Matches in SemOpenAlex for { <https://semopenalex.org/work/W2945015108> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2945015108 endingPage "51" @default.
- W2945015108 startingPage "46" @default.
- W2945015108 abstract "Abstract Soil organic matter has direct relationship with soil fertility and quality. However, its estimation in laboratory generates chemical residues which can contaminate the environment, and more ecological methods to determine the soil organic matter present high costs to the laboratories. This study aimed to evaluate the accuracy of artificial neural networks (ANNs) in estimating soil organic matter content from soil chemical attributes and to indicate whether network complexity affects estimation accuracy. A database was created containing 8556 samples, and 75% of the data were used for calibration and 25% for validation of the models. The variables used were: pH, potassium, phosphorus, calcium, magnesium and potential acidity. However, potassium and phosphorus were removed from the input variables. The ANNs were from the Multilayer Perceptron class, with two hidden layers, each of which had number of neurons ranging from 4 to 20. The 15 ANNs with lowest root mean square error (RMSE) were randomly presented by the program Statistica7®, and 6 of them were chosen for accuracy assessment. The fits were tested by analysis of variance (F test) and accuracy was assessed based on the coefficient of determination (R2), RMSE, mean error (ME), index of agreement (d) and confidence coefficient (c). The ANNs showed high accuracy to estimate soil organic matter in the phases of both calibration (R2 = 0.92; RMSE = 1.82 g kg−1) and validation (R2 = 0.76; RMSE = 1.98 g kg−1). Less complex networks can be trained and show the same accuracy as more complex networks." @default.
- W2945015108 created "2019-05-29" @default.
- W2945015108 creator A5006038532 @default.
- W2945015108 creator A5017769859 @default.
- W2945015108 creator A5019352881 @default.
- W2945015108 creator A5067028648 @default.
- W2945015108 creator A5070800010 @default.
- W2945015108 date "2019-09-01" @default.
- W2945015108 modified "2023-10-06" @default.
- W2945015108 title "Estimation of soil organic matter content by modeling with artificial neural networks" @default.
- W2945015108 cites W1964503221 @default.
- W2945015108 cites W1965328236 @default.
- W2945015108 cites W1974525970 @default.
- W2945015108 cites W1993269563 @default.
- W2945015108 cites W1998539195 @default.
- W2945015108 cites W2003543772 @default.
- W2945015108 cites W2015795971 @default.
- W2945015108 cites W2024141630 @default.
- W2945015108 cites W2027720295 @default.
- W2945015108 cites W2058191772 @default.
- W2945015108 cites W2061280784 @default.
- W2945015108 cites W2084366347 @default.
- W2945015108 cites W2089564362 @default.
- W2945015108 cites W2090602773 @default.
- W2945015108 cites W2090785325 @default.
- W2945015108 cites W2091160252 @default.
- W2945015108 cites W2098019489 @default.
- W2945015108 cites W2103160998 @default.
- W2945015108 cites W2111286455 @default.
- W2945015108 cites W2113831771 @default.
- W2945015108 cites W2115884890 @default.
- W2945015108 cites W2123438286 @default.
- W2945015108 cites W2740118356 @default.
- W2945015108 cites W2743608904 @default.
- W2945015108 cites W2765805814 @default.
- W2945015108 cites W2782527084 @default.
- W2945015108 cites W3014179099 @default.
- W2945015108 doi "https://doi.org/10.1016/j.geoderma.2019.04.044" @default.
- W2945015108 hasPublicationYear "2019" @default.
- W2945015108 type Work @default.
- W2945015108 sameAs 2945015108 @default.
- W2945015108 citedByCount "30" @default.
- W2945015108 countsByYear W29450151082020 @default.
- W2945015108 countsByYear W29450151082021 @default.
- W2945015108 countsByYear W29450151082022 @default.
- W2945015108 countsByYear W29450151082023 @default.
- W2945015108 crossrefType "journal-article" @default.
- W2945015108 hasAuthorship W2945015108A5006038532 @default.
- W2945015108 hasAuthorship W2945015108A5017769859 @default.
- W2945015108 hasAuthorship W2945015108A5019352881 @default.
- W2945015108 hasAuthorship W2945015108A5067028648 @default.
- W2945015108 hasAuthorship W2945015108A5070800010 @default.
- W2945015108 hasConcept C134306372 @default.
- W2945015108 hasConcept C154945302 @default.
- W2945015108 hasConcept C159390177 @default.
- W2945015108 hasConcept C159750122 @default.
- W2945015108 hasConcept C178790620 @default.
- W2945015108 hasConcept C182124840 @default.
- W2945015108 hasConcept C185592680 @default.
- W2945015108 hasConcept C2778152352 @default.
- W2945015108 hasConcept C33923547 @default.
- W2945015108 hasConcept C39432304 @default.
- W2945015108 hasConcept C41008148 @default.
- W2945015108 hasConcept C48743137 @default.
- W2945015108 hasConcept C50644808 @default.
- W2945015108 hasConceptScore W2945015108C134306372 @default.
- W2945015108 hasConceptScore W2945015108C154945302 @default.
- W2945015108 hasConceptScore W2945015108C159390177 @default.
- W2945015108 hasConceptScore W2945015108C159750122 @default.
- W2945015108 hasConceptScore W2945015108C178790620 @default.
- W2945015108 hasConceptScore W2945015108C182124840 @default.
- W2945015108 hasConceptScore W2945015108C185592680 @default.
- W2945015108 hasConceptScore W2945015108C2778152352 @default.
- W2945015108 hasConceptScore W2945015108C33923547 @default.
- W2945015108 hasConceptScore W2945015108C39432304 @default.
- W2945015108 hasConceptScore W2945015108C41008148 @default.
- W2945015108 hasConceptScore W2945015108C48743137 @default.
- W2945015108 hasConceptScore W2945015108C50644808 @default.
- W2945015108 hasFunder F4320321091 @default.
- W2945015108 hasFunder F4320322025 @default.
- W2945015108 hasLocation W29450151081 @default.
- W2945015108 hasOpenAccess W2945015108 @default.
- W2945015108 hasPrimaryLocation W29450151081 @default.
- W2945015108 hasRelatedWork W1977672479 @default.
- W2945015108 hasRelatedWork W1979460005 @default.
- W2945015108 hasRelatedWork W1998832776 @default.
- W2945015108 hasRelatedWork W2057934564 @default.
- W2945015108 hasRelatedWork W2126929798 @default.
- W2945015108 hasRelatedWork W2141359237 @default.
- W2945015108 hasRelatedWork W2154690796 @default.
- W2945015108 hasRelatedWork W2341916046 @default.
- W2945015108 hasRelatedWork W2378245543 @default.
- W2945015108 hasRelatedWork W2383517232 @default.
- W2945015108 hasVolume "350" @default.
- W2945015108 isParatext "false" @default.
- W2945015108 isRetracted "false" @default.
- W2945015108 magId "2945015108" @default.
- W2945015108 workType "article" @default.