FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4292304405> ?p ?o ?g. }

• W4292304405 abstract "Nutrient dynamics play an essential role in aquatic ecosystems. Despite advances in sensor technology, nutrient concentrations are difficult and expensive to monitor in-situ and in real-time. Emerging data-driven methods may provide surrogate measures for nutrient concentrations. In this work, we use 4-years of water quality data with high-frequency (15-min) intervals acquired at 2 automatic stations in the German Danube River to train data-driven algorithms and build surrogate measures for nitrate ( <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML id=M1><mml:msubsup><mml:mrow><mml:mtext>NO</mml:mtext></mml:mrow><mml:mrow><mml:mn>3</mml:mn></mml:mrow><mml:mrow><mml:mo>-</mml:mo></mml:mrow></mml:msubsup></mml:math> -N), ammonium ( <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML id=M2><mml:msubsup><mml:mrow><mml:mtext>NH</mml:mtext></mml:mrow><mml:mrow><mml:mn>4</mml:mn></mml:mrow><mml:mrow><mml:mo>+</mml:mo></mml:mrow></mml:msubsup></mml:math> -N), and orthophosphate ( <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML id=M3><mml:msubsup><mml:mrow><mml:mtext>PO</mml:mtext></mml:mrow><mml:mrow><mml:mn>4</mml:mn></mml:mrow><mml:mrow><mml:mn>3</mml:mn><mml:mo>-</mml:mo></mml:mrow></mml:msubsup></mml:math> -P). Pre-processing of the data included removing outliers and filling missing values by linear interpolation. Multiple Linear Regression (MLR) and Random Forest (RF) are trained, cross-validated, and tested using dissolved oxygen (DO), temperature (Temp), conductivity (EC), pH, discharge rate (Q), and chlorophyll-a (Chl-a) as input futures. Additionally, we used time-series data to develop cyclical features to test improvements in the underlying relationship between data. This work presents a thorough description of the modeling workflow, including intermediate steps for feature engineering, feature selection, and hyperparameter optimization. In total, 12 surrogate models (2 algorithms * 3 constituents * 2 stations) are compared with R 2 and RMSE as error metrics. The results show that RF outperforms MLR when adding at least three predictors for all the surrogate models. The MLR models give R 2 -values for <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML id=M4><mml:msubsup><mml:mrow><mml:mtext>NO</mml:mtext></mml:mrow><mml:mrow><mml:mn>3</mml:mn></mml:mrow><mml:mrow><mml:mo>-</mml:mo></mml:mrow></mml:msubsup></mml:math> -N 0.67 and 0.89, <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML id=M5><mml:msubsup><mml:mrow><mml:mtext>NH</mml:mtext></mml:mrow><mml:mrow><mml:mn>4</mml:mn></mml:mrow><mml:mrow><mml:mo>+</mml:mo></mml:mrow></mml:msubsup></mml:math> -N 0.39 and 0.40, <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML id=M6><mml:msubsup><mml:mrow><mml:mtext>PO</mml:mtext></mml:mrow><mml:mrow><mml:mn>4</mml:mn></mml:mrow><mml:mrow><mml:mn>3</mml:mn><mml:mo>-</mml:mo></mml:mrow></mml:msubsup></mml:math> -P 0.34 and 0.54 of Pfelling station and Jochenstein station, respectively. RF models produce accurate predictions and low error performances for all the targets <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML id=M7><mml:msubsup><mml:mrow><mml:mtext>NO</mml:mtext></mml:mrow><mml:mrow><mml:mn>3</mml:mn></mml:mrow><mml:mrow><mml:mo>-</mml:mo></mml:mrow></mml:msubsup></mml:math> -N ( R 2 = 0.99 and 0.99), <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML id=M8><mml:msubsup><mml:mrow><mml:mtext>NH</mml:mtext></mml:mrow><mml:mrow><mml:mn>4</mml:mn></mml:mrow><mml:mrow><mml:mo>+</mml:mo></mml:mrow></mml:msubsup></mml:math> -N ( R 2 = 0.98 and 0.99), <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML id=M9><mml:msubsup><mml:mrow><mml:mtext>PO</mml:mtext></mml:mrow><mml:mrow><mml:mn>4</mml:mn></mml:mrow><mml:mrow><mml:mn>3</mml:mn><mml:mo>-</mml:mo></mml:mrow></mml:msubsup></mml:math> -P ( R 2 = 0.96 and 0.96). The percentage improvement of RMSE for RF compared to MLR in prediction nutrients ranges from 73 to 92%. This work demonstrates the usefulness of surrogate models using the RF algorithm when reproducing nutrient dynamics and serving as soft sensors for monitoring nutrient concentrations." @default.
• W4292304405 created "2022-08-19" @default.
• W4292304405 creator A5000079785 @default.
• W4292304405 creator A5010314299 @default.
• W4292304405 creator A5026307348 @default.
• W4292304405 date "2022-08-17" @default.
• W4292304405 modified "2023-09-26" @default.
• W4292304405 title "Predicting high-frequency nutrient dynamics in the Danube River with surrogate models using sensors and Random Forest" @default.
• W4292304405 cites W1145321339 @default.
• W4292304405 cites W133989785 @default.
• W4292304405 cites W1552441047 @default.
• W4292304405 cites W1568560596 @default.
• W4292304405 cites W160873593 @default.
• W4292304405 cites W1972401342 @default.
• W4292304405 cites W2009927598 @default.
• W4292304405 cites W2024731811 @default.
• W4292304405 cites W2034993173 @default.
• W4292304405 cites W2047951970 @default.
• W4292304405 cites W2048697945 @default.
• W4292304405 cites W2092829070 @default.
• W4292304405 cites W2107407839 @default.
• W4292304405 cites W2128372317 @default.
• W4292304405 cites W2157606424 @default.
• W4292304405 cites W2165717273 @default.
• W4292304405 cites W2256368425 @default.
• W4292304405 cites W2261059368 @default.
• W4292304405 cites W2516255137 @default.
• W4292304405 cites W2544886233 @default.
• W4292304405 cites W2588810797 @default.
• W4292304405 cites W2730478502 @default.
• W4292304405 cites W2771100845 @default.
• W4292304405 cites W2791592925 @default.
• W4292304405 cites W2806157403 @default.
• W4292304405 cites W2883210850 @default.
• W4292304405 cites W2890188851 @default.
• W4292304405 cites W2906484232 @default.
• W4292304405 cites W2911964244 @default.
• W4292304405 cites W2912393427 @default.
• W4292304405 cites W2931987089 @default.
• W4292304405 cites W2943160824 @default.
• W4292304405 cites W2947463384 @default.
• W4292304405 cites W2956141415 @default.
• W4292304405 cites W2960207024 @default.
• W4292304405 cites W2998282061 @default.
• W4292304405 cites W2999667975 @default.
• W4292304405 cites W3032685738 @default.
• W4292304405 cites W3093733298 @default.
• W4292304405 cites W3107589590 @default.
• W4292304405 cites W3118961085 @default.
• W4292304405 cites W3149084432 @default.
• W4292304405 cites W3202079102 @default.
• W4292304405 cites W4205416889 @default.
• W4292304405 doi "https://doi.org/10.3389/frwa.2022.894548" @default.
• W4292304405 hasPublicationYear "2022" @default.
• W4292304405 type Work @default.
• W4292304405 citedByCount "1" @default.
• W4292304405 countsByYear W42923044052023 @default.
• W4292304405 crossrefType "journal-article" @default.
• W4292304405 hasAuthorship W4292304405A5000079785 @default.
• W4292304405 hasAuthorship W4292304405A5010314299 @default.
• W4292304405 hasAuthorship W4292304405A5026307348 @default.
• W4292304405 hasBestOaLocation W42923044051 @default.
• W4292304405 hasConcept C11413529 @default.
• W4292304405 hasConcept C119857082 @default.
• W4292304405 hasConcept C154945302 @default.
• W4292304405 hasConcept C41008148 @default.
• W4292304405 hasConcept C77088390 @default.
• W4292304405 hasConceptScore W4292304405C11413529 @default.
• W4292304405 hasConceptScore W4292304405C119857082 @default.
• W4292304405 hasConceptScore W4292304405C154945302 @default.
• W4292304405 hasConceptScore W4292304405C41008148 @default.
• W4292304405 hasConceptScore W4292304405C77088390 @default.
• W4292304405 hasLocation W42923044051 @default.
• W4292304405 hasOpenAccess W4292304405 @default.
• W4292304405 hasPrimaryLocation W42923044051 @default.
• W4292304405 hasRelatedWork W2961085424 @default.
• W4292304405 hasRelatedWork W3046775127 @default.
• W4292304405 hasRelatedWork W3170094116 @default.
• W4292304405 hasRelatedWork W4205958290 @default.
• W4292304405 hasRelatedWork W4285260836 @default.
• W4292304405 hasRelatedWork W4286629047 @default.
• W4292304405 hasRelatedWork W4306321456 @default.
• W4292304405 hasRelatedWork W4306674287 @default.
• W4292304405 hasRelatedWork W4386462264 @default.
• W4292304405 hasRelatedWork W4224009465 @default.
• W4292304405 hasVolume "4" @default.
• W4292304405 isParatext "false" @default.
• W4292304405 isRetracted "false" @default.
• W4292304405 workType "article" @default.