FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381936603> ?p ?o ?g. }

• W4381936603 endingPage "107980" @default.
• W4381936603 startingPage "107980" @default.
• W4381936603 abstract "By generating high quality data without the big time investment and economic cost of real experiments, dynamic greenhouse climate and crop simulation models can support decisions on greenhouse climate control, crop management and greenhouse design. The reliability of simulation-based decisions depends on both the prediction accuracy and interpretability of simulation models. The prediction accuracy of these simulation models can be increased by: 1) improving mechanisms in process-based models; 2) calibrating process-based model parameters; 3) deriving black-box relationships from data. Considering the descending interpretability from (1) to (3), this study presents a knowledge-based data-driven modelling approach where firstly a process-based model is selected and modified based on domain knowledge, then data-driven improvement is applied including two steps: parameter value estimation by particle filter (PF) and further black-box improvement by deep neural networks (DNN). The approach was tested with an example of greenhouse climate-tomato production system modelling. Modules from GreenLight (Katzin et al., 2020) and TOMSIM (Heuvelink, 1995, Heuvelink, 1996) were selected, modified and integrated into a process-based greenhouse climate-tomato model. Validation showed that PF-calibration of five greenhouse parameters decreased the seasonal relative root mean squared error (RRMSE) of indoor air vapor pressure predictions from 40.7% of that before PF-calibration to 16.4%, while it did not decrease the RRMSE of indoor air temperature predictions. Combining the PF-calibrated model with a DNN trained on a season of data decreased the RRMSE of indoor air temperature from 15.0% without DNN to 6.7%, and decreased the RRMSE of indoor air vapor pressure to 12.6%. The knowledge-based data-driven greenhouse climate-tomato model had a relative error of 0.9% for seasonal total fresh yield, and an RRMSE of 6.6% for the cumulative yield throughout the season. If process-based model parameters were not calibrated before combining the model with DNNs, the required amount and diversity of DNN training data increased because more information needed to be learnt from data by the DNNs. Without PF-calibration, combining a DNN trained on 50 days of data with the process-based model resulted in RRMSEs of 44.8% and 31.8% for indoor air temperature and vapor pressure prediction, respectively; with PF-calibration, the RRMSEs were decreased to 13.1% and 17.9%. The proposed three-step knowledge-based data-driven approach can not only improve the model prediction accuracy, but can also help to track and interpret the improvements." @default.
• W4381936603 created "2023-06-25" @default.
• W4381936603 creator A5008049313 @default.
• W4381936603 creator A5052723218 @default.
• W4381936603 creator A5057628623 @default.
• W4381936603 creator A5087339331 @default.
• W4381936603 creator A5088195353 @default.
• W4381936603 creator A5088747633 @default.
• W4381936603 date "2023-08-01" @default.
• W4381936603 modified "2023-10-05" @default.
• W4381936603 title "Boosting the prediction accuracy of a process-based greenhouse climate-tomato production model by particle filtering and deep learning" @default.
• W4381936603 cites W1978865129 @default.
• W4381936603 cites W2089790440 @default.
• W4381936603 cites W2104941390 @default.
• W4381936603 cites W2115481594 @default.
• W4381936603 cites W2139422799 @default.
• W4381936603 cites W2145824163 @default.
• W4381936603 cites W2160337655 @default.
• W4381936603 cites W2168361762 @default.
• W4381936603 cites W2603681271 @default.
• W4381936603 cites W2746142811 @default.
• W4381936603 cites W2751565523 @default.
• W4381936603 cites W2765148725 @default.
• W4381936603 cites W2790979755 @default.
• W4381936603 cites W2945740093 @default.
• W4381936603 cites W2962198579 @default.
• W4381936603 cites W2972623009 @default.
• W4381936603 cites W3000707827 @default.
• W4381936603 cites W3000824375 @default.
• W4381936603 cites W3004442222 @default.
• W4381936603 cites W3014650717 @default.
• W4381936603 cites W3015615438 @default.
• W4381936603 cites W3015908511 @default.
• W4381936603 cites W3079760979 @default.
• W4381936603 cites W3115164315 @default.
• W4381936603 cites W3120253624 @default.
• W4381936603 cites W3125795633 @default.
• W4381936603 cites W3146152835 @default.
• W4381936603 cites W4214616180 @default.
• W4381936603 cites W4248332622 @default.
• W4381936603 cites W4311079602 @default.
• W4381936603 cites W807816048 @default.
• W4381936603 doi "https://doi.org/10.1016/j.compag.2023.107980" @default.
• W4381936603 hasPublicationYear "2023" @default.
• W4381936603 type Work @default.
• W4381936603 citedByCount "0" @default.
• W4381936603 crossrefType "journal-article" @default.
• W4381936603 hasAuthorship W4381936603A5008049313 @default.
• W4381936603 hasAuthorship W4381936603A5052723218 @default.
• W4381936603 hasAuthorship W4381936603A5057628623 @default.
• W4381936603 hasAuthorship W4381936603A5087339331 @default.
• W4381936603 hasAuthorship W4381936603A5088195353 @default.
• W4381936603 hasAuthorship W4381936603A5088747633 @default.
• W4381936603 hasBestOaLocation W43819366031 @default.
• W4381936603 hasConcept C105795698 @default.
• W4381936603 hasConcept C119857082 @default.
• W4381936603 hasConcept C139945424 @default.
• W4381936603 hasConcept C144027150 @default.
• W4381936603 hasConcept C165838908 @default.
• W4381936603 hasConcept C2781067378 @default.
• W4381936603 hasConcept C32198211 @default.
• W4381936603 hasConcept C33923547 @default.
• W4381936603 hasConcept C39432304 @default.
• W4381936603 hasConcept C41008148 @default.
• W4381936603 hasConcept C50644808 @default.
• W4381936603 hasConcept C86803240 @default.
• W4381936603 hasConceptScore W4381936603C105795698 @default.
• W4381936603 hasConceptScore W4381936603C119857082 @default.
• W4381936603 hasConceptScore W4381936603C139945424 @default.
• W4381936603 hasConceptScore W4381936603C144027150 @default.
• W4381936603 hasConceptScore W4381936603C165838908 @default.
• W4381936603 hasConceptScore W4381936603C2781067378 @default.
• W4381936603 hasConceptScore W4381936603C32198211 @default.
• W4381936603 hasConceptScore W4381936603C33923547 @default.
• W4381936603 hasConceptScore W4381936603C39432304 @default.
• W4381936603 hasConceptScore W4381936603C41008148 @default.
• W4381936603 hasConceptScore W4381936603C50644808 @default.
• W4381936603 hasConceptScore W4381936603C86803240 @default.
• W4381936603 hasLocation W43819366031 @default.
• W4381936603 hasOpenAccess W4381936603 @default.
• W4381936603 hasPrimaryLocation W43819366031 @default.
• W4381936603 hasRelatedWork W1986582023 @default.
• W4381936603 hasRelatedWork W2883749686 @default.
• W4381936603 hasRelatedWork W2899084033 @default.
• W4381936603 hasRelatedWork W3102363003 @default.
• W4381936603 hasRelatedWork W4289856193 @default.
• W4381936603 hasRelatedWork W4300978571 @default.
• W4381936603 hasRelatedWork W4312914540 @default.
• W4381936603 hasRelatedWork W4313448588 @default.
• W4381936603 hasRelatedWork W4313638343 @default.
• W4381936603 hasRelatedWork W4315864862 @default.
• W4381936603 hasVolume "211" @default.
• W4381936603 isParatext "false" @default.
• W4381936603 isRetracted "false" @default.
• W4381936603 workType "article" @default.