears a huge impact on the accuracy of hydrologic forecasts. In this study, the generalized REGNIE (genRE) interpolation technique is examined. The genRE approach was shown to enhance the traditional Inverse Distance Weighting (IDW) method with information from existing observed climatological precipitation data sets (Van Osnabrugge, 2017). The successful application of the genRE method with a re-analysis precipitation data set, expands the applicability of the method as detailed re-analysis data sets become more prevalent while high density observation networks remain scarce.</p><p>Here, the approach is extended to use climatological precipitation data from the Met Éireann’s Re-Analysis (MÉRA). Investigations are carried out using hourly precipitation accumulations for two major flood events induced by Atlantic storms in the Suir River Basin, Ireland. Alongside genRE, the following techniques are comparatively explored: Inverse Distance Weighting (IDW), Ordinary Kriging (OK) and Regression Kriging (RK). Cross-validation is applied in order to compare the different interpolation methods, while spatial maps and correlation coefficients are utilized for assessing the skill of the interpolators to emulate the climatology of MÉRA. In the process, a preliminary intercomparison between the observed precipitation and MÉRA precipitation for the two events is also made.</p><p>In a statistical sense, cross-validation results verify that genRE performs slightly better than all three interpolation techniques for both events studied. Overall, OK is found to be the most inadequate approach, specifically in terms of preserving the original variance in observed precipitation. MÉRA manages to reproduce the temporal variations of observations in a good manner for both events, whereas it displays less skill when considering spatial variations especially where topography has a major influence. Finally, genRE outperforms all other interpolators in mimicking the climatological conditions of MÉRA for both events.</p><p> </p><p>Van Osnabrugge, B., Weerts, A.H. and Uijlenhoet, R., 2017. genRE: A method to extend gridded precipitation climatology data sets in near real-time for hydrological forecasting purposes. Water Resources Research, 53(11), pp.9284-9303.</p>

scholarly journals Neural networks for the generation of sea bed models using airborne lidar bathymetry data

2016 ◽  
Vol 65 (1) ◽  
pp. 41-54 ◽  
Author(s):  
Tomasz Kogut ◽  
Joachim Niemeyer ◽  
Aleksandra Bujakiewicz
Keyword(s):  
Neural Networks ◽  
Airborne Lidar ◽  
Small Subset ◽  
Data Sets ◽  
Airborne Laser ◽  
Sea Bed ◽  
Distance Weighting ◽  
Airborne Lidar Bathymetry ◽  
Inverse Distance ◽  
Echo Sounding

Abstract Various sectors of the economy such as transport and renewable energy have shown great interest in sea bed models. The required measurements are usually carried out by ship-based echo sounding, but this method is quite expensive. A relatively new alternative is data obtained by airborne lidar bathymetry. This study investigates the accuracy of these data, which was obtained in the context of the project ‘Investigation on the use of airborne laser bathymetry in hydrographic surveying’. A comparison to multi-beam echo sounding data shows only small differences in the depths values of the data sets. The IHO requirements of the total horizontal and vertical uncertainty for laser data are met. The second goal of this paper is to compare three spatial interpolation methods, namely Inverse Distance Weighting (IDW), Delaunay Triangulation (TIN), and supervised Artificial Neural Networks (ANN), for the generation of sea bed models. The focus of our investigation is on the amount of required sampling points. This is analyzed by manually reducing the data sets. We found that the three techniques have a similar performance almost independently of the amount of sampling data in our test area. However, ANN are more stable when using a very small subset of points.

scholarly journals Methodology for spatialization of intense rainfall equation parameters

2014 ◽  
Vol 34 (3) ◽  
pp. 485-495 ◽  
Author(s):  
Alexandre C. Xavier ◽  
Roberto A. Cecílio ◽  
Fernando F. Pruski ◽  
Julião S. de S. Lima
Keyword(s):  
Specific Area ◽  
Coefficient Of Determination ◽  
Percentage Error ◽  
P Value ◽  
Intense Rainfall ◽  
Validation Data ◽  
Significance Level ◽  
Area Of Interest ◽  
Distance Weighting ◽  
Inverse Distance

The aim of this study was to generate maps of intense rainfall equation parameters using interpolated maximum intense rainfall data. The study area comprised Espírito Santo State, Brazil. A total of 59 intense rainfall equations were used to interpolate maximum intense rainfall, with a 1 x 1 km spatial resolution. Maximum intense rainfall was interpolated considering recurrence of 2; 5; 10; 20; 50 and 100 years, and duration of 10; 20; 30; 40; 50; 60; 120; 240; 360; 420; 660; 720; 900; 1,140; 1,380 and 1,440 minutes, resulting in 96 maps of maximum intense rainfall. The used interpolators were inverse distance weighting and ordinary kriging, for which significance level (p-value) and coefficient of determination (R²) were evaluated for the cross-validation data, choosing the method that presented better R² to generate maps. Finally, maps of maximum intense precipitation were used to estimate, cell by cell, the intense rainfall equation parameters. In comparison with literature data, the mean percentage error of estimated intense rainfall equations was 13.8%. Maps of spatialized parameters, obtained in this study, are of simple use; once they are georeferenced, they may be imported into any geographic information system to be used for a specific area of interest.

scholarly journals Spatial Distribution of Soil Nutrients in Farmland in a Hilly Region of the Pearl River Delta in China Based on Geostatistics and the Inverse Distance Weighting Method

Agriculture ◽  
2021 ◽  
Vol 11 (1) ◽  
pp. 50
Author(s):  
Rumi Wang ◽  
Runyan Zou ◽  
Jianmei Liu ◽  
Luo Liu ◽  
Yueming Hu
Keyword(s):  
Spatial Distribution ◽  
Pearl River Delta ◽  
Pearl River ◽  
Weighting Method ◽  
Farmland Protection ◽  
The Pearl River Delta ◽  
Hilly Region ◽  
Distance Weighting ◽  
The Pearl River ◽  
Inverse Distance

Soil nutrients are essential factors that reflect farmland quality. Nitrogen, phosphorus, and potassium are essential elements for plants, while silicon is considered a “quasi-essential” element. This study investigated the spatial distribution of plant nutrients in soil in a hilly region of the Pearl River Delta in China. A total of 201 soil samples were collected from farmland topsoil (0–20 cm) for the analysis of total nitrogen (TN), available phosphorus (AP), available potassium (AK), and available silicon (ASi). The coefficients of variation ranged from 47.88% to 76.91%. The NSRs of TN, AP, AK, and ASi were 0.15, 0. 07, 0.12, and 0.13, respectively. The NSRs varied from 0.02 to 0.20. All variables exhibited weak spatial dependence (R2 < 0.5), except for TN (R2 = 0.701). After comparing the prediction accuracy of the different methods, we used the inverse distance weighting method to analyze the spatial distribution of plant nutrients in soil. The uniform spatial distribution of AK, TN overall showed a trend of increasing from northeast to southwest, and the overall spatial distribution of AP and ASi showed that the northeast was higher than the southwest. This study provides support for the delimitation of basic farmland protection areas, the formulation of land use spatial planning, and the formulation of accurate farmland protection policies.

Sign in / Sign up

Export Citation Format

Share Document