Estimation of local rainfall erosivity using artificial neural network
The information retrieval of local values of rainfall erosivity is essential for soil loss estimation with the Universal Soil Loss Equation (USLE), and thus is very useful in soil and water conservation planning. In this manner, the objective of this study was to develop an Artificial Neural Network...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Instituto de Pesquisas Ambientais em Bacias Hidrográficas (IPABHi)
2011-08-01
|
| Series: | Revista Ambiente & Água |
| Subjects: | |
| Online Access: | http://www.ambi-agua.net/seer/index.php/ambi-agua/article/view/656 |
| _version_ | 1819126129808637952 |
|---|---|
| author | Paulo Tarso Sanches Oliveira Caroline Alvarenga Pertussatti Lais Cristina Soares Rebucci Teodorico Alves Sobrinho |
| author_facet | Paulo Tarso Sanches Oliveira Caroline Alvarenga Pertussatti Lais Cristina Soares Rebucci Teodorico Alves Sobrinho |
| author_sort | Paulo Tarso Sanches Oliveira |
| collection | DOAJ |
| description | The information retrieval of local values of rainfall erosivity is essential for soil loss estimation with the Universal Soil Loss Equation (USLE), and thus is very useful in soil and water conservation planning. In this manner, the objective of this study was to develop an Artificial Neural Network (ANN) with the capacity of estimating, with satisfactory accuracy, the rainfall erosivity in any location of the Mato Grosso do Sul state. We used data from rain erosivity, latitude, longitude, altitude of pluviometric and pluviographic stations located in the state to train and test an ANN. After training with various network configurations, we selected the best performance and higher coefficient of determination calculated on the basis of data erosivity of the sample test and the values estimated by ANN. In evaluating the results, the confidence and the agreement indices were used in addition to the coefficient of determination. It was found that it is possible to estimate the rainfall erosivity for any location in the state of Mato Grosso do Sul, in a reliable way, using only data of geographical coordinates and altitude. |
| first_indexed | 2024-12-22T07:51:08Z |
| format | Article |
| id | doaj.art-433a24c2ba05420e884485f5c739154c |
| institution | Directory Open Access Journal |
| issn | 1980-993X |
| language | English |
| last_indexed | 2024-12-22T07:51:08Z |
| publishDate | 2011-08-01 |
| publisher | Instituto de Pesquisas Ambientais em Bacias Hidrográficas (IPABHi) |
| record_format | Article |
| series | Revista Ambiente & Água |
| spelling | doaj.art-433a24c2ba05420e884485f5c739154c2022-12-21T18:33:29ZengInstituto de Pesquisas Ambientais em Bacias Hidrográficas (IPABHi)Revista Ambiente & Água1980-993X2011-08-016224625410.4136/ambi-agua.656Estimation of local rainfall erosivity using artificial neural networkPaulo Tarso Sanches OliveiraCaroline Alvarenga PertussattiLais Cristina Soares RebucciTeodorico Alves SobrinhoThe information retrieval of local values of rainfall erosivity is essential for soil loss estimation with the Universal Soil Loss Equation (USLE), and thus is very useful in soil and water conservation planning. In this manner, the objective of this study was to develop an Artificial Neural Network (ANN) with the capacity of estimating, with satisfactory accuracy, the rainfall erosivity in any location of the Mato Grosso do Sul state. We used data from rain erosivity, latitude, longitude, altitude of pluviometric and pluviographic stations located in the state to train and test an ANN. After training with various network configurations, we selected the best performance and higher coefficient of determination calculated on the basis of data erosivity of the sample test and the values estimated by ANN. In evaluating the results, the confidence and the agreement indices were used in addition to the coefficient of determination. It was found that it is possible to estimate the rainfall erosivity for any location in the state of Mato Grosso do Sul, in a reliable way, using only data of geographical coordinates and altitude.http://www.ambi-agua.net/seer/index.php/ambi-agua/article/view/656artificial intelligencesoil conservationwater erosion |
| spellingShingle | Paulo Tarso Sanches Oliveira Caroline Alvarenga Pertussatti Lais Cristina Soares Rebucci Teodorico Alves Sobrinho Estimation of local rainfall erosivity using artificial neural network Revista Ambiente & Água artificial intelligence soil conservation water erosion |
| title | Estimation of local rainfall erosivity using artificial neural network |
| title_full | Estimation of local rainfall erosivity using artificial neural network |
| title_fullStr | Estimation of local rainfall erosivity using artificial neural network |
| title_full_unstemmed | Estimation of local rainfall erosivity using artificial neural network |
| title_short | Estimation of local rainfall erosivity using artificial neural network |
| title_sort | estimation of local rainfall erosivity using artificial neural network |
| topic | artificial intelligence soil conservation water erosion |
| url | http://www.ambi-agua.net/seer/index.php/ambi-agua/article/view/656 |
| work_keys_str_mv | AT paulotarsosanchesoliveira estimationoflocalrainfallerosivityusingartificialneuralnetwork AT carolinealvarengapertussatti estimationoflocalrainfallerosivityusingartificialneuralnetwork AT laiscristinasoaresrebucci estimationoflocalrainfallerosivityusingartificialneuralnetwork AT teodoricoalvessobrinho estimationoflocalrainfallerosivityusingartificialneuralnetwork |