Rainfall erosivity for the State of Rio de Janeiro estimated by artificial neural network

Erosividade das chuvas no Estado do Rio de Janeiro estimada por redes neurais artificiais

TECNICAL PAPERS

SOIL AND WATER ENGINEERING

Daniel F. de Carvalho^I; Joseph K. Khoury Júnior^II; Carlos A. A. Varella^III; Jacqueline Z. Giori^IV; Roriz L. Machado^V

^IEngº Agrícola, UFRRJ, Instituto de Tecnologia, Departamento de Engenharia, BR 465, km 7, Seropédica - RJ, [e-mail]. Bolsista do CNPq

^IIEngº Agrícola, UFV, Departamento de Engenharia de Produção e Mecânica, Viçosa - MG, [e-mail]

^IIIEngº Agrônomo, UFRRJ, Instituto de Tecnologia, Departamento de Engenharia, BR 465, km 7, Seropédica - RJ, [e-mail]

^IVEngª Agrícola, M.Sc. em Engenharia Civil, Fone: (0XX28) 9989-2647, [e-mail]

^VEngº Agrônomo, Professor, Instituto Federal de Educação, Ciência e Tecnologia Goiano, Câmpus Ceres, Rod. 154, km 3, Caixa Postal 51, Ceres - GO, [e-mail]

ABSTRACT

The Artificial Neural Networks (ANNs) are mathematical models method capable of estimating non-linear response plans. The advantage of these models is to present different responses of the statistical models. Thus, the objective of this study was to develop and to test ANNs for estimating rainfall erosivity index (EI₃₀) as a function of the geographical location for the state of Rio de Janeiro, Brazil and generating a thematic visualization map. The characteristics of latitude, longitude e altitude using ANNs were acceptable to estimating EI₃₀ and allowing visualization of the space variability of EI₃₀. Thus, ANN is a potential option for the estimate of climatic variables in substitution to the traditional methods of interpolation.

Keywords: geographic information system, interpolation methods, soil conservation.

RESUMO

As Redes Neurais Artificiais (RNAs) são métodos de modelagem matemática capazes de estimar planos de respostas não lineares, tendo a vantagem sobre métodos estatísticos que apresentam respostas lineares ou quadráticas. Este trabalho teve como objetivo desenvolver e testar RNAs para estimaro índice de erosividade das chuvas (EI₃₀) no Estado do Rio de Janeiro, em função da localização geográfica, e gerar um mapa temático para visualização. As características de latitude, longitude e altitude podem ser utilizadas para estimar o índice EI₃₀, permitindogerar um mapa da variabilidade espacial desseíndice.

Palavras-chave: sistema de informação geográfica, métodos de interpolação, conservação de solo.

INTRODUCTION

Despite its importance for agriculture, rain is the main element in soil erosion (NYSSEN et al., 2005). Its distribution is dependent on factors that are static (latitude, distance from the ocean, orographic effects) and dynamic (movement of air masses), which characterize the rainfall in a region when associated with each other (MONTEBELLER et al., 2007).

Soil degradation can be considered one of the most important environmental problems, being water erosion the degradation form that has most affected the yield potential of soils, assisted and accelerated by the man with his inappropriate agricultural management practices (SILVA et al. 2005). According to MACHADO et al. (2008), accelerated erosion is considered one of the most damaging forms of land degradation. In addition to reducing fertility and consequently crop productivity through loss of land, water and nutrients, this phenomenon can cause serious environmental problems, such as silting and contamination of water bodies, consequently raising the costs of water treatment (PRUSKI, 2009).

The Universal Soil Loss Equation (USLE) is an empirical model that estimates soil loss, and identify the factors that have the greatest effect on this phenomenon (WISCHMEIER & SMITH, 1958). Among the USLE factors, the one expressing the erosive capacity of rainfall is known as rain erosivity index (EI₃₀), which is the product of the total kinetic energy of maximum intensity of rain in 30 minutes. According to CARVALHO et al. (2010), erosivity is a numeric index that expresses the rain capability of causing erosion in an area. This factor is considered one of the most important components in the estimation of water erosion when using indirect methods, because it quantifies the effect of the impact of raindrops on the soil, therefore allowing the estimation of their erosivity.

MONTEBELLER et al. (2007) observed that the accurate estimation of erosivity indices in a region requires a reliable time series and uniform distribution of pluviometers. However, due to the limited availability of pluviometer records, the estimation of EI₃₀ index is difficult for some regions in Brazil. In order to overcome this limitation, some authors propose the use of empirical equations that relate the EI₃₀ with monthly and annual precipitation (CARVALHO et al., 2005). However, even with these equations, obtaining the EI₃₀ is restricted to locations where there is a satisfactory rainfall database.

Even in localities where rainfall records are available, SILVA (2004) and GONÇALVES et al. (2006) used interpolation techniques to estimate EI₃₀ values, based on the inverse power of distance (IPD) method. However, this method does not take into account the altitude of the area but instead the value of the rainfall erosivity from other locations, using an inversely proportional relation of the distance between this site and each of the neighboring stations. MONTEBELLER et al. (2007) evaluated the spatial variability of erosivity in the State of Rio de Janeiro, using geostatistical analysis.

An improvement to obtain EI₃₀ values can be attained when interpolation methods take into account the altitude (GONÇALVES, 2002), which is possible by using Artificial Neural Networks (ANN). According to SARIGUL et al. (2003), among the models that utilize artificial intelligence techniques, artificial neural networks (ANNs) are the most widely used. In comparison with statistical models, which determine linear or quadratic plans, the main advantage of an ANN is its ability to model nonlinear response plans. ZANETTI et al. (2008) state that ANNs are distributed parallel systems, composed of simple processing units, which calculate certain mathematical functions. They have been successfully used to model complex relationships involving time series in various areas of knowledge. MOREIRA et al. (2006) and MOREIRA et al. (2009) used ANNs to estimate the erosivity in the states of Sao Paulo and Minas Gerais, respectively. Using estimated values of EI₃₀ from 138 and 268 rainfall stations, respectively, the authors concluded that the developed ANNs showed satisfactory results and can be used for use planning, management and soil conservation in both states.

Based on the above, this study aimed to develop and test ANNs to estimate the values of rainfall erosivity index (EI₃₀) from geographical features (longitude, latitude and altitude) in any area of the State of Rio de Janeiro and prepare a map of erosivity variability for the state of Rio de Janeiro.

MATERIAL AND METHODS

The EI₃₀ values used for the development and testing of ANN were obtained from studies by GONÇALVES (2002) and MONTEBELLER (2005) for 36 locations in the State of Rio de Janeiro. The geographical site (latitude and longitude), the altitude and the EI₃₀ values were standardized by mean and standard deviation in order to reduce the difference in scale of the variables in the training phase of the ANN. Figure 1 and Table 1 show, respectively, the geographic location and precipitation station data used in this study. The pluviometer data series had different number of records, depending on the institution responsible for managing the data (7; 17; 7 and 15 years, on average, respectively, for INMET, SERLA, ANA and Light).

The training and testing of ANN were performed using the platform of the computer program Matlab^® 6.5 with the Neural Network package tool, which uses an iterative method to minimize the error between the ANN output and the observed value, known as the back-propagation error algorithm. This procedure minimizes the mean square error (MSE) between the ANN output and the expected output of the network free parameters (w's and b's). The minimization was performed by Quasi-Newton iterative method using the Levenberg-Marquardt algorithm (ZANETTI et al., 2008).

The ANN architecture was type 3-n₁-n₂-1, being values corresponding to an input vector with three variables, two intermediate layers with n₁ and n₂ neurons, and one neuron in the output layer. The input vector was composed by values of latitude, longitude and altitude of each rainfall station. For the neuron in the output layer, it was used a linear activation function to generate the value of the rainfall erosivity (MJ mm h^-1 ha^-1 yr^-1), of the location represented by the input vector.

ANN training and testing was performed by the "leaving one out" method, which consists of defining a fixed number of iterations to minimize the error. The ANN test was assessed with the observation that falls outside the training, in order not to bias the error. This method is a variant of cross-validation that is used when the sample has small number of observations (SENA JÚNIOR et al., 2008). For each training, just an observation was left out for testing, obtaining thus a greater number of observations in the training sample.

Several ANNs were trained by varying the number of times, number of neurons in the intermediate layers, and activation functions. The numbers of iterations or periods used in the training were 25; 50; 75; 100 and 150. Because in the beginning of training, free parameters were randomly generated and these initial values can influence the outcome of the training, each architecture was trained ten times, and selected the one with lowest classification MSE in the observation test.

In assessing the results obtained with the developed ANN, validity indices were used as proposed by CAMARGO & SENTELHAS (1997), and the absolute value of the mean relative error (MRE) (Equation 1). The indices of validity are: precision (r), indicating the degree of data dispersion (Equation 2), accuracy (d), relating to the removal of the points listed on the regression graph in relation to the line of equal values 1:1 (Equation 3), and confidence (c), represented by the product of the precision index by the accuracy index.

where,

n - 36 weather stations;

A_i - EI₃₀ estimated by ANN for the i-th station, MJ mm h^-1 ha^-1 yr^-1, and

T_i - EI₃₀ of the i-th experimental station, MJ mm h^-1 ha^-1 yr^-1.

where,

- average EI₃₀ estimated by ANN from the 36 stations, and

- experimental average EI₃₀ from the 36 stations.

where,

- absolute deviation between the estimated ANN value for the i-th station and the average experimental values, and

- absolute deviation between the experimental value of the i-th station and the average experimental values.

A graph of correspondence with the MRE and validity indices was used to compare between the EI₃₀ values, obtained by ANN simulation and calculated from pluviometers by GONÇALVES (2002) and MONTEBELLER (2005), for 36 stations in the test phase of ANN. Another correspondence chart was generated with values of EI₃₀ factor , being 62 of these estimated by MONTEBELLER (2005) with equations that correlate EI₃₀ monthly with rainfall and 36 from the factor experimentally obtained by the same authors, totaling 98 values. These values were also obtained by ANN according to their geographic locations (latitude, longitude and altitude) and compared with these 98 values.

To view the results obtained by ANN, a thematic map of erosivity indices of the state of Rio de Janeiro estimated by ANN that presented the best performance was built. The resulting map was reclassified in the interval between EI₃₀ classes of 2,000 MJ mm ha^-1 h^-1 yr^-1, in a total of seven classes, as used by MONTEBELLER (2005).

The preparation of the EI₃₀ variability map was performed using the ArcGis program, and the kriging interpolation method was used, as recommended by CEDDIA et al. (2009). A set of 452 points of geographic coordinates (latitude, longitude and altitude) within the limits of the State of Rio de Janeiro was obtained from picture provided by Google Earth Release 4.2. These coordinates were used to estimate the EI₃₀ by the best ANN developed previously and to obtain a variability map of the EI₃₀ classes of 2000 MJ mm ha^-1 h^-1 yr^-1, according to MONTEBELLER (2005).

RESULTS AND DISCUSSION

Table 2 shows the number of times, number of neurons of the intermediate layers (Layer 1 and Layer 2), the mean relative error (MRE) of the sample from the best ANN and the validity indices used in the work.

The ANN that showed the best result was that trained with 75 iterations (periods) and presented in its architecture intermediate layers with n₁ = 4 and n₂ = 3 neurons. Under these conditions, the confidence index (c) was equal to 0.6, considered "poor" according to CAMARGO & SENTELHAS (1997), and the MRE was 35.4%. The activation functions used in the neurons were sigmoid hyperbolic tangent type (tansig), in the input and intermediate layers, and of linear type (purelin) in the output layer.

The ANN developed to determine the EI₃₀values †has the following parameters:

where,

f₁ = f₂= tansig (n) = 2/(1+exp(-2n))-1;

f₃= purelin (n) = n;

n = value of the entry in the function;

W = adjusted w's matrix parameters of the ANN;

where,

p - input vector of ANN;

Lat - latitude, decimal º;

Long - longitude, decimal º, and

Alt - altitude, m.

Adjusted bias (b's) matrix parameters for ANN

The vector of input and output variables were standardized by the equation:

where,

- standardized variable;

- real variable;

- x average, and

^- x standard deviation.

The values of mean and standard deviations were used for standardization, respectively:

With this defined ANN architecture and parameters, it is possible to estimate the EI₃₀ in the State of Rio de Janeiro, from its implementation in any computing platform that operates with matrices, as well as to generate more data from the EI₃₀ to use in visualization software in attribute maps of values classes.

Figure 2 shows the correspondence graph of the EI₃₀ estimated values of the ANN (eq.(4)) with ones observed from pluviometer data. Combining the results found with the one stipulated by MONTEBELLER (2005), which showed a map with EI₃₀ classes ranging in 2000 MJ mm ha^-1 h^-1 yr^-1, it is noticeable the viability of using ANN to estimate rain erosivity in the State of Rio de Janeiro, because the error introduced would not be detrimental for the purposes of calculating the erosivity. Taking as an example a value of 8000 MJ mm ha^-1 h^-1 yr^-1: when using ANN to estimate the EI₃₀ value of that location and considering an MRE of 35.40%, the range of possible values is between 5,168 and 10,832 MJ mm ha^-1 h^-1 yr^-1(8,000 ± 0.354 x 8,000). Thus, ANN was estimated by including the value in the correct range or, at most, one level above (9,000 to 11,000) or one level below (5000-7000) to the one considered correct (7000-9000). However, the addition of variables that influence the erosivity, and geographic coordinates, should be tested in order to improve the accuracy of the estimated EI₃₀ index.

Figure 3 shows the correspondence graph generated between 98 EI₃₀ values estimated and observed by MONTEBELLER (2005) and GONÇALVES (2002), and the corresponding values simulated by the ANN developed for this other dataset. It is noticeable that the confidence index (c) increased to 0.7, which is considered "good" by the classification proposed by CAMARGO & SENTELHAS (1997). It is also observed that the small number of observations of the EI₃₀ value (obtained in 36 precipitation stations) used in the past training and testing of ANNs may have been the reason for the "poor" results shown in the analysis. Despite the best result in the training of ANN with 98 EI₃₀ values, one should take into account that part of these EI₃₀ values were estimated, reducing the validation reliability compared to ANN evaluated with 36 observations. Thus, the ANN estimation of EI₃₀ index by using a larger sample number for ANN training resulted in acceptable values to compare with calculated and observed values by MONTEBELLER (2005) and GONÇALVES (2002).

The adjusted model of the kriging semivariogram was exponential. Figure 4 shows the thematic map with the EI₃₀, erosivity index for the State of Rio de Janeiro estimated by ANNs. The map showed the same variation tendency of that found by MONTEBELLER et al. (2007). However, the use of ANN allowed generating more points, making it possible to achieve better visualization of the EI₃₀ spatial variability, thus generating a greater number of erosivity classes in the same region. This result attends the recommendation of MONTEBELLER et al. (2007), so that a greater number of erosivity values were obtained, mainly in the north (micro-regions of Campos dos Goytacazes and Macaé) and the coastal lowlands (micro-regions of Bacia de São João and Lagos).

CONCLUSIONS

The geographic characteristics of locations (latitude, longitude and altitude) can be used to estimate EI₃₀ using ANNs for the State of Rio de Janeiro;

The use of ANN allowed generating a greater number of EI₃₀ points, thus enabling the production of thematic map with better visualization of the spatial variability of this attribute.

ACKNOWLEDGMENTS

To the "Programa Interno de Bolsa de Iniciação Científica"- PROIC/DPPG/UFRRJ, for the financial support provided that allowed the development of this work.

Recebido pelo Conselho Editorial em: 9-8-2010

Aprovado pelo Conselho Editorial em: 6-10-2011

• CAMARGO, A.P.; SENTELHAS, P.C. Avaliação do desempenho de diferentes métodos de estimativa da evapotranspiração potencial no Estado de São Paulo. Revista Brasileira de Agrometeorologia, Sete Lagoas, v.5, n.1, p.89-97, 1997.
• CARVALHO, D.F.; MACHADO, R.L.; EVANGELISTA, A.W.P.; KHOURY JUNIOR, J.K.; SILVA, L.D.B. Distribuição, probabilidade de ocorrência e período de retorno dos índices de erosividade EI₃₀ e KE>25 em Seropédica - RJ. Engenharia Agrícola, Jaboticabal, v.30, n.2, p.244-252, 2010.
• CARVALHO, D.F.; MONTEBELLER, C.A.; FRANCO, E.M.; VALCARCEL, R.; BERTOL, I. Padrões de precipitação e índices de erosividade para as chuvas de Seropédica e Nova Friburgo, RJ. Revista Brasileira de Engenharia Agrícola e Ambiental, Campina Grande, v.9, n.1, p.7-14, 2005.
• CEDDIA, M.B.; VIEIRA, S.R.; VILLELA, A.L.O.; MOTA, L.S.; ANJOS, L.H.C.; CARVALHO, D.F. Topgraphyandspatialvariabilityofsoilphysicalproperties. Scientia Agricola, Piracicaba, v.66, n.3, p.338-352, 2009.
• GONÇALVES, F.A. Erosividade das chuvas no Estado do Rio de Janeiro 2002. 120 f. Dissertação (Mestrado em Engenharia Agrícola) - Universidade Federal de Viçosa, Viçosa, 2002.
• GONÇALVES, F.A.; SILVA, D.D.; PRUSKI, F.F.; CARVALHO, D.F.; CRUZ, E.S. Índices e espacialização da erosividade das chuvas para o Estado do Rio de Janeiro. Revista Brasileira de Engenharia Agrícola e Ambiental, Campina Grande, v.10, n.2, p.269-276, 2006.
• MACHADO, R.L.; CARVALHO, D.F.; COSTA, J.R.; OLIVEIRA NETO, D.H.; PINTO, M.F. Análise da erosividade das chuvas associada aos padrões de precipitação pluvial na região de ribeirão das Lajes (RJ). Revista Brasileira de Ciência do Solo, Viçosa-MG, v.32, p.2113-2123, 2008.
• MONTEBELLER, C.A. Variabilidade espacial do potencial erosivo das chuvas no Estado do Rio de Janeiro 2005. 123 f. Dissertação (Mestrado em Ciência do Solo) - Universidade Federal Rural do Rio de Janeiro, Seropédica, 2005.
• MONTEBELLER, C. A.; CEDDIA, M.B.; CARVALHO, D.F; VIEIRA, S.R; FRANCO, E.M. Variabilidade espacial do potencial erosivo das chuvas no Estado do Rio de Janeiro. Engenharia Agrícola, Jaboticabal, v.27, n.2, p.426-435, 2007.
• MOREIRA, M.C.; CECÍLIO, R.A.; PINTO, F.A.C.; PRUSKI, F.F. Desenvolvimento e análise de uma rede neuralartificial para estimativa da erosividade da chuva para o Estado de São Paulo. Revista Brasileira de Ciência do Solo, Viçosa-MG, v.30, n.6, 1069-1074, 2006.
• MOREIRA, M.C.; PRUSKI, F.F.; OLIVEIRA, T. E.; PINTO, F.A.C.; SILVA, D. D. Redes neurais artificiais para estimativa mensal da erosividade da chuva no Estado de Minas Gerais. Revista Engenharia na Agricultura, Viçosa-MG, v.17, n.1, p.75-83, 2009.
• NYSSEN, J.; VANDENREYKEN, H.; POESEN, J.; MOEYERSONS, J.; DECKERS J.; MITIKU H.; SALLES, C.; GOVERS, G. Rainfall erosivity and variability in the Northern Ethiopian Highlands. Journal of Hydrology, Amsterdam, v.311, p.172-187, 2005.
• PRUSKI, F.F. Prejuízos decorrentes da erosão hídrica e tolerância de perda de solos. In: PRUSKI, F.F. Conservação do solo e água - práticas mecânicas para o controle da erosão hídrica 2.ed. Viçosa: Editora UFV, 2009. p.13-23.
• SARIGUL, E.; ABBOTT, A. L.; SCHMOLDT, D.L. Rule-driven defect detection in CT images of hardwood logs. Computers and Electronics in Agriculture, New York, v.41, n.19, p.101-119, 2003.
• SENA JUNIOR, D.G.; PINTO, F.A.C.; QUEIROZ, D.M.; SANTOS, N.T.; KHOURY JUNIOR, J.K. Discriminação entre estágios nutricionais na cultura do trigo com técnicas de visão  artificial e medidor portátil de clorofila. Engenharia Agrícola, Jaboticabal, v.28, n.1, p.187-195, 2008.
• SILVA, A.M.; Rainfall erosivity map for Brazil. Catena, v.57, n.3, p.251-259, 2004.
• SILVA, C.G.; ALVES SOBRINHO, T.; VITORINO, A.C.T.; CARVALHO, D.F. Atributos físicos, químicos e erosão hídrica em entressulcos sob chuva simulada, em sistema de plantio direto e convencional. Engenharia Agrícola, Jaboticabal, v.25, n.1, p.144-153, 2005.
• WISCHMEIER, W.H.; SMITH, D.D. Rainfall energy and its relationship to soil loss. Transactions of the American Geophysical Union, Washington, v.39, p.285-291, 1958.
• ZANETTI, S.S.; SOUZA, E.F.; CARVALHO, D.F. BERNARDO, S. Estimação da evapotranspiração de referência no Estado do Rio de Janeiro usando redes neurais artificiais. Revista Brasileira de Engenharia Agrícola e Ambiental, Campina Grande, v.12, n.2, p.166-172, 2008.

Rainfall erosivity for the State of Rio de Janeiro estimated by artificial neural network

Erosividade das chuvas no Estado do Rio de Janeiro estimada por redes neurais artificiais

Publication Dates

• Publication in this collection
  17 Apr 2012
• Date of issue
  Feb 2012

History

• Received
  09 Aug 2010
• Accepted
  06 Oct 2011